桥梁拉索表面缺陷图像检测关键技术的研究
|
摘要
随着桥梁交通建设的高速发展，大跨度和超大跨度桥梁的斜拉桥和悬索桥被广泛采用。在已建成并使用的这类桥梁中，拉索是其主要受力部件，拉索的可靠性和耐久性将直接关系到桥梁的安全和使用寿命。拉索外表有聚乙烯（PE）或者高密度聚乙烯（HDPE）保护层，但是拉索保护层长期暴露于自然环境中并承受交变载荷，极易发生腐蚀破坏，从而影响拉索的使用寿命，导致桥梁安全事故的发生。因此，对拉索表面缺陷的检测具有十分重要的意义。目前国内外对拉索表面保护层的主要检测方法有人工检测法和激光扫描法。这些方法存在效率低、成本高、智能化程度不足等局限。本文从此领域相关的迫切需求出发，开发了一个桥梁拉索表面缺陷的机器视觉检测系统，并围绕这个系统，深入研究了机器视觉系统的相关理论和关键技术，提出了桥梁拉索表面的分布式机器视觉缺陷检测和缺陷图像识别的方法，取得了较好的效果。针对系统采集的模糊缺陷图像，提出了基于非负支撑域递归逆滤波（NAS-RIF）和自适应全变分（Total Variation, TV）正则化盲图像恢复方法。为了快速有效地获得完整的拉索表面缺陷，提出基于Harris算子改进的尺度不变特征变换（SIFT）特征匹配算法对缺陷图像进行自动拼接。最后采用粒子群优化（Particle Swarm Optimization, PSO）算法来优化支持向量机（Support Vector Machine, SVM）模型并对拉索表面缺陷进行分类识别。本文的主要研究内容与成果如下：
1）提出了基于分布式机器视觉桥梁拉索表面缺陷检测与缺陷图像识别的方法。该方法首先通过爬行机器人装载分布式图像传感器、光源、嵌入式DSP硬件平台、位置传感器和存储设备等机器视觉系统沿拉索爬行，并采用4个分布式CCD图像传感器获取拉索表面四周的图像；然后以TI高性能DSP TMS320DM642（简称DM642）为核心处理器实时实现缺陷图像预处理、缺陷目标分割和缺陷初步判别等，并对初步判别的疑似缺陷进行存储；最后在PC机上通过图像去模糊和图像拼接等图像处理技术完成缺陷图像的识别。
2）对桥梁拉索表面缺陷图像预处理和缺陷提取方法的实时实现进行了研究。分析了表面缺陷图像的噪声类型及来源，并基于DM642嵌入式处理器缓存的特点，提出并改进中值滤波方法对拉索表面图像进行快速有效的滤波处理，同时，为了快速实时实现缺陷目标的初步判别，结合数学形态学（Mathematical Morphology）和改进的Sobel边缘检测算法，提出并采用一种基于MM-Sobel的图像分割方法提取缺陷图像中的缺陷目标。最后对缺陷目标进行判别，并将判别出的疑似缺陷图像及其位置信息进行存储。
3）针对机器视觉检测系统采集的模糊表面缺陷图像，分析了拉索表面图像模糊的模型，提出了一种将NAS-RIF与自适应全变分正则化相结合的图像盲复原算法。该算法针对原始NAS-RIF算法在低信噪比下对噪声敏感的问题，并结合图像退化和图像盲复原的机理，在原始NAS-RIF算法代价函数的基础上加入TV正则化约束项。为了有效地达到图像细节恢复和噪声抑制之间的平衡，通过最大后验概率自适应地调整全变分正则化参数，并采用优化最小化的共轭梯度迭代算法，提高算法的收敛速度。实验结果表明，文中算法的复原效果具有较好的适应性和有效性。
4）系统采用4个CCD摄像头分布在拉索表面一周获取图像，一个缺陷有可能分布在几幅图像中。为了识别完整的缺陷，需要对相应的缺陷图像进行自动拼接。图像匹配是图像拼接算法中十分关键的步骤，根据系统获取拉索表面图像的特征，提出了基于Harris算子改进的SIFT特征匹配算法对缺陷图像进行匹配。首先采用简洁有效的Harris算子提取特征点；然后根据检测系统采集缺陷图像的特点，简化SIFT算子的特征点主方向分配和匹配图像旋转等算法步骤，对特征点进行描述和匹配；最后融合匹配图像，得到相对完整的缺陷图像。实验结果表明，该方法大大降低了算法的复杂度，可以快速有效地获得完整的拉索表面缺陷。
5）拉索表面主要存在纵向开裂、横向开裂、表面侵蚀和疤坑孔洞等4类缺陷，本文基于特征提取和支持向量机算法对这4类缺陷进行分类识别。为了提高SVM分类识别率，采用粒子群优化算法来优化SVM模型的惩罚系数c和核函数参数g，即PSO-SVM算法。通过对拉索表面缺陷的分类识别实验，分类识别率达到了96.25%。实验结果表明，采用PSO-SVM对拉索表面缺陷进行分类识别具有较高的识别率和较快的识别速度。
论文重点对桥梁拉索表面缺陷图像检测关键技术的理论和实验进行研究。基于分布式机器视觉拉索表面缺陷检测系统，采用有效的缺陷图像预处理、缺陷目标分割和缺陷初步判别等图像处理技术，改善了机器视觉检测系统的实时性。探索适用的图像去模糊方法，图像拼接方法和分类识别算法等，提高了拉索表面缺陷识别的效果。本文的研究对机器视觉检测系统在桥梁拉索表面损伤检测和维护中的应用具有重要意义。
With the rapid development of bridge construction, long-span and super long-spancable-stayed bridges and suspension bridges were widely used. Cables are the mainstressed part in these bridges and their reliability and durability are directly related tothe safety and service life. The cables are packaged by polyethylene (PE) or highdensity polyethylene (HDPE) protective layer outside. However, the cables suffer fromthe long-term alternating loads, and they are exposed to the natural environment. Thecables suffer from corrosions, affecting the service life span and resulting in bridgesafety accidents. Therefore, the cable surface defect detection is of great significance. Atpresent, methods for cable surface defect detection are mainly based on artificial visualdetection and laser scanning. These methods have many limitations such as lowefficiency, high cost, and lack of intelligence. According to the urgent need in this field,there has been in-depth study of related theory and key technology of machine visionsystem in this paper. A distributed machine vision system for the bridge cable surfacedefect detection and defect image recognition are proposed. In view of the collectedblur defect images, we put forward a blind image restoration method based onnon-negative domain support recursive inverse filter (NAS-RIF) and adaptive totalvariation (TV) regularization. In order to quickly and efficiently get the complete cablesurface defects, we proposed an improved scale invariant feature transform （SIFT）feature matching algorithm for automatic stitching. Finally, particle swarm optimization(PSO) algorithm is adopted to optimize the support vector machine（SVM）model. Thismodel is employed to classify the cable surface defects. The main research contents andcontributions are as follows.
1）A distributed machine vision system for the bridge cable surface defect detectionand defect image recognition methods were proposed. Firstly, the climb robot loadingdistributed image sensors, a light source, an embedded DSP hardware platform, positionsensors, storage devices, four CCD image sensors distributed around the cable wereused to obtain the cable surface images. Then TI high-performance DSPTMS320DM642(DM642) was employed as the core processor to achieve real-timedefect image preprocessing, defect object segmentation, defect preliminaryidentification, and preliminary identification of defects in storage. Finally, imagedeblurring and image stitching were processed on peasonal computer (PC) to achieve the defect image recognition.
2）The real-time realization methods of surface defect image preprocessing anddefect target extraction have been studied. By Analyzing the noise types and sources ofsurface defect images, an improved median filtering method based on the characteristicsof the embedded processor cache of DM642was proposed for cable surface imagefiltering processing. To realize rapid real-time preliminary identification of defect target,mathematical morphology (MM) and improved Sobel-edge-detection-algorithmcombined to a MM-Sobel image segmentation method was proposed and adopted toextract defect targets of defect images. Finally, the preliminary identification of thedefect was fulfilled. Moreover, defect images and their location information werestored.
3）In view of blur surface defect images collected by the machine vision inspectionsystem, the blur models were analyzed. Thus, a blind image restoration algorithm whichcombined NAS-RIF and adaptive TV regularization was proposed. In this algorithm, wecombined with the mechanism of image degradation and image blind restorationmethods. In view of the original NAS-RIF algorithm being sensitive to noise problemsunder low signal-to-noise ratio, we added TV regularization constraint item to the costfunction of the original NAS-RIF algorithm. In order to effectively achieve the balancebetween image detail recovery and noise suppression, the total variation regularizationparameter was adjusted adaptively by maximum a posteriori probability. TheMajorization-minimization (MM) method and conjugate gradient iterative algorithmwere adopted to improve the rate of convergence of the algorithm. The experimentalresults indicated that the algorithm has good adaptability and effectiveness.
4）The inspection system used4CCD cameras located around the cable to obtainthe cable surface images, a surface defect may be distributed in several images. In orderto identify the complete defect, it need automatic stitching on the corresponding defectimages. Image matching is a crucial step in image mosaic algorithm. According to thecharacteristics of the system for cable surface image, an improved SIFT featurematching algorithm was proposed. First, simple and effective Harris operator was usedto extract feature points. Then, according to the characteristics of the collected defectimages, the main direction assignment of the feature point and the rotation of thematching images were simplified in SIFT algorithm. Finally, the complete defect imagewas obtained by fusing the matching images. The experimental results show that thismethod greatly reduces the complexity of the SIFT algorithm and it can quickly and efficiently get the complete cable surface defects.
5）Longitudinal cracks, transverse cracks, surface erosion, and scarring pit holesare the mainly categories scar defects in cable surface. Feature extraction and supportvector machine (SVM)are employed to classify these defects. In order to improve theSVM classification recognition rate, this paper uses the particle swarm optimization(PSO) algorithm to optimize the punish coefficient c and the kernel functionparameter g of the SVM model, namely the PSO-SVM algorithm. Through theexperiments for surface defect classification and recognition, classification recognitionrate reaches96.25%, the results show that PSO-SVM has high recognition rate and fastrecognition speed.
The thesis focused on theoretical and experimental studies of image detection keytechniques for the bridge cable surface defect. The real-time performance of themachine vision inspection system was improved by using effective defect imagepreprocessing, defect object segmentation and defect preliminary discriminationalgorithms. To explore the applicable image deblurring algorithm, image stitchingmethod and classification recognition algorithm, the effect of the cable surface defectrecognition was also improved. In this thesis, the research on surface damage detectionand maintenance for the bridge cables based on machine vision detection system was ofgreat significance.
1）提出了基于分布式机器视觉桥梁拉索表面缺陷检测与缺陷图像识别的方法。该方法首先通过爬行机器人装载分布式图像传感器、光源、嵌入式DSP硬件平台、位置传感器和存储设备等机器视觉系统沿拉索爬行，并采用4个分布式CCD图像传感器获取拉索表面四周的图像；然后以TI高性能DSP TMS320DM642（简称DM642）为核心处理器实时实现缺陷图像预处理、缺陷目标分割和缺陷初步判别等，并对初步判别的疑似缺陷进行存储；最后在PC机上通过图像去模糊和图像拼接等图像处理技术完成缺陷图像的识别。
2）对桥梁拉索表面缺陷图像预处理和缺陷提取方法的实时实现进行了研究。分析了表面缺陷图像的噪声类型及来源，并基于DM642嵌入式处理器缓存的特点，提出并改进中值滤波方法对拉索表面图像进行快速有效的滤波处理，同时，为了快速实时实现缺陷目标的初步判别，结合数学形态学（Mathematical Morphology）和改进的Sobel边缘检测算法，提出并采用一种基于MM-Sobel的图像分割方法提取缺陷图像中的缺陷目标。最后对缺陷目标进行判别，并将判别出的疑似缺陷图像及其位置信息进行存储。
3）针对机器视觉检测系统采集的模糊表面缺陷图像，分析了拉索表面图像模糊的模型，提出了一种将NAS-RIF与自适应全变分正则化相结合的图像盲复原算法。该算法针对原始NAS-RIF算法在低信噪比下对噪声敏感的问题，并结合图像退化和图像盲复原的机理，在原始NAS-RIF算法代价函数的基础上加入TV正则化约束项。为了有效地达到图像细节恢复和噪声抑制之间的平衡，通过最大后验概率自适应地调整全变分正则化参数，并采用优化最小化的共轭梯度迭代算法，提高算法的收敛速度。实验结果表明，文中算法的复原效果具有较好的适应性和有效性。
4）系统采用4个CCD摄像头分布在拉索表面一周获取图像，一个缺陷有可能分布在几幅图像中。为了识别完整的缺陷，需要对相应的缺陷图像进行自动拼接。图像匹配是图像拼接算法中十分关键的步骤，根据系统获取拉索表面图像的特征，提出了基于Harris算子改进的SIFT特征匹配算法对缺陷图像进行匹配。首先采用简洁有效的Harris算子提取特征点；然后根据检测系统采集缺陷图像的特点，简化SIFT算子的特征点主方向分配和匹配图像旋转等算法步骤，对特征点进行描述和匹配；最后融合匹配图像，得到相对完整的缺陷图像。实验结果表明，该方法大大降低了算法的复杂度，可以快速有效地获得完整的拉索表面缺陷。
5）拉索表面主要存在纵向开裂、横向开裂、表面侵蚀和疤坑孔洞等4类缺陷，本文基于特征提取和支持向量机算法对这4类缺陷进行分类识别。为了提高SVM分类识别率，采用粒子群优化算法来优化SVM模型的惩罚系数c和核函数参数g，即PSO-SVM算法。通过对拉索表面缺陷的分类识别实验，分类识别率达到了96.25%。实验结果表明，采用PSO-SVM对拉索表面缺陷进行分类识别具有较高的识别率和较快的识别速度。
论文重点对桥梁拉索表面缺陷图像检测关键技术的理论和实验进行研究。基于分布式机器视觉拉索表面缺陷检测系统，采用有效的缺陷图像预处理、缺陷目标分割和缺陷初步判别等图像处理技术，改善了机器视觉检测系统的实时性。探索适用的图像去模糊方法，图像拼接方法和分类识别算法等，提高了拉索表面缺陷识别的效果。本文的研究对机器视觉检测系统在桥梁拉索表面损伤检测和维护中的应用具有重要意义。
With the rapid development of bridge construction, long-span and super long-spancable-stayed bridges and suspension bridges were widely used. Cables are the mainstressed part in these bridges and their reliability and durability are directly related tothe safety and service life. The cables are packaged by polyethylene (PE) or highdensity polyethylene (HDPE) protective layer outside. However, the cables suffer fromthe long-term alternating loads, and they are exposed to the natural environment. Thecables suffer from corrosions, affecting the service life span and resulting in bridgesafety accidents. Therefore, the cable surface defect detection is of great significance. Atpresent, methods for cable surface defect detection are mainly based on artificial visualdetection and laser scanning. These methods have many limitations such as lowefficiency, high cost, and lack of intelligence. According to the urgent need in this field,there has been in-depth study of related theory and key technology of machine visionsystem in this paper. A distributed machine vision system for the bridge cable surfacedefect detection and defect image recognition are proposed. In view of the collectedblur defect images, we put forward a blind image restoration method based onnon-negative domain support recursive inverse filter (NAS-RIF) and adaptive totalvariation (TV) regularization. In order to quickly and efficiently get the complete cablesurface defects, we proposed an improved scale invariant feature transform （SIFT）feature matching algorithm for automatic stitching. Finally, particle swarm optimization(PSO) algorithm is adopted to optimize the support vector machine（SVM）model. Thismodel is employed to classify the cable surface defects. The main research contents andcontributions are as follows.
1）A distributed machine vision system for the bridge cable surface defect detectionand defect image recognition methods were proposed. Firstly, the climb robot loadingdistributed image sensors, a light source, an embedded DSP hardware platform, positionsensors, storage devices, four CCD image sensors distributed around the cable wereused to obtain the cable surface images. Then TI high-performance DSPTMS320DM642(DM642) was employed as the core processor to achieve real-timedefect image preprocessing, defect object segmentation, defect preliminaryidentification, and preliminary identification of defects in storage. Finally, imagedeblurring and image stitching were processed on peasonal computer (PC) to achieve the defect image recognition.
2）The real-time realization methods of surface defect image preprocessing anddefect target extraction have been studied. By Analyzing the noise types and sources ofsurface defect images, an improved median filtering method based on the characteristicsof the embedded processor cache of DM642was proposed for cable surface imagefiltering processing. To realize rapid real-time preliminary identification of defect target,mathematical morphology (MM) and improved Sobel-edge-detection-algorithmcombined to a MM-Sobel image segmentation method was proposed and adopted toextract defect targets of defect images. Finally, the preliminary identification of thedefect was fulfilled. Moreover, defect images and their location information werestored.
3）In view of blur surface defect images collected by the machine vision inspectionsystem, the blur models were analyzed. Thus, a blind image restoration algorithm whichcombined NAS-RIF and adaptive TV regularization was proposed. In this algorithm, wecombined with the mechanism of image degradation and image blind restorationmethods. In view of the original NAS-RIF algorithm being sensitive to noise problemsunder low signal-to-noise ratio, we added TV regularization constraint item to the costfunction of the original NAS-RIF algorithm. In order to effectively achieve the balancebetween image detail recovery and noise suppression, the total variation regularizationparameter was adjusted adaptively by maximum a posteriori probability. TheMajorization-minimization (MM) method and conjugate gradient iterative algorithmwere adopted to improve the rate of convergence of the algorithm. The experimentalresults indicated that the algorithm has good adaptability and effectiveness.
4）The inspection system used4CCD cameras located around the cable to obtainthe cable surface images, a surface defect may be distributed in several images. In orderto identify the complete defect, it need automatic stitching on the corresponding defectimages. Image matching is a crucial step in image mosaic algorithm. According to thecharacteristics of the system for cable surface image, an improved SIFT featurematching algorithm was proposed. First, simple and effective Harris operator was usedto extract feature points. Then, according to the characteristics of the collected defectimages, the main direction assignment of the feature point and the rotation of thematching images were simplified in SIFT algorithm. Finally, the complete defect imagewas obtained by fusing the matching images. The experimental results show that thismethod greatly reduces the complexity of the SIFT algorithm and it can quickly and efficiently get the complete cable surface defects.
5）Longitudinal cracks, transverse cracks, surface erosion, and scarring pit holesare the mainly categories scar defects in cable surface. Feature extraction and supportvector machine (SVM)are employed to classify these defects. In order to improve theSVM classification recognition rate, this paper uses the particle swarm optimization(PSO) algorithm to optimize the punish coefficient c and the kernel functionparameter g of the SVM model, namely the PSO-SVM algorithm. Through theexperiments for surface defect classification and recognition, classification recognitionrate reaches96.25%, the results show that PSO-SVM has high recognition rate and fastrecognition speed.
The thesis focused on theoretical and experimental studies of image detection keytechniques for the bridge cable surface defect. The real-time performance of themachine vision inspection system was improved by using effective defect imagepreprocessing, defect object segmentation and defect preliminary discriminationalgorithms. To explore the applicable image deblurring algorithm, image stitchingmethod and classification recognition algorithm, the effect of the cable surface defectrecognition was also improved. In this thesis, the research on surface damage detectionand maintenance for the bridge cables based on machine vision detection system was ofgreat significance.
引文
[1]刘强.模拟酸雨溶液中大跨度斜拉桥拉索钢绞线腐蚀行为研究[D].重庆：重庆大学，2007.
[2]经柏林,谢华鸾.斜拉桥拉索研究综述[J].中国市政工程,2003,(6):22-24+68.
[3]张学元,安百刚,韩恩厚,等.酸雨对材料的腐蚀/冲刷研究现状[J].腐蚀科学与防护技术,2002,14(3):157-160.
[4]王力力,易伟建.斜拉索的腐蚀案例与分析[J].中南公路工程,2007,32(1):93-98.
[5]王应军.大型斜拉桥长期健康监测系统的关键技术研究[D].武汉：武汉理工大学，2006.
[6] M. Bloomstine, O. S., J. Thomsen. Conference on operation, maintenance and rehabilitationof large infrastructure projects: main cable corrosion by dehumidification[J]. Denmark:Copenhagen,2006.
[7] B. Tang, J. K., X. Wang, L. Chen. Surface inspection system of steel strip based on machinevision[C].2009First International Workshop on Database Technology and Applications,2009,359-362.
[8]陈大华.桥梁拉索钢丝模拟酸雨溶液中腐蚀行为研究及拉索寿命预测[D].重庆：重庆大学，2009.
[9]武新军,贲安然,徐江.桥梁缆索金属损伤无损检测方法[J].无损检测,2012,(04):12-16.
[10] Sloane, M. J. D.,Betti, R.,Marconi, G., etc. Experimental Analysis of a NondestructiveCorrosion Monitoring System for Main Cables of Suspension Bridges[J]. J. Bridge Eng.,2013,18(7):653-662.
[11]张家梁,吕恬生,郭剑鹰.在役缆索自动检测[J].无损检测,2003,25(2):99-101.
[12] Blasco, J.,Aleixos, N.,Moltó, E. Computer vision detection of peel defects in citrus by meansof a region oriented segmentation algorithm[J]. Journal of Food Engineering,2007,81(3):535-543.
[13] Meylani, R.,Ertuzun, A.,Er il, A. Texture defect detection using the adaptive two-dimensionallattice filter[C]. In Image Processing,1996. Proceedings., International Conference on,1996:165-168.
[14] Patel, D.,Davies, E. R.,Hnnah, I. The use of convolution operators for detecting contaminantsin food images[J]. Pattern Recognition,1996,29(6):1019-1029.
[15]龙跃,郑皆连,吴振.桥梁拉索典型病害事故的调查与研究[J].预应力技术,2010,(6):28-31+38.
[16] Funck, J. W.,Zhong, Y.,Butler, D. A., etc. Image segmentation algorithms applied to wooddefect detection[J]. Computers and Electronics in Agriculture,2003,41(1–3):157-179.
[17] Steiner, D.,Katz, R. Measurement techniques for the inspection of porosity flaws on machinedsurfaces[J]. Journal of computing and information science in engineering,2007,7(1):85-94.
[18] Kleynen, O.,Leemans, V.,Destain, M. F. Development of a multi-spectral vision system for thedetection of defects on apples[J]. Journal of Food Engineering,2005,69(1):41-49.
[19] Kumar, A. Neural network based detection of local textile defects[J]. Pattern Recognition,2003,36(7):1645-1659.
[20] Ahmed, R.,Sutcliffe, M. P. F. Identification of surface features on cold-rolled stainless steelstrip[J]. Wear,2000,244(1–2):60-70.
[21] Iyer, S.,Sinha, S. K. A robust approach for automatic detection and segmentation of cracks inunderground pipeline images[J]. Image and Vision Computing,2005,23(10):921-933.
[22] Torres, V.,Quek, S.,Fernandes, B., etc. Development of a scanning system to detect corrosionin wire bundles and pipes using magnetoresistive sensors[J]. Insight-Non-Destructive Testingand Condition Monitoring,2011,53(2):82-84.
[23] Christen, R.,Bergamini, A.,Motavalli, M. Influence of steel wrapping on magneto-inductivetesting of the main cables of suspension bridges[J]. NDT&E International,2009,42(1):22-27.
[24] Paulson, P. O. Continuous acoustic monitoring of suspension bridges and cable stays[C]. InNon-Destructive Evaluation Techniques for Aging Infrastructure&Manufacturing,1998:205-213.
[25] Mehrabi, A.,Telang, N. Cable-stayed bridge performance evaluation—Lessons from thefield[C]. In Proceedings of the Structures Congress and Exposition,2003.
[26]张春雷,李国平,雷洛.桥梁拉索HDPE护套日光老化试验[J].哈尔滨工业大学学报,2012,44(8):91-95.
[27] Suzumura, K.,Nakamura, S.-i. Environmental factors affecting corrosion of galvanized steelwires[J]. Journal of materials in civil engineering,2004,16(1):1-7.
[28] Vermaas, G. W. Corrosion and embrittlement of high-strength steel bridge wires[M].2001.
[29]徐俊,陈惟珍.石门大桥拉索病害检测与分析[J].钢结构,2007,22(6):81-84.
[30]杨少军.桥梁拉索体系损伤的检测和监测方法[J].公路交通技术,2005,(3):130-134.
[31] Wu, E.,Ke, Y.,Du, B. Noncontact laser inspection based on a PSD for the inner surface ofminidiameter pipes[J]. Instrumentation and Measurement, IEEE Transactions on,2009,58(7):2169-2173.
[32] Lee, J.-J.,Kim, J.-M.,Ahn, S.-S., etc. Development of a cable exciter to evaluate dampingratios of a stay cable[J]. KSCE Journal of Civil Engineering,2010,14(3):363-370.
[33] Ho, H.-N.,Kim, K.-D.,Park, Y.-S., etc. An efficient image-based damage detection for cablesurface in cable-stayed bridges[J]. NDT&E International,2013,(58):18-23.
[34]任可.基于嵌入式处理平台的桥梁拉索表面缺陷检测技术研究[D].重庆：重庆大学，2007.
[35]贺付亮.基于图像识别的桥梁拉索表面缺陷检测系统设计[D].重庆：重庆大学，2006.
[36]郑李明,王兴松.斜拉桥拉索径向畸变CCD图像的边缘检测与图像提取[J].机械制造与自动化,2008,37(6):107-110.
[37]王生治.基于DSP的缆索表面图像采集与传输系统设计与研究[D].重庆：重庆大学，2010.
[38]孙洪超.蛇形机器人步态生成方法及在桥梁缆索表面检测中的应用研究[D].重庆：华南理工大学，2012.
[39] Moreda, G.,Ortiz-Ca avate, J.,García-Ramos, F. J., etc. Non-destructive technologies for fruitand vegetable size determination–a review[J]. Journal of Food Engineering,2009,92(2):119-136.
[40] Rosati, G.,Boschetti, G.,Biondi, A., etc. Real-time defect detection on highly reflective curvedsurfaces[J]. Optics and Lasers in Engineering,2009,47(3–4):379-384.
[41]李长乐.冷轧带钢表面缺陷图像检测关键技术的研究[D].哈尔滨：哈尔滨工业大学，2009.
[42] Lin, H.-D. Computer-aided visual inspection of surface defects in ceramic capacitor chips[J].Journal of Materials Processing Technology,2007,189(1–3):19-25.
[43] Byrne, G.,Sheahan, C. Inline Color Vision for Specific Electroplating Defect Identification[J].Journal of Manufacturing Processes,2006,8(2):133-143.
[44] Marr, D. Vision: A computational investigation into the human representation and processingof visual information, Henry Holt and Co[J]. Inc., New York, NY,1982.
[45] Malamas, E. N.,Petrakis, E. G. M.,Zervakis, M., etc. A survey on industrial vision systems,applications and tools[J]. Image and Vision Computing,2003,21(2):171-188.
[46] Guo, W.,Soibelman, L.,Garrett Jr, J. H. Automated defect detection for sewer pipelineinspection and condition assessment[J]. Automation in Construction,2009,18(5):587-596.
[47] Kaixiang, P.,Xuli, Z. Classification technology for automatic surface defects detection of steelstrip based on improved BP algorithm[C]. In Natural Computation,2009. ICNC'09. FifthInternational Conference on,2009:110-114.
[48] Kumar, A. Computer-vision-based fabric defect detection: a survey[J]. Industrial Electronics,IEEE Transactions on,2008,55(1):348-363.
[49] Yang, T.,Wang, L.,Zheng, D., etc. Image Acquisition and Segmentation for Ceramic BearingBall Surface Inspection System[C]. In Intelligent Control and Automation,2006. WCICA2006. The Sixth World Congress on,2006:8444-8447.
[50]贾云得.机器视觉[M].北京:科学出版社,2000.
[51] Liu, Y.,Yu, F. Automatic inspection system of surface defects on optical IR-CUT filter basedon machine vision[J]. Optics and Lasers in Engineering,2014,55243-257.
[52] Cubero, S.,Aleixos, N.,Albert, F., etc. Optimised computer vision system for automaticpre-grading of citrus fruit in the field using a mobile platform[J]. Precision Agriculture,2014,15(1):80-94.
[53] Suresh, B. R. A real-time automated visual inspection system for hot steel slabs[J]. IEEETrans. Pattern Analysis Mach. Intell.,1983,5(6):563-572.
[54]戴卫东,安百光. Parsytec自动表面缺陷检查系统在冷轧连续退火线上的应用[J].冶金自动化,2009,33(2):47-51.
[55] Park, D. G.,Levoi, M. P.,Van Haneghem, A. Practical application of on-line hot stripinspection system at Hoogovens[J]. Iron Steel Eng.(USA),1995,72(7):40-43.
[56] Jouet, J. Defect classification in surface inspection of strip steel[J]. Steel Times,1992,16(5):214-216.
[57]王斌,罗志勇,刘栋玉,等.带钢边缘缺陷实时图象识别与宽度测量算法[J].无损检测,1997,19(7):188-190.
[58]罗志勇，刘栋玉，江涛，王斌.新型冷轧带钢表面缺陷在线检测系统[J].华中理工大学学报,1996,24(1):75-78.
[59]王斌,罗志勇,刘栋玉,等.带钢表面重皮缺陷在线图像识别算法研究[J].华中理工大学学报,1996,24(8):36-38.
[60]谢华锟.第八届中国国际机床展览会量仪展品述评——数字化测量技术先进制造技术基础[J].工具技术,2003,37(7):12-18.
[61]刘红冰,康戈文.基于神经网络的冷轧带钢表面缺陷检测[J].中国图象图形学报,2005,10(10):1310-1313.
[62]王宏,朱德生,唐威.一种基于灰度投影的带钢表面缺陷检测算法[J].东北大学学报(自然科学版),2008,29(3):375-377.
[63] Tsai, D.-M.,Lai, S.-C. Defect detection in periodically patterned surfaces using independentcomponent analysis[J]. Pattern Recognition,2008,41(9):2812-2832.
[64] Xie, X. A review of recent advances in surface defect detection using texture analysistechniques[J]. Electronic Letters on Computer Vision and Image Analysis,2008,7(3):1-22.
[65] Radovan, S.,Papadopoulos, G. D.,Georgoudakis, M., etc. Vision system for finished fabricinspection[C]. In Electronic Imaging2002,2002:97-103.
[66] Karimi, M. H.,Asemani, D. Surface defect detection in tiling Industries using digital imageprocessing methods: Analysis and evaluation[J]. ISA Transactions,2014,(In press).
[67] Guzman, E.,Baeten, V.,Pierna, J. A. F., etc. Infrared machine vision system for the automaticdetection of olive fruit quality[J]. Talanta,2013,116894-898.
[68] Mendes, A. d. O.,Fiadeiro, P. T.,Matos Ramos, A. M., etc. Development of an optical systemfor analysis of the ink-paper interaction[J]. Machine Vision and Applications,2013,24(8):1733-1750.
[69] Chiou, Y.-C.,Li, W.-C. Flaw detection of cylindrical surfaces in PU-packing by using machinevision technique[J]. Measurement,2009,42(7):989-1000.
[70] Jia, H.,Murphey, Y. L.,Shi, J., etc. An intelligent real-time vision system for surface defectdetection[C]. In Pattern Recognition,2004. ICPR2004. Proceedings of the17th InternationalConference on,2004:239-242.
[71]章毓晋.图像处理[M].北京:清华大学出版社,2006.
[72] Lucat, L.,Siohan, P.,Barba, D. Adaptive and global optimization methods for weighted vectormedian filters[J]. Signal Processing: Image Communication,2002,17(7):509-524.
[73] Lukac, R.,Smolka, B.,Plataniotis, K. N. Sharpening vector median filters[J]. SignalProcessing,2007,87(9):2085-2099.
[74] Yu, J.,Wang, Y.,Shen, Y. Noise reduction and edge detection via kernel anisotropicdiffusion[J]. Pattern Recognition Letters,2008,29(10):1496-1503.
[75] Candès, E. J.,Donoho, D. L. Continuous curvelet transform: I. Resolution of the wavefrontset[J]. Applied and Computational Harmonic Analysis,2005,19(2):162-197.
[76]冯鹏,米德伶,潘英俊,等.改进的Curvelet变换图像降噪方法[J].光电工程,2005,32(9):67-70+78.
[77] Biswas, A.,Cresswell, H. P.,Rossel, R. A. V., etc. Curve let transform to study scale-dependentanisotropic soil spatial variation[J]. Geoderma,2014,213589-599.
[78] Lian, Q.-S.,Chen, S.-Z. The Translation Invariant Contourlet-like Transform for ImageDenoising[J]. Acta Automatica Sinica,2009,35(5):505-508.
[79] Dai, S.-W.,Sun, Y.-K.,Tian, X.-L., etc. Image denoising based on complex contourlettransform[C]. In Wavelet Analysis and Pattern Recognition,2007. ICWAPR'07. InternationalConference on,2007:1742-1747.
[80] Guo, D. F.,Chen, J. B. The Application of Contourlet Transform to Image Denoising. In Ceis2011, Ran, C.,Yang, G., Eds. Elsevier Science Bv: Amsterdam,2011; Vol.15.
[81] Lazzaro, D.,Montefusco, L. B. Edge-preserving wavelet thresholding for image denoising[J].Journal of Computational and Applied Mathematics,2007,210(1–2):222-231.
[82] De Backer, S.,Pi urica, A.,Huysmans, B., etc. Denoising of multicomponent images usingwavelet least-squares estimators[J]. Image and Vision Computing,2008,26(7):1038-1051.
[83] Dai, M. H. The Development of Wavelet Transform and Its Application in Image Denoise. InManufacturing Process and Equipment, Pts1-4, Liu, X. H.,Zhang, K. F.,Li, M. Z., Eds. TransTech Publications Ltd: Stafa-Zurich,2013; Vol.694-697,2003-2008.
[84] Bettahar, S.,Stambouli, A. B. Shock filter coupled to curvature diffusion for image denoisingand sharpening[J]. Image and Vision Computing,2008,26(11):1481-1489.
[85]于舒春,闫继宏,赵杰,等.立体视觉的四阶段预处理方法[J].吉林大学学报(工学版),2007,37(3):651-654.
[86] Peter, Z.,Bousson, V.,Bergot, C., etc. A constrained region growing approach based onwatershed for the segmentation of low contrast structures in bone micro-CT images[J]. PatternRecognition,2008,41(7):2358-2368.
[87] Damiand, G.,Resch, P. Split-and-merge algorithms defined on topological maps for3D imagesegmentation[J]. Graphical Models,2003,65(1):149-167.
[88] Chung, K.-L.,Yang, W.-J.,Yan, W.-M. Efficient edge-preserving algorithm for color contrastenhancement with application to color image segmentation[J]. Journal of VisualCommunication and Image Representation,2008,19(5):299-310.
[89] Beucher, S.,Lantuejoul, C. Use of watersheds in contour detection[J].1979.
[90] Schmeelk, J. Wavelet transforms and edge detectors on digital images[J]. Mathematical andComputer Modelling,2005,41(13):1469-1478.
[91] Zhang, Z.,Ma, S.,Liu, H., etc. An edge detection approach based on directional wavelettransform[J]. Computers&Mathematics with Applications,2009,57(8):1265-1271.
[92] Villegas, O. O. V.,Elias, R. P.,Villela, P. R., etc. Edge preserving lossy image compressionwith wavelets and contourlets[C]. In Electronics, Robotics and Automotive MechanicsConference,2006,2006:3-8.
[93] Ling, L.,Peikang, H.,Xiaohu, W., etc. Image edge detection based on beamlet transform[J].Systems Engineering and Electronics, Journal of,2009,20(1):1-5.
[94] Wang, L.,Pan, C. Robust level set image segmentation via a local correntropy-based K-meansclustering[J]. Pattern Recognition,2014,47(5):1917-1925.
[95] Jacquey, F.,Comby, F.,Strauss, O. Fuzzy edge detection for omnidirectional images[J]. FuzzySets and Systems,2008,159(15):1991-2010.
[96]焦李成,谭山.图像的多尺度几何分析:回顾和展望[J].电子学报,2003,32(S1):1975-1981.
[97] Shih, F. Y.,Zhang, K. Locating object contours in complex background using improvedsnakes[J]. Computer Vision and Image Understanding,2007,105(2):93-98.
[98] Cabezas, M. G.,Bateni, A.,Montanero, J. M., etc. A new method of image processing in theanalysis of axisymmetric drop shapes[J]. Colloids and Surfaces A: Physicochemical andEngineering Aspects,2005,255(1–3):193-200.
[99] Yen, J.-C.,Chang, F.-J.,Chang, S. A new criterion for automatic multilevel thresholding[J].Image Processing, IEEE Transactions on,1995,4(3):370-378.
[100] Otsu, N. A threshold selection method from gray-level histograms[J]. Automatica,1975,11(285-296):23-27.
[101] Rosenfeld, A.,De La Torre, P. Histogram concavity analysis as an aid in threshold selection[J].Systems, Man and Cybernetics, IEEE Transactions on,1983,(2):231-235.
[102] Wu, S.,Amin, A. Automatic thresholding of gray-level using multistage approach[C]. InDocument Analysis and Recognition,2003. Proceedings. Seventh International Conference on,2003:493-497.
[103] Zhang, X.-P.,Desai, M. D. Wavelet based automatic thresholding for image segmentation[C].In Image Processing,1997. Proceedings., International Conference on,1997:224-227.
[104]田捷,韩博闻,王岩,等.模糊C-均值聚类法在医学图像分析中的应用[J].软件学报,2001,12(11):1623-1629.
[105] Kapur, J. N.,Sahoo, P. K.,Wong, A. K. C. A new method for gray-level picture thresholdingusing the entropy of the histogram[J]. Computer Vision, Graphics, and Image Processing,1985,29(3):273-285.
[106]陈黎,黄心汉,王敏,等.带钢缺陷图像的自动阈值分割研究[J].计算机工程与应用,2002,38(7):244-246.
[107]聂方彦.图像阈值化与目标分割方法中的若干问题研究[D].重庆：重庆大学，2010.
[108]孟祥迪,陈升来,郭静寰.基于图像边缘信息和Fisher准则的钢板表面缺陷分割研究[J].光学技术,2007,33(3):382-385.
[109]赵松青.带钢表面孔洞实时检测系统及相关技术研究[D].武汉：华中科技大学，2005.
[110]冯宇平.图像快速配准与自动拼接技术研究[D].长春：中国科学院研究生院(长春光学精密机械与物理研究所)，2010.
[111] Wexler, Y.,Shechtman, E.,Irani, M. Space-time video completion[C]. In Computer Vision andPattern Recognition,2004. CVPR2004. Proceedings of the2004IEEE Computer SocietyConference on,2004,(1): I-120-I-127.
[112]吴琼玉,周东翔,蔡宣平.基于图像序列的虚拟场景重建和漫游[J].中国图象图形学报,2006,11(1):113-118.
[113] Szeliski, R.,Shum, H.-Y. Creating full view panoramic image mosaics and environmentmaps[C]. In Proceedings of the24th annual conference on Computer graphics and interactivetechniques,1997:251-258.
[114]张红颖,张加万,孙济洲.改进Demons算法的非刚性医学图像配准[J].光学精密工程,2007,15(1):145-150.
[115]王华,王龙山,高金刚,等.面向汽车车架纵梁检测的序列图像快速拼接算法[J].光学精密工程,2008,16(3):531-536.
[116] Brown, L. G. A survey of image registration techniques[J]. ACM computing surveys (CSUR),1992,24(4):325-376.
[117] Szeliski, R. Video mosaics for virtual environments[J]. Computer Graphics and Applications,IEEE,1996,16(2):22-30.
[118] Yun Tian, G.,Gledhill, D.,Taylor, D. Comprehensive interest points based imaging mosaic[J].Pattern Recognition Letters,2003,24(9–10):1171-1179.
[119] M. Brown, D. G. L. Recognising panoramas[C]. In Proceedings of IEEE InternationalConference on Computer Vision,2003:1218-1225.
[120] Ha, S. J.,Koo, H.,Lee, S. H., etc. Panorama mosaic optimization for mobile camera systems[J].Consumer Electronics, IEEE Transactions on,2007,53(4):1217-1225.
[121]王小睿,吴信才.遥感多图象的自动配准方法[J].中国图象图形学报,1997,2(10):39-43.
[122]荆根强,张天序,杨卫东,等.局部自适应序列图像拼接算法[J].红外与激光工程,2004,33(6):622-625.
[123]李晓明,赵训坡,郑链,等.基于Fourier-Mellin变换的图像配准方法及应用拓展[J].计算机学报,2006,29(3):466-472.
[124]朱云芳,叶秀清,顾伟康.视频序列的全景图拼接技术[J].中国图象图形学报,2006,11(8):1150-1155.
[125]杨占龙,郭宝龙.基于兴趣点伪泽尼克矩的图像拼接[J].中国激光,2007,34(11):1548-1552.
[126] Banham, M. R.,Katsaggelos, A. K. Digital image restoration[J]. Signal Processing Magazine,IEEE,1997,14(2):24-41.
[127]邹谋炎.反卷积和信号复原[M].北京:国防工业出版社,2001.
[128] Joshi, M. V.,Chaudhuri, S. Joint blind restoration and surface recovery in photometricstereo[J]. JOSA A,2005,22(6):1066-1076.
[129] Hall, P.,Qiu, P. Blind deconvolution and deblurring in image analysis[J]. Statistica Sinica,2007,17(4):1483.
[130] Biemond, J.,Tekalp, A. M.,Lagendijk, R. L. Maximum likelihood image and bluridentification: a unifying approach[J]. Optical Engineering,1990,29(5):422-435.
[131] Reeves, S. J.,Mersereau, R. M. Blur identification by the method of generalizedcross-validation[J]. Image Processing, IEEE Transactions on,1992,1(3):301-311.
[132] Qidwai, U.,Chen, C.-H. Blind image restoration for ultrasonic C-Scan using constrained2D-HOS[C]. In Acoustics, Speech, and Signal Processing,2001. Proceedings.(ICASSP'01).2001IEEE International Conference on,2001:3405-3408.
[133] Ayers, G.,Dainty, J. C. Iterative blind deconvolution method and its applications[J]. Opticsletters,1988,13(7):547-549.
[134] McCallum, B. C. Blind deconvolution by simulated annealing[J]. Optics Communications,1990,75(2):101-105.
[135] Kundur, D.,Hatzinakos, D. A novel blind deconvolution scheme for image restoration usingrecursive filtering[J]. Signal Processing, IEEE Transactions on,1998,46(2):375-390.
[136] You, Y.-L., Kaveh, M.. A regularization approach to join blur identification and imagerestoration[J]. IEEE Transactions on Image Processing,1996,5(3):416-428.
[137] You, Y.-L.,Kaveh, M. Anisotropic blind image restoration[C]. In Image Processing,1996.Proceedings., International Conference on,1996:461-464.
[138] Chan, T. F.,Wong, C.-K. Total variation blind deconvolution[J]. Image Processing, IEEETransactions on,1998,7(3):370-375.
[139] Vogel, C. R.,Oman, M. E. Iterative methods for total variation denoising[J]. SIAM Journal onScientific Computing,1996,17(1):227-238.
[140] Shen, J. On the foundations of vision modeling: I. Weber’s law and Weberized TVrestoration[J]. Physica D: Nonlinear Phenomena,2003,175(3–4):241-251.
[141]张航,罗大庸.一种改进的全变差盲图像复原方法[J].电子学报,2005,33(7):1288-1290.
[142] He, L.,Marquina, A.,Osher, S. J. Blind deconvolution using TV regularization and Bregmaniteration[J]. International Journal of Imaging Systems and Technology,2005,15(1):74-83.
[143] Money, J. H.,Kang, S. H. Total variation minimizing blind deconvolution with shock filterreference[J]. Image and Vision Computing,2008,26(2):302-314.
[144] Molina, R.,Mateos, J.,Katsaggelos, A. K. Blind deconvolution using a variational approach toparameter, image, and blur estimation[J]. Image Processing, IEEE Transactions on,2006,15(12):3715-3727.
[145] Babacan, S. D.,Molina, R.,Katsaggelos, A. K. Parameter estimation in total variation blinddeconvolution[C]. In16th European Signal Processing Conference (EUSIPCO2008),Lausanne, Switzerland,2008:25-29.
[146] Cuicui, K.,Shengcai, L.,Shiming, X., etc. Kernel sparse representation with local patterns forface recognition[C]. In Image Processing (ICIP),201118th IEEE International Conference on,2011:3009-3012.
[147] Cover, T.,Hart, P. Nearest neighbor pattern classification[J]. Information Theory, IEEETransactions on,1967,13(1):21-27.
[148] Paredes, R.,Pérez, J.,Juan, A., etc. Local representations and a direct voting scheme for facerecognition[C]. In In Workshop on Pattern Recognition in Information Systems,2001.
[149] Zhang, B.,Srihari, S. N. Fast k-nearest neighbor classification using cluster-based trees[J].Pattern Analysis and Machine Intelligence, IEEE Transactions on,2004,26(4):525-528.
[150] Du, P.,Tan, K.,Xing, X. Wavelet SVM in Reproducing Kernel Hilbert Space for hyperspectralremote sensing image classification[J]. Optics Communications,2010,283(24):4978-4984.
[151]潘琛,林怡,陈映鹰.基于多特征的遥感影像决策树分类[J].光电子.激光,2010,21(5):731-736.
[152] Damodaran, B. B.,Nidamanuri, R. R. Assessment of the impact of dimensionality reductionmethods on information classes and classifiers for hyperspectral image classification bymultiple classifier system[J]. Advances in Space Research,2013(In press).
[153] Sohn, Y.,Rebe, N. S. Supervised and unsupervised spectral angle classifier[J]. Photogrammetric Engineering and Remote Sensing,2002,68(12):1271-1281.
[154] Ratle, F.,Camps-Valls, G.,Weston, J. Semisupervised Neural Networks for EfficientHyperspectral Image Classification[J]. Geoscience and Remote Sensing, IEEE Transactionson,2010,48(5):2271-2282.
[155] Mu,x,noz, M., etc. Semisupervised One-Class Support Vector Machines for Classification ofRemote Sensing Data[J]. Geoscience and Remote Sensing, IEEE Transactions on,2010,48(8):3188-3197.
[156] Strom, Y. TI: Automatic Surface Inspection of Continuously Cast Billets[J].1992.
[157]高潮,李新科,郭永彩,等.桥梁拉索表面缺陷的机器视觉检测系统[J].中国科技论文在线,2011,6(10):775-780.
[158] Sih, G. C.,Tang, X. S.,Li, Z. X., etc. Fatigue crack growth behavior of cables and steel wiresfor the cable-stayed portion of Runyang bridge: Disproportionate loosening and/or tighteningof cables[J]. Theoretical and Applied Fracture Mechanics,2008,49(1):1-25.
[159]高潮,任可,郭永彩,等.基于DSP和图像识别的拉索表面缺陷检测技术[J].重庆大学学报(自然科学版),2007,30(9):36-38.
[160]郭永彩,李哲,高潮.桥梁拉索表面缺陷无损检测系统设计[J].重庆大学学报,2010,33(8):7-11.
[161]李新科,高潮,郭永彩,等.桥梁拉索表面缺陷的分布式机器视觉检测[J].光学技术,2013,39(5):424-428.
[162] Qi, X.,Fengyu, X.,Xingsong, W. Modular Sensor for Detecting Cable Faults of Cable-StayedBridge[C]. In Mechatronics and Machine Vision in Practice,2008. M2VIP2008.15thInternational Conference on,2008:35-39.
[163] Xu, F.,Wang, X. Design and experiments on a new wheel-based cable climbing robot[C]. InAdvanced Intelligent Mechatronics,2008. AIM2008. IEEE/ASME International Conferenceon,2008:418-423.
[164]刘星星. DM642在网络多媒体开发平台中的应用[J].计算机科学,2007,34(1):106-108.
[165]李哲.基于DSP的表面缺陷无损检测系统设计[D].重庆：重庆大学，2010.
[166]李彧雯.轨道部件图像检测系统设计[D].南昌：南昌大学，2012.
[167]尹承添.基于机器视觉的钢板表面缺陷图像处理算法研究[D].南昌：南昌大学，2010.
[168]李天长.基于DM642的嵌入式实时图像处理的研究[D].重庆：重庆大学，2008.
[169] Ko, S.-J.,Lee, Y. H. Center weighted median filters and their applications to imageenhancement[J]. Circuits and Systems, IEEE Transactions on,1991,38(9):984-993.
[170]柴宝仁.中值滤波在气象传真图中降噪的分析[J].北京理工大学学报,2011,31(4):417-419.
[171]刘俊飞.基于双目视觉的护理机器人抱取功能的实现[D].南京：南京理工大学，2012.
[172]何春华,张雪飞,胡迎春.基于改进Sobel算子的边缘检测算法的研究[J].光学技术,2012,38(3):323-327.
[173]张怀利,倪国强,许廷发,等.从SAR遥感图像中提取水域的一种双模式结合方法[J].光学技术,2009,35(1):77-79+83.
[174] Kundur, D.,Hatzinakos, D. Blind image deconvolution[J]. Signal Processing Magazine, IEEE,1996,13(3):43-64.
[175]郭永彩,王婀娜,高潮.空间自适应和正则化技术的盲图像复原[J].光学精密工程,2008,16(11):2263-2267.
[176]张航,罗大庸.图像盲复原算法研究现状及其展望[J].中国图象图形学报,2004,9(10):1-8.
[177] A. N. Tikhonov, V. Y. A. Solutions of ill-posed problems[R]. Winston and Sons. Washington,DC,1977.
[178] Rudin, L. I.,Osher, S.,Fatemi, E. Nonlinear total variation based noise removal algorithms[J].Physica D: Nonlinear Phenomena,1992,60(1–4):259-268.
[179]陈建军.基于偏微分方程的图像降噪和图像恢复研究[D].重庆：重庆大学，2009.
[180] Goldstein, T.,Osher, S. The split Bregman method for L1-regularized problems[J]. SIAMJournal on Imaging Sciences,2009,2(2):323-343.
[181] Rudin, L. I.,Osher, S. Total variation based image restoration with free local constraints[C]. InImage Processing,1994. Proceedings. ICIP-94., IEEE International Conference,1994:31-35.
[182] Chan, T. F.,Golub, G. H.,Mulet, P. A nonlinear primal-dual method for total variation-basedimage restoration[J]. SIAM Journal on Scientific Computing,1999,20(6):1964-1977.
[183] Wang, Y.,Yin, W.,Zhang, Y. A fast algorithm for image deblurring with total variationregularization[R].2007.
[184] Chan, T. F.,Mulet, P. On the convergence of the lagged diffusivity fixed point method in totalvariation image restoration[J]. SIAM journal on numerical analysis,1999,36(2):354-367.
[185] Y. You, M. K. A regularization approach to joint blue identification and image restoration[J].1996,(5):416-427.
[186] Bioucas-Dias, J. M.,Figueiredo, M. A.,Oliveira, J. P. Total variation-based imagedeconvolution: a majorization-minimization approach[C]. In Acoustics, Speech and SignalProcessing,2006. ICASSP2006Proceedings.2006IEEE International Conference on,2006:II-II.
[187]高潮,郭永彩,刘国祥.基于频域共轭梯度算法的盲目图像恢复[J].计算机学报,2003,26(09):1152-1156.
[188] Q. Yuan, L. Z., H. Shen. Regional Spatially Adaptive Total Variation Super-Resolution withSpatial Information Filtering and Clustering[J]. IEEE Transactions on Image Processing,2013,22(6):2327-2342.
[189] Gao, H.,Zuo, Z. An adaptive non-local total variation blind deconvolution employing splitBregman iteration[C]. In Computational Intelligence and Design (ISCID),2012FifthInternational Symposium on,2012:394-398.
[190] Oliveira, J. P.,Bioucas-Dias, J. M.,Figueiredo, M. A. T. Adaptive total variation imagedeblurring: A majorization–minimization approach[J]. Signal Processing,2009,89(9):1683-1693.
[191] Mignotte, M. A segmentation-based regularization term for image deconvolution[J]. ImageProcessing, IEEE Transactions on,2006,15(7):1973-1984.
[192] Lowe, D. G. Distinctive image features from scale-invariant keypoints[J]. International journalof computer vision,2004,60(2):91-110.
[193]袁修孝,李然.带匹配支持度的多源遥感影像SIFT匹配方法[J].武汉大学学报(信息科学版),2012,37(12):1438-1442.
[194]唐永鹤,卢焕章.基于灰度差分不变量的快速局部特征描述算法[J].光学精密工程,2012,20(2):447-454.
[195] Hongbo, Z.,Xuejun, X.,Jing, W., etc. A Rapid Automatic Image Registration Method Based onImproved SIFT[J]. Procedia Environmental Sciences,2011,11,(Part A):85-91.
[196]廉蔺,李国辉,田昊,等.加窗灰度差直方图描述子及其对SURF算法的改进[J].电子与信息学报,2011,33(5):1042-1048.
[197] C. Huo, C. P., L. Huo, et al. Multi-level SIFT Matching for Large-Size VHR ImageRegistration[J]. IEEE Geoscience and remote sensing letters,2012,9(2):171-175.
[198]徐秋辉,佘江峰,宋晓群,等.利用Harris-Laplace和SIFT描述子进行低空遥感影像匹配[J].武汉大学学报(信息科学版),2012,37(12):1443-1447.
[199]朱云芳.基于图像拼接的视频编辑[D].杭州：浙江大学，2006.
[200] Zhou, J.,Shi, J. A robust algorithm for feature point matching[J]. Computers&Graphics,2002,26(3):429-436.
[201] X. L. Dai, S. K. A feature-based image registration algorithm using improved chain-coderepresentation combined with invariant moments[J]. IEEE Trans. on Geoscience and RemoteSensing,1999,37(5):2351-2362.
[202] Mallat., S. A Theory for Multiresolution Signal Decomposition: The Wavelet Representation[J]. IEEE Trans. on Pattern Anal. Mach. Intell.,1989,11(7):674-693.
[203] Yang, Z.-L.,Guo, B.-L. Image mosaic based on SIFT[C]. In Intelligent Information Hidingand Multimedia Signal Processing,2008. IIHMSP'08International Conference on,2008:1422-1425.
[204] Guandong, G.,Kebin, J. A new image mosaics algorithm based on feature points matching[C].In Innovative Computing, Information and Control,2007. ICICIC'07. Second InternationalConference on,2007:471-471.
[205] C. D. Kuglin, D. D. H. The phase correlation image alignment method[C]. In IEEEConference on Cybernetics and Society,1975:163-175.
[206]张静,胡志萍,刘志泰,等.基于轮廓相位相关的图像自动拼接[J].大连理工大学学报,2005,45(1):68-74.
[207] Bailey, J. G.,Messner, R. A. Log-polar mapping as a preprocessing stage for an image trackingsystem[C]. In1988Robotics Conferences,1989:15-22.
[208] Lim, F.,West, G.,Venkatesh, S. Use of log polar space for foveation and feature recognition[J].IEE Proceedings-Vision, image and Signal Processing,1997,144(6):323-331.
[209]李忠新,茅耀斌,王执铨.基于对数极坐标映射的图像拼接方法[J].中国图象图形学报,2005,10(1):59-63.
[210] Q. S. Chen, M. D., F. Deconinck. Symmetric Phase-only matched filtering of Fourier-Mellintransforms for image registration and recognition[J]. IEEE Transactions on Pattern Analysisand Machine Intelligence,1994,16(12):1156-1168.
[211]汪瑶.双目计算机视觉三维检测技术研究[D].广州：广东工业大学，2012.
[212] Beis, J. S.,Lowe, D. G. Shape indexing using approximate nearest-neighbour search inhigh-dimensional spaces[C]. In Computer Vision and Pattern Recognition,1997. Proceedings.,1997IEEE Computer Society Conference on,1997:1000-1006.
[213] Fischler, M. A.,Bolles, R. C. Random sample consensus: a paradigm for model fitting withapplications to image analysis and automated cartography[J]. Communications of the ACM,1981,24(6):381-395.
[214]杨占龙.基于特征点的图像配准与拼接技术研究[D].西安：西安电子科技大学，2008.
[215]姚汉英,孙文峰,李平,等. SAR图像拼接效果的评价方法研究[J].计算机工程,2010,36(15):196-198.
[216] Sodero Martins Pincelli, A. L. P.,de Moura, L. F.,Brito, J. O. Effect of thermal rectification oncolors of Eucalyptus Saligna and Pinus caribaea Woods[J]. Maderas. Ciencia y tecnología,2012,14(2):239-248.
[217] Lin, S. W.,Ying, K. C.,Chen, S. C., etc. Particle swarm optimization for parameterdetermination and feature selection of support vector machines[J]. Expert Syst. Appl.,2008,35(4):1817-1824.
[218] Chang, C. C.,Lin, C. J. LIBSVM: A Library for Support Vector Machines[J]. ACM Trans.Intell. Syst. Technol.,2011,2(3):1-27.
[219] Jiang, M.,Luo, Y. P.,Yang, S. Y. Stochastic convergence analysis and parameter selection ofthe standard particle swarm optimization algorithm[J]. Inf. Process. Lett.,2007,102(1):8-16.
[220] Garnier, S.,Gautrais, J.,Theraulaz, G. The biological principles of swarm intelligence[J].Swarm Intelligence,2007,30(1):3-31.
[221] Valuvanathorn, S.,Nitsuwat, S.,Huang, M. L., etc. Multi-Feature Face Recognition based onPSO-SVM[C]. In2012Tenth International Conference on Ict and Knowledge Engineering,2012:140-145.
[222] Huang, C. L.,Wang, C. J. A GA-based feature selection and parameters optimization forsupport vector machines[J]. Expert Syst. Appl.,2006,31(2):231-240.
[2]经柏林,谢华鸾.斜拉桥拉索研究综述[J].中国市政工程,2003,(6):22-24+68.
[3]张学元,安百刚,韩恩厚,等.酸雨对材料的腐蚀/冲刷研究现状[J].腐蚀科学与防护技术,2002,14(3):157-160.
[4]王力力,易伟建.斜拉索的腐蚀案例与分析[J].中南公路工程,2007,32(1):93-98.
[5]王应军.大型斜拉桥长期健康监测系统的关键技术研究[D].武汉：武汉理工大学，2006.
[6] M. Bloomstine, O. S., J. Thomsen. Conference on operation, maintenance and rehabilitationof large infrastructure projects: main cable corrosion by dehumidification[J]. Denmark:Copenhagen,2006.
[7] B. Tang, J. K., X. Wang, L. Chen. Surface inspection system of steel strip based on machinevision[C].2009First International Workshop on Database Technology and Applications,2009,359-362.
[8]陈大华.桥梁拉索钢丝模拟酸雨溶液中腐蚀行为研究及拉索寿命预测[D].重庆：重庆大学，2009.
[9]武新军,贲安然,徐江.桥梁缆索金属损伤无损检测方法[J].无损检测,2012,(04):12-16.
[10] Sloane, M. J. D.,Betti, R.,Marconi, G., etc. Experimental Analysis of a NondestructiveCorrosion Monitoring System for Main Cables of Suspension Bridges[J]. J. Bridge Eng.,2013,18(7):653-662.
[11]张家梁,吕恬生,郭剑鹰.在役缆索自动检测[J].无损检测,2003,25(2):99-101.
[12] Blasco, J.,Aleixos, N.,Moltó, E. Computer vision detection of peel defects in citrus by meansof a region oriented segmentation algorithm[J]. Journal of Food Engineering,2007,81(3):535-543.
[13] Meylani, R.,Ertuzun, A.,Er il, A. Texture defect detection using the adaptive two-dimensionallattice filter[C]. In Image Processing,1996. Proceedings., International Conference on,1996:165-168.
[14] Patel, D.,Davies, E. R.,Hnnah, I. The use of convolution operators for detecting contaminantsin food images[J]. Pattern Recognition,1996,29(6):1019-1029.
[15]龙跃,郑皆连,吴振.桥梁拉索典型病害事故的调查与研究[J].预应力技术,2010,(6):28-31+38.
[16] Funck, J. W.,Zhong, Y.,Butler, D. A., etc. Image segmentation algorithms applied to wooddefect detection[J]. Computers and Electronics in Agriculture,2003,41(1–3):157-179.
[17] Steiner, D.,Katz, R. Measurement techniques for the inspection of porosity flaws on machinedsurfaces[J]. Journal of computing and information science in engineering,2007,7(1):85-94.
[18] Kleynen, O.,Leemans, V.,Destain, M. F. Development of a multi-spectral vision system for thedetection of defects on apples[J]. Journal of Food Engineering,2005,69(1):41-49.
[19] Kumar, A. Neural network based detection of local textile defects[J]. Pattern Recognition,2003,36(7):1645-1659.
[20] Ahmed, R.,Sutcliffe, M. P. F. Identification of surface features on cold-rolled stainless steelstrip[J]. Wear,2000,244(1–2):60-70.
[21] Iyer, S.,Sinha, S. K. A robust approach for automatic detection and segmentation of cracks inunderground pipeline images[J]. Image and Vision Computing,2005,23(10):921-933.
[22] Torres, V.,Quek, S.,Fernandes, B., etc. Development of a scanning system to detect corrosionin wire bundles and pipes using magnetoresistive sensors[J]. Insight-Non-Destructive Testingand Condition Monitoring,2011,53(2):82-84.
[23] Christen, R.,Bergamini, A.,Motavalli, M. Influence of steel wrapping on magneto-inductivetesting of the main cables of suspension bridges[J]. NDT&E International,2009,42(1):22-27.
[24] Paulson, P. O. Continuous acoustic monitoring of suspension bridges and cable stays[C]. InNon-Destructive Evaluation Techniques for Aging Infrastructure&Manufacturing,1998:205-213.
[25] Mehrabi, A.,Telang, N. Cable-stayed bridge performance evaluation—Lessons from thefield[C]. In Proceedings of the Structures Congress and Exposition,2003.
[26]张春雷,李国平,雷洛.桥梁拉索HDPE护套日光老化试验[J].哈尔滨工业大学学报,2012,44(8):91-95.
[27] Suzumura, K.,Nakamura, S.-i. Environmental factors affecting corrosion of galvanized steelwires[J]. Journal of materials in civil engineering,2004,16(1):1-7.
[28] Vermaas, G. W. Corrosion and embrittlement of high-strength steel bridge wires[M].2001.
[29]徐俊,陈惟珍.石门大桥拉索病害检测与分析[J].钢结构,2007,22(6):81-84.
[30]杨少军.桥梁拉索体系损伤的检测和监测方法[J].公路交通技术,2005,(3):130-134.
[31] Wu, E.,Ke, Y.,Du, B. Noncontact laser inspection based on a PSD for the inner surface ofminidiameter pipes[J]. Instrumentation and Measurement, IEEE Transactions on,2009,58(7):2169-2173.
[32] Lee, J.-J.,Kim, J.-M.,Ahn, S.-S., etc. Development of a cable exciter to evaluate dampingratios of a stay cable[J]. KSCE Journal of Civil Engineering,2010,14(3):363-370.
[33] Ho, H.-N.,Kim, K.-D.,Park, Y.-S., etc. An efficient image-based damage detection for cablesurface in cable-stayed bridges[J]. NDT&E International,2013,(58):18-23.
[34]任可.基于嵌入式处理平台的桥梁拉索表面缺陷检测技术研究[D].重庆：重庆大学，2007.
[35]贺付亮.基于图像识别的桥梁拉索表面缺陷检测系统设计[D].重庆：重庆大学，2006.
[36]郑李明,王兴松.斜拉桥拉索径向畸变CCD图像的边缘检测与图像提取[J].机械制造与自动化,2008,37(6):107-110.
[37]王生治.基于DSP的缆索表面图像采集与传输系统设计与研究[D].重庆：重庆大学，2010.
[38]孙洪超.蛇形机器人步态生成方法及在桥梁缆索表面检测中的应用研究[D].重庆：华南理工大学，2012.
[39] Moreda, G.,Ortiz-Ca avate, J.,García-Ramos, F. J., etc. Non-destructive technologies for fruitand vegetable size determination–a review[J]. Journal of Food Engineering,2009,92(2):119-136.
[40] Rosati, G.,Boschetti, G.,Biondi, A., etc. Real-time defect detection on highly reflective curvedsurfaces[J]. Optics and Lasers in Engineering,2009,47(3–4):379-384.
[41]李长乐.冷轧带钢表面缺陷图像检测关键技术的研究[D].哈尔滨：哈尔滨工业大学，2009.
[42] Lin, H.-D. Computer-aided visual inspection of surface defects in ceramic capacitor chips[J].Journal of Materials Processing Technology,2007,189(1–3):19-25.
[43] Byrne, G.,Sheahan, C. Inline Color Vision for Specific Electroplating Defect Identification[J].Journal of Manufacturing Processes,2006,8(2):133-143.
[44] Marr, D. Vision: A computational investigation into the human representation and processingof visual information, Henry Holt and Co[J]. Inc., New York, NY,1982.
[45] Malamas, E. N.,Petrakis, E. G. M.,Zervakis, M., etc. A survey on industrial vision systems,applications and tools[J]. Image and Vision Computing,2003,21(2):171-188.
[46] Guo, W.,Soibelman, L.,Garrett Jr, J. H. Automated defect detection for sewer pipelineinspection and condition assessment[J]. Automation in Construction,2009,18(5):587-596.
[47] Kaixiang, P.,Xuli, Z. Classification technology for automatic surface defects detection of steelstrip based on improved BP algorithm[C]. In Natural Computation,2009. ICNC'09. FifthInternational Conference on,2009:110-114.
[48] Kumar, A. Computer-vision-based fabric defect detection: a survey[J]. Industrial Electronics,IEEE Transactions on,2008,55(1):348-363.
[49] Yang, T.,Wang, L.,Zheng, D., etc. Image Acquisition and Segmentation for Ceramic BearingBall Surface Inspection System[C]. In Intelligent Control and Automation,2006. WCICA2006. The Sixth World Congress on,2006:8444-8447.
[50]贾云得.机器视觉[M].北京:科学出版社,2000.
[51] Liu, Y.,Yu, F. Automatic inspection system of surface defects on optical IR-CUT filter basedon machine vision[J]. Optics and Lasers in Engineering,2014,55243-257.
[52] Cubero, S.,Aleixos, N.,Albert, F., etc. Optimised computer vision system for automaticpre-grading of citrus fruit in the field using a mobile platform[J]. Precision Agriculture,2014,15(1):80-94.
[53] Suresh, B. R. A real-time automated visual inspection system for hot steel slabs[J]. IEEETrans. Pattern Analysis Mach. Intell.,1983,5(6):563-572.
[54]戴卫东,安百光. Parsytec自动表面缺陷检查系统在冷轧连续退火线上的应用[J].冶金自动化,2009,33(2):47-51.
[55] Park, D. G.,Levoi, M. P.,Van Haneghem, A. Practical application of on-line hot stripinspection system at Hoogovens[J]. Iron Steel Eng.(USA),1995,72(7):40-43.
[56] Jouet, J. Defect classification in surface inspection of strip steel[J]. Steel Times,1992,16(5):214-216.
[57]王斌,罗志勇,刘栋玉,等.带钢边缘缺陷实时图象识别与宽度测量算法[J].无损检测,1997,19(7):188-190.
[58]罗志勇，刘栋玉，江涛，王斌.新型冷轧带钢表面缺陷在线检测系统[J].华中理工大学学报,1996,24(1):75-78.
[59]王斌,罗志勇,刘栋玉,等.带钢表面重皮缺陷在线图像识别算法研究[J].华中理工大学学报,1996,24(8):36-38.
[60]谢华锟.第八届中国国际机床展览会量仪展品述评——数字化测量技术先进制造技术基础[J].工具技术,2003,37(7):12-18.
[61]刘红冰,康戈文.基于神经网络的冷轧带钢表面缺陷检测[J].中国图象图形学报,2005,10(10):1310-1313.
[62]王宏,朱德生,唐威.一种基于灰度投影的带钢表面缺陷检测算法[J].东北大学学报(自然科学版),2008,29(3):375-377.
[63] Tsai, D.-M.,Lai, S.-C. Defect detection in periodically patterned surfaces using independentcomponent analysis[J]. Pattern Recognition,2008,41(9):2812-2832.
[64] Xie, X. A review of recent advances in surface defect detection using texture analysistechniques[J]. Electronic Letters on Computer Vision and Image Analysis,2008,7(3):1-22.
[65] Radovan, S.,Papadopoulos, G. D.,Georgoudakis, M., etc. Vision system for finished fabricinspection[C]. In Electronic Imaging2002,2002:97-103.
[66] Karimi, M. H.,Asemani, D. Surface defect detection in tiling Industries using digital imageprocessing methods: Analysis and evaluation[J]. ISA Transactions,2014,(In press).
[67] Guzman, E.,Baeten, V.,Pierna, J. A. F., etc. Infrared machine vision system for the automaticdetection of olive fruit quality[J]. Talanta,2013,116894-898.
[68] Mendes, A. d. O.,Fiadeiro, P. T.,Matos Ramos, A. M., etc. Development of an optical systemfor analysis of the ink-paper interaction[J]. Machine Vision and Applications,2013,24(8):1733-1750.
[69] Chiou, Y.-C.,Li, W.-C. Flaw detection of cylindrical surfaces in PU-packing by using machinevision technique[J]. Measurement,2009,42(7):989-1000.
[70] Jia, H.,Murphey, Y. L.,Shi, J., etc. An intelligent real-time vision system for surface defectdetection[C]. In Pattern Recognition,2004. ICPR2004. Proceedings of the17th InternationalConference on,2004:239-242.
[71]章毓晋.图像处理[M].北京:清华大学出版社,2006.
[72] Lucat, L.,Siohan, P.,Barba, D. Adaptive and global optimization methods for weighted vectormedian filters[J]. Signal Processing: Image Communication,2002,17(7):509-524.
[73] Lukac, R.,Smolka, B.,Plataniotis, K. N. Sharpening vector median filters[J]. SignalProcessing,2007,87(9):2085-2099.
[74] Yu, J.,Wang, Y.,Shen, Y. Noise reduction and edge detection via kernel anisotropicdiffusion[J]. Pattern Recognition Letters,2008,29(10):1496-1503.
[75] Candès, E. J.,Donoho, D. L. Continuous curvelet transform: I. Resolution of the wavefrontset[J]. Applied and Computational Harmonic Analysis,2005,19(2):162-197.
[76]冯鹏,米德伶,潘英俊,等.改进的Curvelet变换图像降噪方法[J].光电工程,2005,32(9):67-70+78.
[77] Biswas, A.,Cresswell, H. P.,Rossel, R. A. V., etc. Curve let transform to study scale-dependentanisotropic soil spatial variation[J]. Geoderma,2014,213589-599.
[78] Lian, Q.-S.,Chen, S.-Z. The Translation Invariant Contourlet-like Transform for ImageDenoising[J]. Acta Automatica Sinica,2009,35(5):505-508.
[79] Dai, S.-W.,Sun, Y.-K.,Tian, X.-L., etc. Image denoising based on complex contourlettransform[C]. In Wavelet Analysis and Pattern Recognition,2007. ICWAPR'07. InternationalConference on,2007:1742-1747.
[80] Guo, D. F.,Chen, J. B. The Application of Contourlet Transform to Image Denoising. In Ceis2011, Ran, C.,Yang, G., Eds. Elsevier Science Bv: Amsterdam,2011; Vol.15.
[81] Lazzaro, D.,Montefusco, L. B. Edge-preserving wavelet thresholding for image denoising[J].Journal of Computational and Applied Mathematics,2007,210(1–2):222-231.
[82] De Backer, S.,Pi urica, A.,Huysmans, B., etc. Denoising of multicomponent images usingwavelet least-squares estimators[J]. Image and Vision Computing,2008,26(7):1038-1051.
[83] Dai, M. H. The Development of Wavelet Transform and Its Application in Image Denoise. InManufacturing Process and Equipment, Pts1-4, Liu, X. H.,Zhang, K. F.,Li, M. Z., Eds. TransTech Publications Ltd: Stafa-Zurich,2013; Vol.694-697,2003-2008.
[84] Bettahar, S.,Stambouli, A. B. Shock filter coupled to curvature diffusion for image denoisingand sharpening[J]. Image and Vision Computing,2008,26(11):1481-1489.
[85]于舒春,闫继宏,赵杰,等.立体视觉的四阶段预处理方法[J].吉林大学学报(工学版),2007,37(3):651-654.
[86] Peter, Z.,Bousson, V.,Bergot, C., etc. A constrained region growing approach based onwatershed for the segmentation of low contrast structures in bone micro-CT images[J]. PatternRecognition,2008,41(7):2358-2368.
[87] Damiand, G.,Resch, P. Split-and-merge algorithms defined on topological maps for3D imagesegmentation[J]. Graphical Models,2003,65(1):149-167.
[88] Chung, K.-L.,Yang, W.-J.,Yan, W.-M. Efficient edge-preserving algorithm for color contrastenhancement with application to color image segmentation[J]. Journal of VisualCommunication and Image Representation,2008,19(5):299-310.
[89] Beucher, S.,Lantuejoul, C. Use of watersheds in contour detection[J].1979.
[90] Schmeelk, J. Wavelet transforms and edge detectors on digital images[J]. Mathematical andComputer Modelling,2005,41(13):1469-1478.
[91] Zhang, Z.,Ma, S.,Liu, H., etc. An edge detection approach based on directional wavelettransform[J]. Computers&Mathematics with Applications,2009,57(8):1265-1271.
[92] Villegas, O. O. V.,Elias, R. P.,Villela, P. R., etc. Edge preserving lossy image compressionwith wavelets and contourlets[C]. In Electronics, Robotics and Automotive MechanicsConference,2006,2006:3-8.
[93] Ling, L.,Peikang, H.,Xiaohu, W., etc. Image edge detection based on beamlet transform[J].Systems Engineering and Electronics, Journal of,2009,20(1):1-5.
[94] Wang, L.,Pan, C. Robust level set image segmentation via a local correntropy-based K-meansclustering[J]. Pattern Recognition,2014,47(5):1917-1925.
[95] Jacquey, F.,Comby, F.,Strauss, O. Fuzzy edge detection for omnidirectional images[J]. FuzzySets and Systems,2008,159(15):1991-2010.
[96]焦李成,谭山.图像的多尺度几何分析:回顾和展望[J].电子学报,2003,32(S1):1975-1981.
[97] Shih, F. Y.,Zhang, K. Locating object contours in complex background using improvedsnakes[J]. Computer Vision and Image Understanding,2007,105(2):93-98.
[98] Cabezas, M. G.,Bateni, A.,Montanero, J. M., etc. A new method of image processing in theanalysis of axisymmetric drop shapes[J]. Colloids and Surfaces A: Physicochemical andEngineering Aspects,2005,255(1–3):193-200.
[99] Yen, J.-C.,Chang, F.-J.,Chang, S. A new criterion for automatic multilevel thresholding[J].Image Processing, IEEE Transactions on,1995,4(3):370-378.
[100] Otsu, N. A threshold selection method from gray-level histograms[J]. Automatica,1975,11(285-296):23-27.
[101] Rosenfeld, A.,De La Torre, P. Histogram concavity analysis as an aid in threshold selection[J].Systems, Man and Cybernetics, IEEE Transactions on,1983,(2):231-235.
[102] Wu, S.,Amin, A. Automatic thresholding of gray-level using multistage approach[C]. InDocument Analysis and Recognition,2003. Proceedings. Seventh International Conference on,2003:493-497.
[103] Zhang, X.-P.,Desai, M. D. Wavelet based automatic thresholding for image segmentation[C].In Image Processing,1997. Proceedings., International Conference on,1997:224-227.
[104]田捷,韩博闻,王岩,等.模糊C-均值聚类法在医学图像分析中的应用[J].软件学报,2001,12(11):1623-1629.
[105] Kapur, J. N.,Sahoo, P. K.,Wong, A. K. C. A new method for gray-level picture thresholdingusing the entropy of the histogram[J]. Computer Vision, Graphics, and Image Processing,1985,29(3):273-285.
[106]陈黎,黄心汉,王敏,等.带钢缺陷图像的自动阈值分割研究[J].计算机工程与应用,2002,38(7):244-246.
[107]聂方彦.图像阈值化与目标分割方法中的若干问题研究[D].重庆：重庆大学，2010.
[108]孟祥迪,陈升来,郭静寰.基于图像边缘信息和Fisher准则的钢板表面缺陷分割研究[J].光学技术,2007,33(3):382-385.
[109]赵松青.带钢表面孔洞实时检测系统及相关技术研究[D].武汉：华中科技大学，2005.
[110]冯宇平.图像快速配准与自动拼接技术研究[D].长春：中国科学院研究生院(长春光学精密机械与物理研究所)，2010.
[111] Wexler, Y.,Shechtman, E.,Irani, M. Space-time video completion[C]. In Computer Vision andPattern Recognition,2004. CVPR2004. Proceedings of the2004IEEE Computer SocietyConference on,2004,(1): I-120-I-127.
[112]吴琼玉,周东翔,蔡宣平.基于图像序列的虚拟场景重建和漫游[J].中国图象图形学报,2006,11(1):113-118.
[113] Szeliski, R.,Shum, H.-Y. Creating full view panoramic image mosaics and environmentmaps[C]. In Proceedings of the24th annual conference on Computer graphics and interactivetechniques,1997:251-258.
[114]张红颖,张加万,孙济洲.改进Demons算法的非刚性医学图像配准[J].光学精密工程,2007,15(1):145-150.
[115]王华,王龙山,高金刚,等.面向汽车车架纵梁检测的序列图像快速拼接算法[J].光学精密工程,2008,16(3):531-536.
[116] Brown, L. G. A survey of image registration techniques[J]. ACM computing surveys (CSUR),1992,24(4):325-376.
[117] Szeliski, R. Video mosaics for virtual environments[J]. Computer Graphics and Applications,IEEE,1996,16(2):22-30.
[118] Yun Tian, G.,Gledhill, D.,Taylor, D. Comprehensive interest points based imaging mosaic[J].Pattern Recognition Letters,2003,24(9–10):1171-1179.
[119] M. Brown, D. G. L. Recognising panoramas[C]. In Proceedings of IEEE InternationalConference on Computer Vision,2003:1218-1225.
[120] Ha, S. J.,Koo, H.,Lee, S. H., etc. Panorama mosaic optimization for mobile camera systems[J].Consumer Electronics, IEEE Transactions on,2007,53(4):1217-1225.
[121]王小睿,吴信才.遥感多图象的自动配准方法[J].中国图象图形学报,1997,2(10):39-43.
[122]荆根强,张天序,杨卫东,等.局部自适应序列图像拼接算法[J].红外与激光工程,2004,33(6):622-625.
[123]李晓明,赵训坡,郑链,等.基于Fourier-Mellin变换的图像配准方法及应用拓展[J].计算机学报,2006,29(3):466-472.
[124]朱云芳,叶秀清,顾伟康.视频序列的全景图拼接技术[J].中国图象图形学报,2006,11(8):1150-1155.
[125]杨占龙,郭宝龙.基于兴趣点伪泽尼克矩的图像拼接[J].中国激光,2007,34(11):1548-1552.
[126] Banham, M. R.,Katsaggelos, A. K. Digital image restoration[J]. Signal Processing Magazine,IEEE,1997,14(2):24-41.
[127]邹谋炎.反卷积和信号复原[M].北京:国防工业出版社,2001.
[128] Joshi, M. V.,Chaudhuri, S. Joint blind restoration and surface recovery in photometricstereo[J]. JOSA A,2005,22(6):1066-1076.
[129] Hall, P.,Qiu, P. Blind deconvolution and deblurring in image analysis[J]. Statistica Sinica,2007,17(4):1483.
[130] Biemond, J.,Tekalp, A. M.,Lagendijk, R. L. Maximum likelihood image and bluridentification: a unifying approach[J]. Optical Engineering,1990,29(5):422-435.
[131] Reeves, S. J.,Mersereau, R. M. Blur identification by the method of generalizedcross-validation[J]. Image Processing, IEEE Transactions on,1992,1(3):301-311.
[132] Qidwai, U.,Chen, C.-H. Blind image restoration for ultrasonic C-Scan using constrained2D-HOS[C]. In Acoustics, Speech, and Signal Processing,2001. Proceedings.(ICASSP'01).2001IEEE International Conference on,2001:3405-3408.
[133] Ayers, G.,Dainty, J. C. Iterative blind deconvolution method and its applications[J]. Opticsletters,1988,13(7):547-549.
[134] McCallum, B. C. Blind deconvolution by simulated annealing[J]. Optics Communications,1990,75(2):101-105.
[135] Kundur, D.,Hatzinakos, D. A novel blind deconvolution scheme for image restoration usingrecursive filtering[J]. Signal Processing, IEEE Transactions on,1998,46(2):375-390.
[136] You, Y.-L., Kaveh, M.. A regularization approach to join blur identification and imagerestoration[J]. IEEE Transactions on Image Processing,1996,5(3):416-428.
[137] You, Y.-L.,Kaveh, M. Anisotropic blind image restoration[C]. In Image Processing,1996.Proceedings., International Conference on,1996:461-464.
[138] Chan, T. F.,Wong, C.-K. Total variation blind deconvolution[J]. Image Processing, IEEETransactions on,1998,7(3):370-375.
[139] Vogel, C. R.,Oman, M. E. Iterative methods for total variation denoising[J]. SIAM Journal onScientific Computing,1996,17(1):227-238.
[140] Shen, J. On the foundations of vision modeling: I. Weber’s law and Weberized TVrestoration[J]. Physica D: Nonlinear Phenomena,2003,175(3–4):241-251.
[141]张航,罗大庸.一种改进的全变差盲图像复原方法[J].电子学报,2005,33(7):1288-1290.
[142] He, L.,Marquina, A.,Osher, S. J. Blind deconvolution using TV regularization and Bregmaniteration[J]. International Journal of Imaging Systems and Technology,2005,15(1):74-83.
[143] Money, J. H.,Kang, S. H. Total variation minimizing blind deconvolution with shock filterreference[J]. Image and Vision Computing,2008,26(2):302-314.
[144] Molina, R.,Mateos, J.,Katsaggelos, A. K. Blind deconvolution using a variational approach toparameter, image, and blur estimation[J]. Image Processing, IEEE Transactions on,2006,15(12):3715-3727.
[145] Babacan, S. D.,Molina, R.,Katsaggelos, A. K. Parameter estimation in total variation blinddeconvolution[C]. In16th European Signal Processing Conference (EUSIPCO2008),Lausanne, Switzerland,2008:25-29.
[146] Cuicui, K.,Shengcai, L.,Shiming, X., etc. Kernel sparse representation with local patterns forface recognition[C]. In Image Processing (ICIP),201118th IEEE International Conference on,2011:3009-3012.
[147] Cover, T.,Hart, P. Nearest neighbor pattern classification[J]. Information Theory, IEEETransactions on,1967,13(1):21-27.
[148] Paredes, R.,Pérez, J.,Juan, A., etc. Local representations and a direct voting scheme for facerecognition[C]. In In Workshop on Pattern Recognition in Information Systems,2001.
[149] Zhang, B.,Srihari, S. N. Fast k-nearest neighbor classification using cluster-based trees[J].Pattern Analysis and Machine Intelligence, IEEE Transactions on,2004,26(4):525-528.
[150] Du, P.,Tan, K.,Xing, X. Wavelet SVM in Reproducing Kernel Hilbert Space for hyperspectralremote sensing image classification[J]. Optics Communications,2010,283(24):4978-4984.
[151]潘琛,林怡,陈映鹰.基于多特征的遥感影像决策树分类[J].光电子.激光,2010,21(5):731-736.
[152] Damodaran, B. B.,Nidamanuri, R. R. Assessment of the impact of dimensionality reductionmethods on information classes and classifiers for hyperspectral image classification bymultiple classifier system[J]. Advances in Space Research,2013(In press).
[153] Sohn, Y.,Rebe, N. S. Supervised and unsupervised spectral angle classifier[J]. Photogrammetric Engineering and Remote Sensing,2002,68(12):1271-1281.
[154] Ratle, F.,Camps-Valls, G.,Weston, J. Semisupervised Neural Networks for EfficientHyperspectral Image Classification[J]. Geoscience and Remote Sensing, IEEE Transactionson,2010,48(5):2271-2282.
[155] Mu,x,noz, M., etc. Semisupervised One-Class Support Vector Machines for Classification ofRemote Sensing Data[J]. Geoscience and Remote Sensing, IEEE Transactions on,2010,48(8):3188-3197.
[156] Strom, Y. TI: Automatic Surface Inspection of Continuously Cast Billets[J].1992.
[157]高潮,李新科,郭永彩,等.桥梁拉索表面缺陷的机器视觉检测系统[J].中国科技论文在线,2011,6(10):775-780.
[158] Sih, G. C.,Tang, X. S.,Li, Z. X., etc. Fatigue crack growth behavior of cables and steel wiresfor the cable-stayed portion of Runyang bridge: Disproportionate loosening and/or tighteningof cables[J]. Theoretical and Applied Fracture Mechanics,2008,49(1):1-25.
[159]高潮,任可,郭永彩,等.基于DSP和图像识别的拉索表面缺陷检测技术[J].重庆大学学报(自然科学版),2007,30(9):36-38.
[160]郭永彩,李哲,高潮.桥梁拉索表面缺陷无损检测系统设计[J].重庆大学学报,2010,33(8):7-11.
[161]李新科,高潮,郭永彩,等.桥梁拉索表面缺陷的分布式机器视觉检测[J].光学技术,2013,39(5):424-428.
[162] Qi, X.,Fengyu, X.,Xingsong, W. Modular Sensor for Detecting Cable Faults of Cable-StayedBridge[C]. In Mechatronics and Machine Vision in Practice,2008. M2VIP2008.15thInternational Conference on,2008:35-39.
[163] Xu, F.,Wang, X. Design and experiments on a new wheel-based cable climbing robot[C]. InAdvanced Intelligent Mechatronics,2008. AIM2008. IEEE/ASME International Conferenceon,2008:418-423.
[164]刘星星. DM642在网络多媒体开发平台中的应用[J].计算机科学,2007,34(1):106-108.
[165]李哲.基于DSP的表面缺陷无损检测系统设计[D].重庆：重庆大学，2010.
[166]李彧雯.轨道部件图像检测系统设计[D].南昌：南昌大学，2012.
[167]尹承添.基于机器视觉的钢板表面缺陷图像处理算法研究[D].南昌：南昌大学，2010.
[168]李天长.基于DM642的嵌入式实时图像处理的研究[D].重庆：重庆大学，2008.
[169] Ko, S.-J.,Lee, Y. H. Center weighted median filters and their applications to imageenhancement[J]. Circuits and Systems, IEEE Transactions on,1991,38(9):984-993.
[170]柴宝仁.中值滤波在气象传真图中降噪的分析[J].北京理工大学学报,2011,31(4):417-419.
[171]刘俊飞.基于双目视觉的护理机器人抱取功能的实现[D].南京：南京理工大学，2012.
[172]何春华,张雪飞,胡迎春.基于改进Sobel算子的边缘检测算法的研究[J].光学技术,2012,38(3):323-327.
[173]张怀利,倪国强,许廷发,等.从SAR遥感图像中提取水域的一种双模式结合方法[J].光学技术,2009,35(1):77-79+83.
[174] Kundur, D.,Hatzinakos, D. Blind image deconvolution[J]. Signal Processing Magazine, IEEE,1996,13(3):43-64.
[175]郭永彩,王婀娜,高潮.空间自适应和正则化技术的盲图像复原[J].光学精密工程,2008,16(11):2263-2267.
[176]张航,罗大庸.图像盲复原算法研究现状及其展望[J].中国图象图形学报,2004,9(10):1-8.
[177] A. N. Tikhonov, V. Y. A. Solutions of ill-posed problems[R]. Winston and Sons. Washington,DC,1977.
[178] Rudin, L. I.,Osher, S.,Fatemi, E. Nonlinear total variation based noise removal algorithms[J].Physica D: Nonlinear Phenomena,1992,60(1–4):259-268.
[179]陈建军.基于偏微分方程的图像降噪和图像恢复研究[D].重庆：重庆大学，2009.
[180] Goldstein, T.,Osher, S. The split Bregman method for L1-regularized problems[J]. SIAMJournal on Imaging Sciences,2009,2(2):323-343.
[181] Rudin, L. I.,Osher, S. Total variation based image restoration with free local constraints[C]. InImage Processing,1994. Proceedings. ICIP-94., IEEE International Conference,1994:31-35.
[182] Chan, T. F.,Golub, G. H.,Mulet, P. A nonlinear primal-dual method for total variation-basedimage restoration[J]. SIAM Journal on Scientific Computing,1999,20(6):1964-1977.
[183] Wang, Y.,Yin, W.,Zhang, Y. A fast algorithm for image deblurring with total variationregularization[R].2007.
[184] Chan, T. F.,Mulet, P. On the convergence of the lagged diffusivity fixed point method in totalvariation image restoration[J]. SIAM journal on numerical analysis,1999,36(2):354-367.
[185] Y. You, M. K. A regularization approach to joint blue identification and image restoration[J].1996,(5):416-427.
[186] Bioucas-Dias, J. M.,Figueiredo, M. A.,Oliveira, J. P. Total variation-based imagedeconvolution: a majorization-minimization approach[C]. In Acoustics, Speech and SignalProcessing,2006. ICASSP2006Proceedings.2006IEEE International Conference on,2006:II-II.
[187]高潮,郭永彩,刘国祥.基于频域共轭梯度算法的盲目图像恢复[J].计算机学报,2003,26(09):1152-1156.
[188] Q. Yuan, L. Z., H. Shen. Regional Spatially Adaptive Total Variation Super-Resolution withSpatial Information Filtering and Clustering[J]. IEEE Transactions on Image Processing,2013,22(6):2327-2342.
[189] Gao, H.,Zuo, Z. An adaptive non-local total variation blind deconvolution employing splitBregman iteration[C]. In Computational Intelligence and Design (ISCID),2012FifthInternational Symposium on,2012:394-398.
[190] Oliveira, J. P.,Bioucas-Dias, J. M.,Figueiredo, M. A. T. Adaptive total variation imagedeblurring: A majorization–minimization approach[J]. Signal Processing,2009,89(9):1683-1693.
[191] Mignotte, M. A segmentation-based regularization term for image deconvolution[J]. ImageProcessing, IEEE Transactions on,2006,15(7):1973-1984.
[192] Lowe, D. G. Distinctive image features from scale-invariant keypoints[J]. International journalof computer vision,2004,60(2):91-110.
[193]袁修孝,李然.带匹配支持度的多源遥感影像SIFT匹配方法[J].武汉大学学报(信息科学版),2012,37(12):1438-1442.
[194]唐永鹤,卢焕章.基于灰度差分不变量的快速局部特征描述算法[J].光学精密工程,2012,20(2):447-454.
[195] Hongbo, Z.,Xuejun, X.,Jing, W., etc. A Rapid Automatic Image Registration Method Based onImproved SIFT[J]. Procedia Environmental Sciences,2011,11,(Part A):85-91.
[196]廉蔺,李国辉,田昊,等.加窗灰度差直方图描述子及其对SURF算法的改进[J].电子与信息学报,2011,33(5):1042-1048.
[197] C. Huo, C. P., L. Huo, et al. Multi-level SIFT Matching for Large-Size VHR ImageRegistration[J]. IEEE Geoscience and remote sensing letters,2012,9(2):171-175.
[198]徐秋辉,佘江峰,宋晓群,等.利用Harris-Laplace和SIFT描述子进行低空遥感影像匹配[J].武汉大学学报(信息科学版),2012,37(12):1443-1447.
[199]朱云芳.基于图像拼接的视频编辑[D].杭州：浙江大学，2006.
[200] Zhou, J.,Shi, J. A robust algorithm for feature point matching[J]. Computers&Graphics,2002,26(3):429-436.
[201] X. L. Dai, S. K. A feature-based image registration algorithm using improved chain-coderepresentation combined with invariant moments[J]. IEEE Trans. on Geoscience and RemoteSensing,1999,37(5):2351-2362.
[202] Mallat., S. A Theory for Multiresolution Signal Decomposition: The Wavelet Representation[J]. IEEE Trans. on Pattern Anal. Mach. Intell.,1989,11(7):674-693.
[203] Yang, Z.-L.,Guo, B.-L. Image mosaic based on SIFT[C]. In Intelligent Information Hidingand Multimedia Signal Processing,2008. IIHMSP'08International Conference on,2008:1422-1425.
[204] Guandong, G.,Kebin, J. A new image mosaics algorithm based on feature points matching[C].In Innovative Computing, Information and Control,2007. ICICIC'07. Second InternationalConference on,2007:471-471.
[205] C. D. Kuglin, D. D. H. The phase correlation image alignment method[C]. In IEEEConference on Cybernetics and Society,1975:163-175.
[206]张静,胡志萍,刘志泰,等.基于轮廓相位相关的图像自动拼接[J].大连理工大学学报,2005,45(1):68-74.
[207] Bailey, J. G.,Messner, R. A. Log-polar mapping as a preprocessing stage for an image trackingsystem[C]. In1988Robotics Conferences,1989:15-22.
[208] Lim, F.,West, G.,Venkatesh, S. Use of log polar space for foveation and feature recognition[J].IEE Proceedings-Vision, image and Signal Processing,1997,144(6):323-331.
[209]李忠新,茅耀斌,王执铨.基于对数极坐标映射的图像拼接方法[J].中国图象图形学报,2005,10(1):59-63.
[210] Q. S. Chen, M. D., F. Deconinck. Symmetric Phase-only matched filtering of Fourier-Mellintransforms for image registration and recognition[J]. IEEE Transactions on Pattern Analysisand Machine Intelligence,1994,16(12):1156-1168.
[211]汪瑶.双目计算机视觉三维检测技术研究[D].广州：广东工业大学，2012.
[212] Beis, J. S.,Lowe, D. G. Shape indexing using approximate nearest-neighbour search inhigh-dimensional spaces[C]. In Computer Vision and Pattern Recognition,1997. Proceedings.,1997IEEE Computer Society Conference on,1997:1000-1006.
[213] Fischler, M. A.,Bolles, R. C. Random sample consensus: a paradigm for model fitting withapplications to image analysis and automated cartography[J]. Communications of the ACM,1981,24(6):381-395.
[214]杨占龙.基于特征点的图像配准与拼接技术研究[D].西安：西安电子科技大学，2008.
[215]姚汉英,孙文峰,李平,等. SAR图像拼接效果的评价方法研究[J].计算机工程,2010,36(15):196-198.
[216] Sodero Martins Pincelli, A. L. P.,de Moura, L. F.,Brito, J. O. Effect of thermal rectification oncolors of Eucalyptus Saligna and Pinus caribaea Woods[J]. Maderas. Ciencia y tecnología,2012,14(2):239-248.
[217] Lin, S. W.,Ying, K. C.,Chen, S. C., etc. Particle swarm optimization for parameterdetermination and feature selection of support vector machines[J]. Expert Syst. Appl.,2008,35(4):1817-1824.
[218] Chang, C. C.,Lin, C. J. LIBSVM: A Library for Support Vector Machines[J]. ACM Trans.Intell. Syst. Technol.,2011,2(3):1-27.
[219] Jiang, M.,Luo, Y. P.,Yang, S. Y. Stochastic convergence analysis and parameter selection ofthe standard particle swarm optimization algorithm[J]. Inf. Process. Lett.,2007,102(1):8-16.
[220] Garnier, S.,Gautrais, J.,Theraulaz, G. The biological principles of swarm intelligence[J].Swarm Intelligence,2007,30(1):3-31.
[221] Valuvanathorn, S.,Nitsuwat, S.,Huang, M. L., etc. Multi-Feature Face Recognition based onPSO-SVM[C]. In2012Tenth International Conference on Ict and Knowledge Engineering,2012:140-145.
[222] Huang, C. L.,Wang, C. J. A GA-based feature selection and parameters optimization forsupport vector machines[J]. Expert Syst. Appl.,2006,31(2):231-240.