摘要
中国是羽毛球生产大国,产量占全世界一半以上。羽毛球的生产工艺自诞生起150多年没有较大改变,仍是半机械半人工的生产方式,属于劳动密集型行业。随着劳动力成本的增加,企业必须提高生产的技术含量,减少人工,因此研究羽毛球自动化生产有巨大的实用价值。国内部分机构对羽毛球自动化生产进行过研究,成果集中在羽毛的尺寸测量上,缺陷检测研究得较少。然而毛杆上的折痕影响到羽毛球的耐打程度,是羽毛球质量的重要检测项目,必须在生产的第一环节进行。
基于机器视觉的毛杆缺陷检测,是将羽毛按规定方位固定到采集工位,使用几个从不同角度对着工位的摄像头采集羽毛图像,对采集到的图像进行综合分析处理,先提取羽毛杆,然后继续在毛杆上检测缺陷,最后将检测结果发送给羽毛投递系统,完成羽毛的分类。
自动化设备必须有较高的检测速度才能满足每日生产需求,图像分辨率是影响检测速度的关键,毛杆缺陷检测将在有限的图像分辨率上进行。研究存在以下难点：首先,部分缺陷由于结构和尺寸的原因,在垂直照射的环境下不能清晰成像；其次,羽毛杆与羽毛叶的色差以及毛杆与折痕缺陷的色差都较小,很难通过色差亮度等进行区分；再次,毛杆的表面有隆起以及图像中的边缘表现,使毛杆区域呈现一定的灰度梯度,该灰度变化尚无通用的方法补偿,在此背景下无疑加大了导数法缺陷检测难度；最后,检测时需分为两步：先提杆,后检测缺陷。二个步骤都要有较高的精确度才能保证缺陷检测的准确性。据所查的文献资料,直接解决相关问题的文献很少,因此,解决毛杆缺陷的检测具有理论研究价值。针对以上缺陷检测过程中的难题,本文从缺陷光学成像分析开始,对毛杆缺陷检测各过程的预处理、毛杆提取、缺陷检测及缺陷识别进行了系统的研究,主要的研究成果及创新点简述如下：
1首次研究光源照射角度与缺陷成像之间的理论关系,建立缺陷的成像公式,提出增加采集侧光照射的图像,然后对多幅采集图像进行综合判定的检测方法。仿真和应用结果都表明,该方法能使正光照射时不能成像的缺陷在侧光采集时清晰成像,有利于提高缺陷识别率。同时针对侧光采集时图像上亮度不一致现象,推导出亮度分布函数,据此对图像补偿。函数可预先计算,能极大提高检测时补偿速度。
2研究羽毛图像中的毛杆提取方法,根据毛杆中心线和宽度变化连续的特点,首次提出和建立基于中心线和宽度变化的动态轮廓模型,并给出迭代求解公式。实验结果表明,新算法的计算规模和计算复杂度均小于原始动态轮廓算法,且能有效地避免噪声和强边缘干扰,对于细长类目标的快速准确提取具有推广价值。
3研究基于复扩散滤波的缺陷边缘保持,提出耦合冲击滤波的复扩散函数对图像滤波方法。该方法在复扩散同时,叠加适当的冲击函数,由依赖边缘强度的冲击函数来选择增强或抑制效果。实验结果表明该方法的边缘保持和去噪效果优于其他算法,具有应用价值。
4研究基于脊波的缺陷检测算法,提出小对象上的边缘检测改进算法。该算法区别对待图像中的背景和检测对象,并通过拉伸增加对象在图像中的面积。实验结果表明,该算法能有效地检测出多种角度的微小缺陷,有利于提高缺陷识别率。算法对于其它小目标上的缺陷检测具有参考价值。
5建立全自动羽毛检测平台。集羽毛尺寸检测,颜色检测和缺陷检测为一体,减少单独检测时占据的中间环节。检测平台填补了羽毛自动化检测的空白,具有很好的实用价值。
China is the biggest badminton producer, accounting for more than 50% the world's production. Badminton production process has not been changed for 150 years since it was invented, this semi-manual processes are time consuming, labor-intensive and unreliable. With increment of labor cost, companies must improve technological innovation of manual intervention; therefore the research of badminton automated production process has great practical value. Some researches about the automation processes of badminton production have been done by some institutions, in fact, their results mainly focused on measuring size and detecting color of feathers, very few studies were done on defect detection. However, defect detection is a key point to badminton quality, especially rod defect of feathers, it relates to the resistance of playing badminton, defect feathers should be detected at the beginning of production.
Based on machine vision inspection of quill defect detection, the process is to fix the feather at the station in specific direction, and capture feather images via cameras at different positions of station. After comprehensive analysis of the image processing, quill can be extracted, then defects can be detected in the hair, the final test results will be sent to the feathers delivery system, to complete the classification of feathers.
Manufacturer need to address more than two million feathers every day, the speed of automation is the first consideration. To achieve this purpose, this paper has done some researches on feather rod defect detection with limited image pixels. Study found that defect detection have difficulties in the following:first, due to structure and size, some defect images are not clear under the normal image acquisition environment; Secondly, color difference is very tiny among rods, feathers and hairs, meanwhile width limit by rods is not significant, it is difficult to determine the threshold value; Thirdly, the uplift surface and the edge effect image of hair and rod, makes consistent shadow of gray in some areas. Currently the imbalance of gray shadow has no general method to compensate, at this point it will undoubtedly increase the difficulties of defect detection; Finally, the background of defects is quill, it must be identified before defect detection, the identification rate of a single feather is the product of two successful operations. To ensure final identification rate, every single step of the process should go with the best results. In this paper, starting from optical imaging analysis, studies have been done in pretreatment process, quills process, and defect identification system, the major research and innovation summarized as follows:
1. Built up a full-automation feahter test platform which include feather thickness test, tortuosity and camber test, square and roundness test, colour test and defect test. Decressed the taches in test each characteristic separately. The platform included feather transmission system, functions of which contained feather selection, orientation, camera shooting and transmission; the image collection system, the function of which contained light source setting, type and model selection of camera, orientation and control; the image processing system, the function of which contained get the images from the image collection system, analyse, process and identfy the images and transmitted the final result to the transmission system to sort the feather.
2. Combine with the physical structure of the quill, analysed the imaging process of the feather and the quill with PHONE theory. Posed a method using facelight and sidelight image select method to test the defect, which can extremely improve the imaging rate of defect. Focuse on the distribution of brightness nonuniform phenomenon built up a collection system illumination model. Deduced the brightness distribution function form the model. The brightness of image has been compensated to make it basicly balanced.
3. Posed a dynamic active model base on centre line model to collect the quill. This algorithm base on centre line's symmety, use the centre line and the width to describe the outline of the quill. The 2D outline curve of model has been simplifyed to two independent 1D function. Using the continuity and derivability enegy to indicate the inner enegy of the model. The improved algorithm can avoid the strong outline disturb effectively, decrease the quantity of compute. Combine with the initial outline automatic setting algorithm, no intervention division of the quill can be realized.
4. A method ehich using the coupling impact filtering complex spread function to filtering the image has been posed in the paper. In this method the impact function can sharpen the border. The real part of complex spread can restrain the noise. The imaginary part can test the border. The tow part coupled each other, overlaid complex spread with appropriate impact function, based on the impact function which depend on the strength of the border to choose effect of strengthen or reduce. Bacauce the border strength of the defect is higher than that of noise, the defect will be strengthened and the noise will be reduced.
5. Considered the Quantum error of image background will cover the characteristic of defect border, posed an improved ridge wave algorithm. This algorithm decreased the gray level difference between the quill and the background, weaker the effect of the quill border Quantum error, drew the linear characteristic of defect, reduced the range of defect direction, improved the test efficiency, can detected small defect of different angle, was propitious to raise the identify rate of the defect.
引文
[1]Ullah Aman, Vasanthan Thavaratnam, Bressler David. Bioplastics from feather quill [J]. Biomacromolecules,2011,12(10)3826-3832
[2]缪琴,徐林森,方世辉等.表面贴装晶圆视觉检测技术的研究[J].工业仪表与自动化装置,2011,5：27-29
[3]McCarthy C L, Hancock N H, Raine S R. Applied machine vision of plants: A review with implications for field deployment in automated farming operations[J]. Intelligent Service Robotics.2010,3(4):209-217
[4]F. Smach, M. Atr, J. Miteran, M. Abid. Design of a Neural Networks Classifier for Face Detection[J].Journal of Computer Science,2006,2(3):257-260
[5]Zhang Xuewu, Liang Ruiyu, Ding Yanqiong, et al. The System of Copper Strips Surface Defects Inspection Based on Intelligent Fusion [C]. Proceedings of the IEEE International Conference on Automation and Logistics. Qingdao. Inst. of Elec. and Elec,2008:476-480
[6]Li T. Applying wavelets transform, rough set theory and support vector machine for copper clad laminate defectsclassification[J].Expert Systems with Applications,2009,36 (32):5822-5829
[7]E. Malamas, G. M. Petrakis, M, Zervakis, et al. A survey on industrial vision system applications and tools. [J] Image and Vision Computing,2003,21(2): 171-188
[8]王骏,顾耀林.基于图像的光照模型的研究与实现[J].计算机工程与设计2005.1：107-120
[9]李刚.基于灰色系统理论的路面图像裂缝检测算法研究[D].武汉：武汉理工大学,2010.
[10]Egemen Teomete, Viren R Amin, Halil Ceylan. Digital image processing for pavement distress analyses[C]. Proceesdings of the2005Mid-Continent Transportation Research Symposium.2005,:1-173
[11]卢文科,朱长纯,方建安等.小波变换用于钢丝绳断丝检测的研究[J].传感技术学报,2007,20(7)：1659-1661
[12]章程辉.红毛丹品质的机器视觉检测技术研究[D].北京：中国农业大学,2005
[13]陈家新,周纬杰.一种改进的Phong光照模型及光线跟踪实现[J]系统仿真学报2002.12：253-256
[14]姜宏岸,李存华.基于Phong模型的三维地形光照场景仿真[C].中国计算机用户协会.计算机仿真.西宁：国防科技大学,2005,359-361
[15]Pierre Gravel, Gilles Beaudoin, Jacques ADG. A method for Modeling Noise in Medical Images. [C]IEEE Transactions on Medical Imaging,2004, 23(10):1221-1233
[16]Kennedy Lesa M, Basu Mitra. Application of projection pursuit learning to boundary detection and deblurring in images. [J]Pattern recognition, 2000,33(12):2019-2031
[17]郑捷文,蔡利栋.匀速直线运动模糊图像的恢复.[J]暨南大学学报,2002,3(23)：42-45
[18]Li D, Mersereau RM, Simske S. Blind image deconvolution through support vector. [J]IEEE Transactions on Neurl Network,2007,18(3):931-935
[19]Wang Chao, Ye Zhongfu.Brightness Preserving Histogram Equalization with Maximum Entropy:A ariational Perspective. [J]IEEE Transactions on Consumer Electronics,2005,51(4):1326-1334
[20]Yan Y, Wang H, Li S. Biomedical Image Processing Using FCM Algorithm Based on the Wavelet Transform[J]. Journal of Wuhan University of Technology,2004,19(3):18-20
[21]赵继印,郝志成,李建坡等.小波自适应比例改进算法在图像去噪中的应用.光[J].光电工程,2006,33(1)：81-84
[22]宇飞,毕笃彦.基于小波变换的自适应多阈值图像去噪.[J]中国图像图形学报,2005,10(5)：567-570
[23]芮挺,王金岩,沈春林等.基于PCA的图像小波去噪方法[J].小型微型计算机系统,2006,27(1)：158-16
[24]Venkatasubramanian Vijayaraghavan, Henry Leung. A Novel Chaos-Based High Resolution Imaging Technique and Its Application to Through-the-Wall Imagin[C]g. IEEE Signal Processing letters,2005,12(7):528-531
[25]王鹏,基于运动视觉技术的钢球表面缺陷检测[D],哈尔滨：哈尔滨理工大学,2008
[26]张洪涛,钢板表面缺陷在线视觉检测系统关键技术研究[D],天津：天津大学,2008
[27]彭向前,产品表面缺陷在线检测方法研究及系统实现[D],武汉：华中科技大学,2008
[28]韩斌,计算机视觉检测中的若干问题研究及应用[D],无锡：江南大学,2009
[29]梁冬泰,多尺度多元图像分析机器视觉检测理论及其应用研究[D],杭州：浙江大学,2009
[30]刘艳,基于CCD扫描的聚合物薄膜缺陷检测关键技术研究[D],哈尔滨：哈尔滨理工大学,2009
[31]刘正,轮胎X光检测与多纹理图像分析技术的研究[D],天津：天津大学,2008
[32]Newman and A. Jain. A survey of automated visual inspection. [J] Computer Vision and Image Understanding,61(2):231-262,1995
[33]高建贞,任明武.一种快速实用的灰度校正算法[J].中国图象图形学报2002.6：334：337
[34]Achmad Balza, Mustafa Mohd Marzuki, Hussain Aini. Enhanced anisotropic diffusion with noise amplification suppression[C].2009 IEEE International Conference on Signal and Image Processing,2009:237-240.
[35]Yu H C, Chua C S. GVF-based anisoropic diffusion models[C]. IEEE Transactions on Image Processing,2006,15(6):1517-1524
[36]Martin-Herrero J. Anisotropic diffusion in the hypercube[C]. IEEE Transactions on Geoscience and Remote Sensing,2007,45(5):1386-1398
[37]Rifkah E, Amer A. Fast automated stopping-time and edge-strength estimation for anisotropic diffusion[C]. In:Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing. Las Vegas, USA:IEEE,2008.933-936
[38]Krissian K, Westin C F, Kikinis R, Vosburgh K G. Oriented speckle reducing anisotropic diffusion[C]. IEEE Transactions on Image Processing, 2007,16(5):1412-1424
[39]El-Tawil Magdy, Al-Mulla Noha. Using homotopy-WHEP technique in solving nonlinear diffusion equation with stochastic no homogeneity[J]. Lecture Notes in Computer Science,2010,5890:51-67
[40]Black M J, Sapiro G, Marimont D H, Heeger D. Robust anisotropic diffusion [J]. IEEE Transactions on Image Processing,1998,7(3):421-432
[41]Gilboa G, Sochen N, Zeevi Y Y. Forward-and-backward diffusion processes for adaptive image enhancement and denoising[J]. IEEE Transactions on Image Processing,2002,11(7):689-703
[42]Gilboa G, Sochen N, Zeevi Y Y. Image enhancement and denoising by complex diffusion processes [J]. IEEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(8):1020-1036
[43]Chen Guan-Nan, Yang Kun-Tao, Rong Chen, Xie hi-Ming. A new study on image enhancement and denoising coupled with shock filters and anisotropic diffusion[C]. Proceedings-1st International Congress on Image and Signal Processing,2008,3:231-235
[44]Guy Gilboa, Nir Sochen, Zeevi Y Y, Image enhancement and denoising by complex diffusion processes [J]. IEEE Trans. On Pattern Analysis and Machine Intelligence,2003,28(8):1020-1036.
[45]Guy Gilboa, Nir A. Sochen, Zeevi Y Y. Regularized shock filters and complex diffusion [C]. In:Proceedings of the 7th European Conference on Computer Vision, LNCS 2350, Springer-Verlag,2002:399-413
[46]Ludusan C, Lavialle 0, Terebes R, Borda M, Pop S. Image enhancement using hybrid shock filters[C].2010 IEEE International Conference on Automation, Quality and Testing, Robotics.2010,3;111-116
[47]COULON 0, ARRIDGE S R. Dual echo MR image processing using multi-spectral probabilistic diffusion coupled with shock filters [C]. MIUA 2000, British Conference on Medical Image Understanding and Analysis, London, United-Kingdom,2000:256-264
[48]KORNPROBST P, DERICHE R, AUBERT G. Image coupling, restoration and enhancement via PDE's [C]. Proc. Int. Conf. on Image Processing 1997: Santa-Barbara (USA),1997:458-461
[49]邓仕超 刘铁根 萧泽新.应用Canny算法和灰度等高线的金相组织封闭边缘提取[J].光学精密工程,2010,18(10)：2314-2323.
[50]王凯 于海勋 王广平.一种改进的小波多尺度相乘目标边缘提取方法[J].计算机仿真,2009(10)：244-247.
[51]陈方涵 苗华 陈宇 王文生.基于小波多尺度积的目标识别[J].光学学报,2009(5)：1223-1226.
[52]吴德刚 张宇波 曹立波.一种改进的模糊边缘检测算法[J].激光与红外,2010,40(12)：1374-1377.
[53]沙秀艳 辛杰.基于最大熵的模糊核聚类图像分割方法[J].计算机工程,2011,37(10)：187-188,191.
[54]彭丰平 鲍苏苏 曾碧卿.基于自适应区域生长算法的肝脏分割[J].计算机工程与应用,2010,46(33)：198-200.
[55]朱煜 江林佳.基于遗传模糊C-均值与概率松弛法的图像分割研究[J].激光与红外,2008,38(4)：392-395.
[56]Kass M, Witkin A, and Terzopoulos D. Snakes:Active Contour Models[J]. Int. J. Computer Vision,1988,1:321-331
[57]Hongbin Zhang, Guangli Li. Application in stomach epidermis tumors segmentation by GVF snake model[C].2008 International Seminar on Future BioMedical Information Engineering,2008,453-456
[58]Xu C, Prince P L. Snakes, Shapes, and Gradient Vector Flow [J]. IEEE Trans on Image Processing,1998.7:359-369
[59]Marin-Jimenez Manuel, De La Blanca, Nicolas Perez. Matching deformable features based on oriented multi-scale filter banks[J].Lecture Notes in Computer Science 2006,4069:336-345
[60]Bhandarkar S M, and Zhang Hui. Image Segmentation Using Evolutionary Computation [J]. IEEE Trans. On Evolutionary Computation,1999,3(1):1-21
[61]Turk M and Pentland A. Eigenfaces for recognition[J]. Journal Cognitive Neuroscience,1991,3:71-86
[62]宁志刚 汪仁煌 刘燕 杨保柱 杨玲.仪表精度等级符号自动识别研究[J]·机床与液压,2010,38(7)：56-58,94.
[63]高炜欣 汤楠 李琳 穆向阳.基于多层Hopfield神经网络的X射线焊缝气泡检测[J].机械工程学报,2007,43(4)：193-197.
[64]Fabien Salzenstein, and Wojciech Pieczynski. Parameter Estimation in Hidden Fuzzy Markov Random Fields and Image Segmentation[J]. Graphical Models and Image Processing,1997,59(4):205-220
[65]A C Bovik, M Clark, W S Geisler. Multichannel texture analysis using localized spatial filters[J]. IEEF. Transactions on Pattern Analysis and Machine Intelligence,1990,12(1):55-73.
[66]惠斌,唐旭晟,罗海波等.基于Gabor小波SDF匹配滤波器的人脸识别[J].信息与控制,2008,37(5)：633-636.
[67]陈洋,王润生.结合Gabor滤波器和ICA技术的纹理分类方法[J].电子学报,2007,35(2)：299-303.
[68]苑玮琦,刘汪澜,柯丽.Gabor滤波器参数设计及其在虹膜识别中的应用[J].计算机应用研究,2008,25(8)：2399-2401.
[69]Kong W K, Zhan g D, Li W. Palmprint Feature Extraction Using 2-D Gabor Filters[J]. Pattern Recognition,2003,36(10):2339-2347.
[70]赵英男,杨静宇,孟宪权.一种实用的Gabor滤波器组参数设置方法[J].计算机工程,2006,32(19)：173-175.
[71]张开华,周文罡,张振等,一种改进的C-V主动轮廓模型[J],光电工程,2008,35(12)：112-116
[72]李小毛,唐延东,闵莉,一种改进的无需水平集重新初始化的C-V主动轮廓模型[J],光电工程,2006,33(9)：97-102
[73]李熙莹,倪国强.一种自动提取目标的主动轮廓法[J].光子学报,2002,31(3)：606-610
[74]罗红根,朱利民,丁汉.基于主动轮廓模型和水平集方法的图像分割技术[J].中国图象图形学报,2006,11(3)：301-309
[75]闵莉,李小毛,唐延东,基于形状保持主动轮廓的椭圆状目标检测[J],光电工 程,2008,35(2)：52-58
[76]C. Boukouvalas, J. Kittler, R. Marik, and M. Petrou. Color grading of randomly textured ceramic tiles using color histograms[J]. IEEE Transactions on Industry Electronics,1999,46(1):219-226.
[77]Freeland obert, Odhiambo Lameck. Subsurface characterization using textural features extracted from GPR data[J]. Transactions of the ASABE,2007,50(1):287-293
[78]龙永红,吴敏.基于灰度共生矩阵和颜色特征的泡罩包装缺陷检测[J].湖南大学学报(自然科学版)2005,32(6)65-68
[79]苏彩红,朱学峰,刘笛.基于灰度共生矩阵和颜色特征的墙地砖缺陷自动检测的研究[J].计算机工程与应用,2004,11：229-231
[80]Y.Huang and K.Chan. Texture decomposition by harmonics extraction from higher order statistics[J]. IEEE Transactions on Image Processing, 2004,13(1):1-14
[81]Zhao G y,Pietikainen M. Dynamic Texture recongnition using local binary patterns with an application to facial expression[C]. IEEE Transactions on PAMI,2007,29(6):915-928
[82]Ojala T, Pietikaninen M, Maenpaa T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[C]. IEEE Trans on PAMI,2002,24(7):971-987
[83]Jin H L, Liu Q S, Lu H Q, et al. Face detection using improved LBP under Bayesian framework[C]. In:Proc. of the International Conf. on Image and Graphics, Hong Kong:IEEE Computer Society Press,2004,306-309
[84]陆春君 陈松灿 谭晓阳.基于纹理频谱子集的纹理识别[J].江南大学学报：自然科学版,2007,6(6)：753-757.
[85]付蓉,石美红,陈惠娟.自适应局部二值模式算法及其在织物疵点检测中的应用[J],纺织高校基础科学学报2010,23(1)：99-104
[86]M.Niskanen, H. Kauppinen, andO. Silvlen. Real-time apects of SOM-based visual surface inspection[C]. In Machine Vision Applications in Industrial Inspection,2002,123-134,
[87]A. Monadjemi. Towards Effcient Texture Classifcation and Abnormality Detection. PhD thesis, UK:University of Bristol,2004.
[88]Tsai Du-Ming, Kuo Chih-Chia. Defect detection in inhomogeneously textured sputtered surfaces using 3D Fourier image reconstruction[J]. Machine Vision and Applications,2007,18(6):383-400
[89]刘泽福,王冰峰,康戈文 基于带钢表面缺陷检测的背景相减的方法福建电脑[J].2006,5：107-108
[90]Jasper W J, Gamier S J, Potapalli H. Texture characterization and effect detection using adaptive wavelets[J.]Opt. Eng.,1996,35(11): 3140-3149
[91]Conci A, Proena CB. A Box Counting Approach for Color Segmentation [C]. Santa Barbara, International Conference on Image Processes-ICIP'97; USA:1997,228-230.
[92]Surface texture characterization of fibers using Fractional Brownian Motion model
[93]Liaw Jiunjian, Lu ChuanPin, Chang LinHuang. Surface texture characterization of fibers using Fractional Brownian Motion model[J], International Journal of Innovative Computing, Information and Control,2011,7(3):1311-1320
[94]Gomez F, Romero E. Rotation invariant texture characterization using a curvelet based descriptor[J]. Pattern Recognition Letters, 2011,32(16):2178-2186
[95]Xu Tao, Gondra, A simple and effective texture characterization for image segmentation[J]. Signal, Image and Video Processing,2010:1-15.
[96]A.Kumarand G.Pang. Defect detection in textured materials using optimized filters[J]. IEEE Transactions on System, Man, and Cybernetics-CPartB:Cybernetic,32(5):553-570,2002
[97]C. Neubauer. Segmentation of defects in textile fabric[C].In Proceedings of the 7th International Conferenceon Pattern Recognition, 1992,1:688-691,1992
[98]A. Monadjemi, M. Mirmehdi, and B.Thomas. Restructured eigenfilter matching for novelty detection in random textures[C]. In British Machine Vision Conference,2004,637-646
[99]D. Tsai and C. Heish. Automated surface inspection for directional textures[J]. Image and Vision Computing,1999,18(1):49-62.
[100]兰添才.基于空域同态滤波的钢丝绳表面缺陷检测[J].福建电脑,2008,24(9)：8-9,48.
[101]尹义龙,詹小四,谭台哲,等.基于加博函数的指纹增强算法及其应用[J].软件学报,2003,14(3)：484-489
[102]Ma Jianglin, Zhao Zhongming, Wang Chengyi, Zhong Jianqiang. New unsupervised texture segmentation method using Gabor wavelet[J]. Wuhan Daxue Xuebao (Xinxi Kexue Ban)/Geomatics and Information Science of Wuhan University,2009,34(1):11-14
[103]KUMARA, PANG G K H. Defect detection in textured materials using Gabor filters [J]. IEEE Transactions on Industry Applications,2002,38(2): 425-440.
[104]贡玉南,华建兴,黄秀宝.基于匹配Gabor滤波器的规则纹理缺陷检测方法[J].中国图象图形学报.2001,6(7)：624-628
[105]袁端磊宋寅卯基于最优Gabor滤波器的织物缺陷检测[J].中国图象图形学报2006,11(7)：954-958
[106]温兆麟,陈新,李克天,郑德涛Gabor滤波器在彩色纹理表面缺陷检测中的应用[J].计算机应用研究2007,24(6)：184-186
[107]李坤全张道光. Haar变换在纺织检测中应用的研究[J].中原工学院学报,2002,13(2)：23-26.
[108]YANG Xuezhi,PANG G,YUNG N. Robust fabric defect detection and classification using multiple adaptive wavelets [J].IEEE Proceedings on Image Signal Process,2005,152(6):715-723.
[109]Yang Xuezhi,Pang G, YunG N. Discriminative fabric defect detection using adaptive wavelets[J]. Optical Engineering,2002,41(12):3116-3126
[110]于海,乌日图基于小波分析的织物疵点视觉检测方法[J].计量与测试技术 2007,34(10)：40-42
[111]苏畅,陈宇拓,喻云水,张潇云 基于小波与数学形态学的木材缺陷检测[J].计算机工程与应用,2008,44(33)：246-248
[112]吴成东 周博 李孟歆 李莹 吴丹.基于小波变换的墙地砖缺陷图像分割[J].沈阳建筑大学学报,自然科学版,2006,22(3)：500-503.
[113]杨学志 沈晶.采用小波框架的纺织品缺陷分类方法[J].工程图学学报,2009,30(5)：108-112.
[114]刘泓,莫玉龙 基于二维自适应异小波基小波变换的规则纹理缺陷检测中国图象图形学报1999,4(4)：349-352
[115]B.Mandelbrot. The Fractal Geometry of Nature[M]. W. H. Freeman,1983
[116]谢永华 王克奇.基于分形理论木材表面缺陷识别的研究[J].林业机械与木工设备,2006,34(7)：21-22.
[117]徐科 陈鲲鹏 杨朝霖 周鹏 高阳.最优尺度分形维数在热轧带钢表面缺陷识别中的应用[J].冶金设备,2008(2)：1-4,18.
[118]舒坚,胡茂林 基于Markov随机场模型的纹理图像的缺陷检测计[J].算机技术与发展2006,16(5)：65-67
[119]吴清 赵歆波 周惠群.基于马尔科夫随机场的叶片缺陷检测技术[J].计算机应用研究,2006,23(9)：187-188,212.
[120]Bi, Mingde, Sun, Zhigang Fabric defect detection using undecimated wavelet transform[J]. Information Technology Journal 2011,10(9):1701-1708
[121]S. Ozdemir, A. Baykut, R. Meylani, A. Ercil, and A. Ertuzun. Comparative evaluation of texture analysis algorithms for defect inspection of textile products[C]. In International Conference on Pattern Recognition,1998,1738-1740.
[122]Bodnarova A, Bennamoun M, and Latham S. J. Optimal Gabor Filters for Textile Flaw Detection [J]. Pattern Recognition,35(12):2973-2991
[123]Clausi D A. Deng H. Design-based texture feature fusion using garbor filters and co—occurrence probabilities[J]. IEEE Transactions on Image Processing,2005,14(7):925-936
[124]薄华,马缚龙,焦李成.图像纹理的灰度共生矩阵计算问题的分析[J].电 子学报,2006,34(1)：155-158
[125]Krishnamachari S, Chellappa R. Muhiresolution Gauss—markov random field models for texture segmentation[J]. IEEE Transactions on Image Processing,1997,6(2):251-267.
[126]涂宏斌,周新建.基于机器视觉的货车滚动轴承外圈麻点缺陷检测[J],铸造技术,2006,27(9)：978-980
[127]于海武,乌日图基于小波分析的织物疵点视觉检测方法[J]计量与测试技术,2007,34(10)：40-42
[128]郭晓锋,刘文田.基于图像处理的羽毛自动分拣系统[J].现代电子技术,2004,3：30-31
[129]Do M N, Vetterli M. The finite Ridgelet transform for image representation[J]. IEEE Transactions on Image Processing,2003,12 (1):16-28
[130]贾建,焦李成.数字脊波变换的实现与一种改进方法[J].计算机研究与发展,2006,43(1)：115-119.
[131]唐敏,成礼智.基于自适应脊波变换的边缘检测[J].计算机应用,2006,26(11)：2713-2715
