低质量可见光图像的处理技术和识别方法研究
|
摘要
低质量可见光图像在现实生活中大量存在且应用广泛。但是在许多重要成像领域,很多因素会导致图像的退化、细节部分的丢失,它们会造成图像的混叠,降晰和扭曲。因此观察到的图像往往不能满足实际应用对图像质量的要求。这个特点使得对它们的研究难以直接借用现有的图像处理技术,因而成为光学图像识别中的一个新的研究领域。本文在教育部博士点基金项目资助下,开展了如下研究工作:
研究了低质量可见光图像的重建方法。针对低质量可见光图像存在的像素过低、偏斜、旋转以及断裂等不同问题,分别研究了断裂图像的重建技术、图像的填充方法、以及低分辨率可见光图像的超分辨率重建技术。这些图像重建技术的研究是图像特征提取以及识别的前提,具有重要的理论价值和指导作用。
提出了基于小区域模板匹配的低质量可见光图像识别方法。现有的模板匹配及其改进算法存在匹配时间过长,不适合工业生产使用的缺点,提出了基于小区域模板匹配的算法原理,并分别对激光刻蚀标牌字符图像和低质量可见光空间目标进行了实验。实验证明该方法可以有效的缩短算法的匹配时间,具有较高的识别率。在此基础上,将相关系数法引入到低质量空间目标的类别识别与姿态识别之中,当测试样本与模板库样本尺寸大小不一时同样可以进行匹配。从实验结果来看,这种基于特征相关系数的匹配方法很适合于空间运动目标的匹配,由于这种匹配方法能够很容易地克服图像中轻微存在的变形、噪声和局部遮挡,因而具有较高的匹配精度。
研究了低质量可见光图像的旋转不变性矢量提取方法,解决了样本存在偏斜、旋转等情况时造成识别率下降的问题。首先将矩特征引入到图像的不变性矢量生成之中,给出了具体的算法。然后针对不同旋转下的图像,分别对文中方法和传统方法所提取的矢量曲线进行了对比说明,实验验证了文中方法的有效性。
提出了基于概率PCA模型的观测数据集本征维数确定方法。对于观测数据集的主分量确定方法的研究,国内外学者多采用经验式的方法来确定其本征维数,或者直接采用观测数据相关矩阵(或协方差矩阵)中特征值所在总体的方差贡献率大小的方式来定量的得到观测数据集的本征矢量维数。针对这一问题,首先给出了概率PCA模型;然后采用AIC、CAIC和BIC准则给出了本征矢量维数的确定方法;对影响主分量确定的模型的各个参数进行了仿真,并给出了相应的仿真实验结果:对于不同类型的观测样本集,给出了三类准则的适用范围;对提取到的新的特征矢量曲线数据集合,分别用以上三种准则给出了本征矢量维数的确定方法,对于三种准则在字符图像上的适用性给出了说明;最后,采用粗略估计子空间维数区间和精确判定最优本征矢量维数相结合的方法,大大减低了错误出现的可能,提高了算法的鲁棒性,同时也减少了算法的运行时间。对比实验表明,本文提出的方法与传统方法相比具有更高的识别率。
提出了基于端点、三叉点和四叉点等结构特征的二级压印凹凸字符识别方法。为了解决统计特征区分相似字符、旋转字符能力弱的问题,建立了基于端点、三叉点和四叉点等结构特征的压印凹凸字符二级识别网络。在第一级基于统计特征识别的基础上采用由三叉点等结构特征组成的第二级识别网络进行识别和校验。实验表明,该二级分类器能够区分相似字符,对于断裂比较严重的字符同样具有很好的识别能力。
研究了基于混合Contourlet与主成分变换的低质量图像融合方法。针对低质量图像可能存在的局部遮挡、噪声等问题,将多传感器图像信息或者单摄像机得到的多幅图像信息有机的结合起来,以获取对同一场景的更精确、更全面、更可靠的图像描述。实验表明,采用混合Contourlet与主成分变换的融合方法可以较好的实现目标的融合。
本课题为2006年国家教育部博士点基金项目资助课题。
There exist large amounts of low-quaility visual images in the real world and they have been used widely. There are many factors which lead to the image blurring, serious detail loss, image warping and ambiguities images, for those reasons, the images we observed are usually not accurate enough to fit the requirement of the image resolution. It is this characteristic that makes it difficult to use the existing research achievements of the traditional optical image recognition to recognize them. Accordingly, recognition of such image becomes a new hot spot. Supported by Doctoral Fund of Ministry of Education of China, the research carried out in this dissertation is as followings.
The low-quaility visual image preprocessing is investigated first. Aimed to solve the problem cause by low-resolution, skewed image, rotated image and broken image, the reconstruction of broken characters, filling the holes of image, image enhancement are researched. As the image preprocessing is the precondition of image feature extraction and recognition; such researches paly an important role of theoretical guidance.
A novel low-quaility visual image recognition based on the small region template-matching algorithm is presented. It is used to overcome the shortcoming of long time waste and unsuitable for the industrial process. The laser etched label characters and the deep space objects are used to testify the probability of the method, it shows that this algorithm uses less time and could get much higher recognition rate. Based on this method, the theory of correlation factor is lead into the small region template matching method to solve the problem of size mismatching. The experiment shows that this method is suitable for the motion objects; it also shows that this method can easily overcome the deformation, noise and local shading, so this method has much higher matching precision.
The rotated image will decrease the recognition rate by using principal component analysis. To solve this problem, a novel sample vector formation method is presented. The invariant features such as moment invariants are used to get the rotate invariant vectors; the recognition is carried out directly on the gray-level images by adopting the improved PCA subspace method. Experimental results show that this method could decrease the number of sieving samples and has much higher recognition rate comparing with the typical method.
A central issue in PCA is choosing the number of intrinsic components to retain. However, most studies assume a known dimension or determine it heuristically, though there are a number of model selection criteria in the literature of statistics. In this dissertation, the probabilistic reformulation of PCA is used and a model selection criterion for determining the intrinsic dimensionality of data including Akaike's information criterion (AIC), the consistent Akaika's information criterion (CAIC), and the Bayesian inference criterion (BIC) are derived. At last, aimed to the character images, these parameters could affect the determination of the subspace dimension is analyzed in detail. The range of application of these three criterions is analyzed and a two-step method to estimate the intrinsic dimension of the observed character dataset is presented. Experiments demonstrate that the new algorithm is feasible and robust; it also can decrease the time waste. The comparison experiment for the recognition of protuberant characters shows that this method has much higher recognition rate than typical used PCA methods.
A new algorithm based on the structural properties such as the endings, the three crossing points, the four crossing points and the positions of the three crossing points is presented. It could solve the problem of low recognition rate caused by rotate, similar and broken characters. A two-level recognition network is setup, the first network is based on the PCA method, after the first step recognition is complete, the result is sent to the second network which is based on the described structural features, the error-prone characters and the character with low degree of confidence are recognized again. Experiment results show that the two-level character recognition network has much higher recognition rate and it is much robust as it can recognize the similar characters and some broken characters.
A single sensor cannot produce a complete representation of a scene, Image fusion is the process of combining information from two or more images of a scene into a single composite image that is more informative and is more suitable for visual perception or computer processing. A novel fusion method of low-quality images based on hybrid Contourlet-PCA transform is proposed. The experiment result shows that the proposed method could well fuse hyperspectral images with noises eliminated and it outperforms the Contourlet and PCA methods.
This work is supported by Doctoral Fund of Ministry of Education of China.
研究了低质量可见光图像的重建方法。针对低质量可见光图像存在的像素过低、偏斜、旋转以及断裂等不同问题,分别研究了断裂图像的重建技术、图像的填充方法、以及低分辨率可见光图像的超分辨率重建技术。这些图像重建技术的研究是图像特征提取以及识别的前提,具有重要的理论价值和指导作用。
提出了基于小区域模板匹配的低质量可见光图像识别方法。现有的模板匹配及其改进算法存在匹配时间过长,不适合工业生产使用的缺点,提出了基于小区域模板匹配的算法原理,并分别对激光刻蚀标牌字符图像和低质量可见光空间目标进行了实验。实验证明该方法可以有效的缩短算法的匹配时间,具有较高的识别率。在此基础上,将相关系数法引入到低质量空间目标的类别识别与姿态识别之中,当测试样本与模板库样本尺寸大小不一时同样可以进行匹配。从实验结果来看,这种基于特征相关系数的匹配方法很适合于空间运动目标的匹配,由于这种匹配方法能够很容易地克服图像中轻微存在的变形、噪声和局部遮挡,因而具有较高的匹配精度。
研究了低质量可见光图像的旋转不变性矢量提取方法,解决了样本存在偏斜、旋转等情况时造成识别率下降的问题。首先将矩特征引入到图像的不变性矢量生成之中,给出了具体的算法。然后针对不同旋转下的图像,分别对文中方法和传统方法所提取的矢量曲线进行了对比说明,实验验证了文中方法的有效性。
提出了基于概率PCA模型的观测数据集本征维数确定方法。对于观测数据集的主分量确定方法的研究,国内外学者多采用经验式的方法来确定其本征维数,或者直接采用观测数据相关矩阵(或协方差矩阵)中特征值所在总体的方差贡献率大小的方式来定量的得到观测数据集的本征矢量维数。针对这一问题,首先给出了概率PCA模型;然后采用AIC、CAIC和BIC准则给出了本征矢量维数的确定方法;对影响主分量确定的模型的各个参数进行了仿真,并给出了相应的仿真实验结果:对于不同类型的观测样本集,给出了三类准则的适用范围;对提取到的新的特征矢量曲线数据集合,分别用以上三种准则给出了本征矢量维数的确定方法,对于三种准则在字符图像上的适用性给出了说明;最后,采用粗略估计子空间维数区间和精确判定最优本征矢量维数相结合的方法,大大减低了错误出现的可能,提高了算法的鲁棒性,同时也减少了算法的运行时间。对比实验表明,本文提出的方法与传统方法相比具有更高的识别率。
提出了基于端点、三叉点和四叉点等结构特征的二级压印凹凸字符识别方法。为了解决统计特征区分相似字符、旋转字符能力弱的问题,建立了基于端点、三叉点和四叉点等结构特征的压印凹凸字符二级识别网络。在第一级基于统计特征识别的基础上采用由三叉点等结构特征组成的第二级识别网络进行识别和校验。实验表明,该二级分类器能够区分相似字符,对于断裂比较严重的字符同样具有很好的识别能力。
研究了基于混合Contourlet与主成分变换的低质量图像融合方法。针对低质量图像可能存在的局部遮挡、噪声等问题,将多传感器图像信息或者单摄像机得到的多幅图像信息有机的结合起来,以获取对同一场景的更精确、更全面、更可靠的图像描述。实验表明,采用混合Contourlet与主成分变换的融合方法可以较好的实现目标的融合。
本课题为2006年国家教育部博士点基金项目资助课题。
There exist large amounts of low-quaility visual images in the real world and they have been used widely. There are many factors which lead to the image blurring, serious detail loss, image warping and ambiguities images, for those reasons, the images we observed are usually not accurate enough to fit the requirement of the image resolution. It is this characteristic that makes it difficult to use the existing research achievements of the traditional optical image recognition to recognize them. Accordingly, recognition of such image becomes a new hot spot. Supported by Doctoral Fund of Ministry of Education of China, the research carried out in this dissertation is as followings.
The low-quaility visual image preprocessing is investigated first. Aimed to solve the problem cause by low-resolution, skewed image, rotated image and broken image, the reconstruction of broken characters, filling the holes of image, image enhancement are researched. As the image preprocessing is the precondition of image feature extraction and recognition; such researches paly an important role of theoretical guidance.
A novel low-quaility visual image recognition based on the small region template-matching algorithm is presented. It is used to overcome the shortcoming of long time waste and unsuitable for the industrial process. The laser etched label characters and the deep space objects are used to testify the probability of the method, it shows that this algorithm uses less time and could get much higher recognition rate. Based on this method, the theory of correlation factor is lead into the small region template matching method to solve the problem of size mismatching. The experiment shows that this method is suitable for the motion objects; it also shows that this method can easily overcome the deformation, noise and local shading, so this method has much higher matching precision.
The rotated image will decrease the recognition rate by using principal component analysis. To solve this problem, a novel sample vector formation method is presented. The invariant features such as moment invariants are used to get the rotate invariant vectors; the recognition is carried out directly on the gray-level images by adopting the improved PCA subspace method. Experimental results show that this method could decrease the number of sieving samples and has much higher recognition rate comparing with the typical method.
A central issue in PCA is choosing the number of intrinsic components to retain. However, most studies assume a known dimension or determine it heuristically, though there are a number of model selection criteria in the literature of statistics. In this dissertation, the probabilistic reformulation of PCA is used and a model selection criterion for determining the intrinsic dimensionality of data including Akaike's information criterion (AIC), the consistent Akaika's information criterion (CAIC), and the Bayesian inference criterion (BIC) are derived. At last, aimed to the character images, these parameters could affect the determination of the subspace dimension is analyzed in detail. The range of application of these three criterions is analyzed and a two-step method to estimate the intrinsic dimension of the observed character dataset is presented. Experiments demonstrate that the new algorithm is feasible and robust; it also can decrease the time waste. The comparison experiment for the recognition of protuberant characters shows that this method has much higher recognition rate than typical used PCA methods.
A new algorithm based on the structural properties such as the endings, the three crossing points, the four crossing points and the positions of the three crossing points is presented. It could solve the problem of low recognition rate caused by rotate, similar and broken characters. A two-level recognition network is setup, the first network is based on the PCA method, after the first step recognition is complete, the result is sent to the second network which is based on the described structural features, the error-prone characters and the character with low degree of confidence are recognized again. Experiment results show that the two-level character recognition network has much higher recognition rate and it is much robust as it can recognize the similar characters and some broken characters.
A single sensor cannot produce a complete representation of a scene, Image fusion is the process of combining information from two or more images of a scene into a single composite image that is more informative and is more suitable for visual perception or computer processing. A novel fusion method of low-quality images based on hybrid Contourlet-PCA transform is proposed. The experiment result shows that the proposed method could well fuse hyperspectral images with noises eliminated and it outperforms the Contourlet and PCA methods.
This work is supported by Doctoral Fund of Ministry of Education of China.
引文
1 Simon Baker, Takeo Kanade. Limits on super-resolution and how to break them. IEEE Transactions on Patern Analysis and Machine Intelligence, 2002,24(9): 1167-1183.
2 Sung Cheol Park, Min Kyu Park, and Moon Gi Kang. Super-resolution image reconstruction a technical overview. IEEE Signal Processing Magazine 20:2 1-36, May 2003.
3 Michael K. Ng and Nirmal K. Bose. Mathematical analysis of super-resolution methodology. IEEE Signal Processing Magazine. MAY 2003.
4 Sean Borman, Robert Stevenson. Spatial resolution enhancement of low-resolution image sequences: a comprehensive review with directions for future research, Indiana: Laboratory for Image and Signal Analysis in University of Notre Dame, 1998.
5 Rafael Molina, Miguel Vega, Javier Abad, et al. Estimation in Bayesian high-resolution image reconstruction with multisensors. IEEE Transactions on Image Processing, 2003, 12 (12): 996-1011.
6 Max Born and Emil Wolf. Principles of optics. Cambridge University Press, 1999.
7 J.A. Parker, R. V Kenyon, and D. E. Troxel. Comparison of interpolating methods for image resampling. IEEE Transactions on Medical Imaging, 1983,3 (2): 31-39.
8 P. Vandewalle, S. S usstrunk, and M. Vetterli. Super resolution images reconstructed from aliased images. In SPIE/IS&T Visual Communication and Image Processing Conference, Ebrahimi and T.Sikora, Eds. 5150, July 2003:1398-1405.
9 Barbara Zitova, Jan Flusser. Image registration methods: a survey. Image and Vision Computing 21, 2003:977-1000.
10 J.B.Antoine Maintzl and Max A.Viergever.An Overview of Medical Image Registration Methods.Imaging Science Department,Imaging Center Utrecht.
11 P.A.van den Elsen,E.J.D.Pol,and M.A.Viergever.Medical image matching- a review with classification.IEEE Engineering in medicine and biology,12(1):26-39,1993.
12 Lisa Gottesfeld Brown.A survey of image registration techniques Department of Computer Science.Columbia of University.January 12,1992.
13 Jian-xiong Dong,Adam Krzy(?)ak and Ching Y.Suen.An Improved Handwritten Chinese Character Recognition System Using Support Vector Machine.Pattern Recognition Letters.2005,26(12):1849-1856.
14 A.Basu,C.Watters and M.Shepherd.Support Vector Machines for Text Categorization.Proceedings of 36th Annual Hawaii International Conference on System Sciences.2003,1:103-109.
15 A.R.Ahmad,M.Khalid and R.Yusof.Kernel Methods and Support Vector Machines for Handwriting Recognition.Student Conference of Research and Development.2002:309-312.
16 A.Mitiche,J.K.Aggarwa.Pattern Category Assignment by Neural Networks and Nearest Neighbors Rule:A Synopsis and A Characterization.International Journal of Pattern Recognition and Artificial Intelligence.1996,10(5):393-408.
17 l-Seok Oh,Ching Y.Suen.A Class-modular Feed-forward Neural Network for Handwriting Recognition.Pattern Recognition.2002,35(1):229-244.
18 刘建胜,汪同庆,居琰.基于神经网络和学习子空间的OCR识别方法在选票处理中的应用.计算机工程.2002,28(11):36-38.
19 E.Oja.The ALSM Algorithm:an Improved Subspace Method of Classification.Pattern Recognition,1983,16(4):421-427.
20 M.Prakash,M.Narasimha Murty.Hebbian Learning Subspace Method:A New Approach.Pattern Recognition.1997,30(1):141-149.
21 蒋伟峰,刘济林.基于PCA学习子空间算法的有限汉字识别.中国图象图形学报.2001,6(2):186-190.
22 M.Aksela,J.Laaksonen.Adaptive Combination of Adaptive Classifiers for Handwritten Character Recognition.Pattern Recognition Letters.2007,25(1):136-143.
23 L.Xu,A.Krzyzak and C.Y.Suen.Methods for Combining Multiple Classifiers and Their Applications in Handwritten Character Recognition.IEEE Trans.Systems,Man,and Cybernetics.1992,22:418-435.
24 T.K.Ho,J.J.Hull and S.N.Srihari.Decision Combination in Multiple Classifier Systems.IEEE Trans.Pattern Analysis and Machine Intelligence.1994,16(1):66-75.
25 Louisa Lam,Ching Y.Suen.Optimal Combinations of Pattern Classifiers.Pattern Recognition Letters.1995,16(9):945-954.
26 Chien-Hsing Chou,Chin-Chin Lin and Ying-Ho Liu,et al.A Prototype Classification Method and Its Use in a Hybrid Solution for Multi-class Pattern Recognition.Pattern Recognition.2006,39(4):624-634.
27 李新,夏定元.玻璃瓶字符识别中运动图像的获取.光通信技术.2004,(4):62-64.
28 汪蕙,鲍旭东,罗立民.车轮序列号自动识别系统.测控技术.2002,21(7):23-25.
29 戴鲲,张大力.火车标牌识别系统的设计与实现.计算机工程.2001,27(11):106-107,161.
30 苏健平,陈志强.集装箱检测信息自动采集系统的箱号识别策略.核电子与探测技术.2003,23(4):333-336.
31 徐蔚然.基于知识的银行票据二值化方法.中文信息学报.2002,16(2):60-64
32 S.M.Pizer,E.P.Ambum and J.D.Austin,et al.Adaptive Histogram Equalization and Its Variation.Computer Vision Graphics Image Process.1957,39(3):355-368.
33 K.W.Leszczynski,S.Shalev.A Robust Algorithm for Contrast Enhancement by Local Histogram Modification.Image and Vision Computing.1989,7(3):704-711.
34 Y.Choi and R.Krishnapuram.A Robust Approach to Image Enhancement Based on Fuzzy Logic.IEEE Trans.On Image Processing.1997,6(6):685-693.
35 Yeong taeg Kim.Contrast Enhancement Using Brightness Preserving Bi-histogram Equalization.IEEE Trans.on Consumer Electronics.1997,43(1):1-8
36 E.L.Hall.Almost Uniform Distribution for Computer Image Enhancement.IEEE Trans.Comput..1984,C-33:207-208.
37 周妮娜,王敏,黄心汉.车牌字符识别的预处理算法.计算机工程与应用.2003,(15):220-221,232.
38 陈强,朱立新,夏德深.结合Canny算子的图像二值化.计算机辅助设计与图形学报.2005,17(6):1302-1306.
39 李国平.基于莫尔技术的标牌凹凸字符图像获取与识别研究[D].山东大学博士论文.2007:3.
40 Y.J.Zhang.A Survey on Evaluation Methods for Image Segmentation.Pattern Recognition.1996,29(8):1335-1346
41 N.R.Pal,S.K.Pal.A Review on Image Segmentation Techniques.Pattern Recognition.1993,26(9):1277-1294.
42 吴一全,末兆达.图象处理中阈值选取方法30年(1962-1992)的进展(一).数据采集与处理.1993,8(3):193-201.
43 吴一全,末兆达.图象处理中阈值选取方法30年(1962-1992)的进展(二).数据采集与处理.1993,8(4):268-281.
44 Jianguo Wang,Hong Yan,Mending broken handwriting with a macrostructure analysis method to improve recognition[J].Pattern recognition letters,1999,20:855-864.
45 Donggang Yu,Hong Yan,reconstruction of broken handwritten digits based on structural morphological features[J].Pattern recognition,2001, 34:235-254.
46 Adrian P.Whichello,Hong Yan,linking broken character borders with variable sized masks to improve recognition[J].Pattern recognition,1996,29(8):1429-1435.
47 李学勇.金属标牌压印凹凸字符的特征提取和识别方法研究[D].山东大学博士论文,2008:5.
48 Yi Lu,Beverly Haist,Laurel Harmon,et al.An Accurate and Efficient System for Segmenting Machine-printed Text.US Postal Service 5th Advanced Technology Conference,Washington,DC,USA.1992,93-105.
49 E.Lecolinet,O.Baret.Cursive Word Recognition:Methods and Strategies:Springer Verlag,1994.
50 R.Bozinovic,S.N.Shrihari.String Correction Algorithm for Cursive Script Recognition.IEEE Trans On PAMI.1982,4(6):635-663.
51 M.Gilloux.Hidden Markov Models in handwriting Recognition:Springer Verlag,1994.
52 Strathy N W,Suen C Y,Kryzak A.Segmentation of handwritten digits using contour features.In:Second Int.Conf.Document Anal.Recognition,Oct.1993.577-580.
53 Hoschek W.Peer-to-peer Grid Databases for Web Service Discovery,Grid computing:Making the Global Infrastructure a Reality.NOV.2002.
54 Stocia,Morris R,Karger D,Kaashoek M F,Balakrishnan h.Chord:A scalable peer-to-peer lookup service for internet application.Submission to ACM SIGCOMM,2001.
55 Vermal K,ET al.METEOR-S WSDI:A Structure of Registries for semantic publication and discovery of web service.Http://lsdis.cs.uga.edu/lib/ download/MWSDI.pdf,2002.
56 Zhao B Y,Kubiatowicz J,Joseph A D,Tapestry:An infrastructure for Fault-tolerant widearea location and routing.Technical report No.UCB/CSD-01-1141,Computer science division,university of California at Berkeley,April 2001.
57 Zhonglong Zheng,Jie Jiang.Supervised locality persuit embedding for pattern classification.Image and Vision Computing.2006,24(8):819-826.
58 Yuanyan Tang,Jiming Liu,Hong Ma,et al.Wavelet orthonormal decompositions for extraction feature in pattern recognition.International journal of pattern recognition and artificial intelligence.1999,13(6):803-831.
59 沈会良,李志能.基于矩和小波变换的数字字母识别研究.中国图象图形学报.2000,5(3):249-252.
60 S.Omachi,H.Aso.A qualitative adaptation of subspace method for character recognition.System and computers in Japan,2000,31(12):1-10.
61 梁志贞,施鹏飞.核不相关鉴别分析以及它在字符识别中的应用.计算机研究与发展.2006,43(1):132-137.
62 Kukhwan Seo.Comparison of Feature Performance and its Application to Feature Combination in Off-line Handwritten Korean Alphabet Recognition.International Journal of Pattern Recognition and Artificial Intelligence.1998,12(2):251-261.
63 Lionel Prevost,Loic Oudot and Alvaro Moises,et al.Hybrid Generative/Discriminative Classifier for Unconstrained Character Recognition.Pattern Recognition Letters.2005,26(12):1840-1848.
64 An-Bang Wang and Kuo-Chin Fan.Optical Recognition of Handwritten Chinese Characters by Hierarchical Radical Matching Method.Pattern Recognition,2001,34(1):15-35.
65 马俊莉,莫玉龙,王明祥.一种基于改进模板匹配的车牌字符识别方法.小型微型计算机系统.2003,24(9):1670-1672.
66 B.Verma,et al.Fusion of Multiple Handwritten Word Recognition Techniques.Pattern Recognition Letters.2001,(2):991-998.
67 张军,戚飞虎,叶芗芸.用于字符识别的椭圆基函数概率神经网络.红外与毫米波学报.1998,17(2):91-97.
68 居琰,江同庆,刘建胜等.基于集成RBF神经网络的小类别手写体汉字识别系统.计算机工程与应用.2002,(23):100-102,158.
69 Md.Rafiul Hassan,Baikunth Nath and Michael Kirley.A Fusion Model of HMM,ANN and GA for Stock Market Forecasting.Expert Systems with Applications.2007,33(1):171-150.
70 J.J.Buckley,Y.Hayashi.Fuzzy Neural Networks:A Survey.Fuzzy Sets and Systems.1994,66(1):1-13.
71 C.Comes,V.N.Vapnik,Support Vector Networks.Machine Learning.1995,20:273-297.
72 张学工.关于统计学习理论与支持向量机.自动化学报.2000,26(1):32-42.
73 E.Osuna,R.Freund,F.Giori.Training Support Vector Machines:An Application to Face Detection.In:Proc.of CVPR 97,Puerto Rico,1997:130-136.
74 T.Joachims.Text Categorization with Support Vector Machines:Learning with Many Relevant Features.Machine Learning.1998,11398:137-142.
75 K.L.Kim,K.Jung and S.H.Park.Supervised Texture Segmentation Using Support Vector Machines.IEEE Electronics Letters,1999,3(22):1935-1936.
76 N.Marie,I.Guyon,and J.Denker,et al.Writer Adaptation for On-line Handwritten Character Recognition.2nd International Conference On Pattern Recognition and Document Analysis.1993:157-191.
77 梁路宏,艾海舟,肖习攀等.基于模板匹配与支持向量机的人脸检测.计算机学报.2002,25(1):22-29.
78 WANG Zhijun,Ziou D.Costas Armenakis,et al.A comparative analysis of image fusion methods[J].IEEE Transactions on Geoscience and Remote Sensing,2005,43(6):1391-1402.
79 李弼程,彭天强,彭波,等.智能图像处理技术[M].北京:电子工业出版社,2004:269-281.
80 闫敬文,卓琳,屈小波.图像融合研究最新进展.厦门理工学院学报[J],2007,15(4):44-49.
81 J.Rocha,T.Pravlidis,A Shape analysis model wit application to a character recognition system[C].IEEE Trans,Pattern Anal.Mach.Intell.1994,16(4):393-404.
82 Chen Hongxi.A Simplified Method of Edge Growing[J],Journal of LanZhou jiaotong university,2004,23(6):35-38.
83 Liu Hongyan,Li Qi,YANG Dongwei.A Method of Repairing Figure Strokes Based on End-point Direction[J],Journal of university of electronic science and technology of China,2001,30(5):516-519.
84 Basak J,Chanda B.On Edge and Line Linking with Connectionist Mode[J].IEEE Transaction.On Syst,Man,Cybernet,1994,24(3):413-428.
85 Feng Lin,Yan Shipeng,Sun Tao.A Contour Extraction Algorithm of Special Region in Image Registration[J].Computer Technology and Development,2006,16(3):11-13.
86 张燕,曾立波,吴琼水,谢文娟.一种适用于任意形状区域的快速孔洞填充算法.计算机应用研究,2004,12:155-156.
87 Shi,V.Govindaraju,Character image enhancement by selective region growing,Pattern Recogn.1996(17):523-527.
88 G.M.Geraets,A.N.van Daatselaar,J.G.C.Verheij.An efficient filling algorithm for counting regions.Computer Methods and Programs in Biomedicine,2004(76),1-11.
89 王琪,王丽萍,陈凯迪.一种简单的图案填充算法.微计算机信息,2005,21(9-3):116-117.
90 王三福,李莉,张念喜.对区域填充算法的一点改进.天水师范学院学报,2006,26(2):17-20.
91 张志龙,李吉成,沈振康.一种新的快速复杂连通区域扫描线填充算法.计算机工程与应用,2004,40(31):6-8.
92 余腊生,沈德耀.扫描线种子填充算法的改进.计算机工程,2003,29(10):70-72
93 李桂清,李陶深.扫描线种子填充算法的问题及改进.广西大学学报(自然科学版),1998,23(3):207-211.
94 Stark H,Oskoui P.High-resolution image recovery from image-planear rays using convex projections[J].Journal of the Opt.Soc.of America,1989,6(11):1715-1726.
95 M.Irani and S.Peleg.Improving resolution by images registration.Graphical Models and Image Processing,1991,53:231-239.
96 Assaf Zomet,Alex Rav-Acha,Shmuel Peleg:Robust Super-Resolution.CVPR(1) 2001:645-650.
97 Keren D,Peleg S,Brada R.Image sequence enhancement using sub-pixel displacement[C].Proceedings IEEE Conference on Computer Vision and Pattern Recognition.1988:742 - 746.
98 R.Y.Tsai and T.S.Huang.Multipleframe image restoration and registration [C].In advances in computer vision and image processing.Greenwich,CT:JAI Press Inc.1984:317-339.
99 H.C.Andrews,B.R.Hunt.Digital image restoration.Englewood Clifs,N.J.:Prentice-Hall,1977.
100 Xuechuan Wang,et al.Feature extraction and dimensionality reduction algorithms and their applications in vowel recognition[J].Pattern recognition,2003(36):2429-2439.
101 曹建海.金属标牌压印凹凸字符的检测与识别研究[D].济南:山东大学,2004,80-82.
102 Abd-Krim Seghouane,Andrzej Cichocki.Bayesian estimation of the number of principal components[J].Signal Processing,2007,87:562-568.
103 Xuelei Hu,Lei Xu,A comparative investigation on subspace dimension determination[J],Neural Networks,2004(17):1051-1059.
104 Dietmar cordes,Rajesh R.Nandy.Eatimation of the intrinsic dimensionality of fMRI data[J],NeuroImage,2006(29):145-154.
105 Hu M K.Visual pattern recognition by moment invariant[J].IEEE Trans.On Information Theory,1962,8(2):179-187.
106 S.Dudani,K.Breeding,R.McGhee.Aircraft identification by moment invariants[J].IEEE Trans,Comput,C-26.1977:39-45.
107 Y.S.Abu-Mostafa,D.Psaltis.Recognitive aspects of moment invariants [J].IEEE Trans,PAMI-6.1984,698-706.
108 T.H.Resis.The revised fundamental theorem of moment invariants[J].IEEE Trans,PAMI-13.1991,830-834.
109 Dai M,Baylou P,Najim M.An efficient algorithm for computation of shape moments from run-length codes or chain codes[J].Pattern recognition,1992,25(10):1119-1128.
110 芮挺,王金岩,沈春林,等.基于线形分析的特征不变性目标识别[J].计算机工程,2005,31(15):4-6.
111 芮挺,等.基于ICA的特征不变性目标识别[J].小型微型计算机系统,2005,26(3):505-508.
112 王其聪.基于小波分析的矩特征和神经网络的图像识别[D].杭州:浙江工业大学,2005,11-17.
113 王峻峰,等.基于主分量分析的信号白化解相关处理[J].中国机械工程,2005,16(21):1954-1956.
114 T.Korenius,et al.On principal component analysis,cosine and Euclidean measures information retrieval[J].Informat.Sci.(2007),doi:10.1016/j.ins.2007.05.027.
115 E.Salinelli,C.Sgarra.Shift,slope and curvature for a class of yields correlation matrices[J],Linear Algebra Appl.2007,doi:10.1016/j.laa.2007.05.041
116 E.Oja.The ALSM algorithm:an improved subspace method of classification.Recognition[J],1983,16(4):421-427.
117 Tindall D W,Application of neural network techniques to automatic license plate recognition[C].In European Convention on Security and Detection[C].Brighron,England,1995:81-85.
118 Liu wei-yi,Sheng yi-qiang,Qiao Hui et al.Characteristic Dot Matching Method of Realizing Rapidly Recognition of the Number Plate[J],Journal of OPTOELECTRONICS·LASER,2002,13(3):274-276.
119 Song Jiatao,Liu Jilin,Analysis and Extraction of Structural Features of Alphabetic and Digital Characters on Vehicle License Plate[J],Journal of image and graphics,Vol.7(A) No.9.2002.9:945-949.
120 Fu Qingling,Han Liqun.Recognition for handwritten numbers based on artificial neuron network[J],Journal of Beijing Technology and business university(Natural science edition),2004,22(3):43-45.
121 Deng Lihua,Cui Zhiqing,Zhang Jing.Recognition for Handwriting Numbers Based on Artificial Neural Network[J],Journal of China three gorges university(Natural science),2005,27(3):254-256.
122 Trier O D.Jain A K,Taxt T.Feature extraction method for character recognition A survey[J].Pattern Recognition,1996,9(4):641-662.
123 张金国,吕庭豪.基于MATLAB的改进模板匹配方法的机器人目标识别系统,机器人,2003,25(7):623-625.
124 崔政,李壮,两种改进的模板匹配识别算法,计算机过程与设计,2006,27(6):1083-1085.
125 左力,图像处理系统在自动化设备中用作位置反馈的一种方法,机械与电子,2004(1):43-44.
126 Kosuke Mitani,Hitoshi Saji.Robust template matching by using variable size block division.Optomechatronic machine vision,Sapporo,Japan,Sumi,Kazuhiko,2005:298-305.
127 Takahiro Mae,Shun'ichi Kaneko,Takayuki Tanaka.Efficient template matching algorithm based on interval estimations on correlation.Optomechatronic machine vision,Sapporo,Japan,Sumi,Kazuhiko,2005:13-22.
125 Di Stefano L,Mattoccia S.fast template matching using bounded partial correlation,Machine Vision and Applications 2003,3(4):213-221
129 Wang Hongjie,Guo Wengang,Lt) Fuyun etc.Application of laser etching technology[J],Infrared and laser engineering,2004,33(5):469-472.
130 杨蕊红,潘泉,程咏梅.三维飞机目标识别的一种新方法[J].计算机仿真,2006,23(6):82-85.
131 张丽珂,张鹏翀.相关跟踪算法在水下高速运动体识别中的研究,哈尔滨工程大学学报,Vol 27,No4,2006,526-529.
132 徐玉秀,周晓梅,闻邦椿.薄壁圆盘裂纹的应变分形特征及诊断识别研究,振动与冲击,Vol 26,No 5,2007,8-10.
133 M.Turk,A.Pentland.Eigenfaces for Recognition.Journal of Cognitive Neuroscience.1991,3(1):71-86.
134 李学勇,路长厚,李建美.基于重构误差的单类子空间压印凹凸字符识别.机械工程学报,2008,44(5):181-185.
135 S.Mika,G.R(a|¨)tsch,J.Weston,et al.Construction Descriptive and Discriminative Non-Linear Features:Rayleigh Coefficients in Kernel Feature Spaces.IEEE Transaction on Pattern Analysis and Machine Intelligence.2001,25(5):623-628.
136 K.R.Muller,S.Mika,G.Ratsch,et al.An Introduction to Kernel-Based Learning Algorithms.IEEE Transactions on Neural Network.2001,12(2):181-201.
137 P.N.Belhumeur,J.P.Hespanha,D.J.Kriegman.Eigenfaces Vs.Fisherfaces:Recognition Using Class Specific Linear Projection.IEEE Trans On PAMI.1997,19(7):711-720.
138 J.W.Lu,K.N.Plataniotis,A.N.Venetsanopoulos.Face Recognition Using Kernel Direct Discriminant Analysis Algorithms.IEEE Transactions on Neural Networks.2003,14(1):117-126.
139 M.S.Bartlet,J.R.Movellan,T.J.Sejnowski.Face Recognition by Independent Component Analysis.IEEE Trans.On Neural networks.2002,13(6):450-146.
140 孙即祥.现代模式识别.长沙:国防科技大学出版社,2002
141 周彦平,舒锐,陶坤宇,等.空间目标光电探测与识别技术的研究.光学技术,2007,33(1),68.73+76.
142 阎建国,高亮,卢京潮.图象处理技术在车牌识别中的应用.电子技 术应用.2000,(1):1 1 7-1 87
143 Wai-Tak Wong,Frank Y.Shih and Jung Liu.Shape-based Image Retrieval Using Support Vector Machines,Fourier Descriptors and Self-organizing Maps.Information Sciences.2007,177(8):1878-1891
144 Chert Zhi-jun,Lin Yu-chi,Zhao Mei-rong,etc.Pretreatment Algorithm of Numeric Character Auto Recognition in View Field of Eye Lens on Universal Tools Microscope[J],Journal of Optoelectronics·Laser,2005,16(1):80-82.
145 Xue Bingru,Yang Jingyu,Lou Zhen.Etc.Eliminate Glitch and Glitch Join in Handwriting Chinese Characters[J].Journal of NanJing university of science and technology,1999.23.(2):141-144(in Chinese)
146 Niu Xin,Shen Lansun.Research on License Plate Recognition Technology[J],Measurement & Control technology,1999,18(12):14-17.
147 Xuan Guorong,Yang Jie,Ye Chengzhou,Number-Plate Character Recognition[J].Journal of Shanghai Jiaotong university,2000,34(5):672-675.
148 Dahai Cheng,Hong Yan.Recognition of handwritten digits based on contour information[J].Pattern Recognition,1998,31(3):235-255.
149 Z.Z.Li,H.J,Li.Recognition of handwritten characters by parts with multiple orientations[J].Mathematical and computer modeling,2002,35:441-479.
150 Adnan Amin.Recognition of hand-printed characters based on structural description and inductive logic programming[J].Pattern recognition letters,2003(24):3187-3196.
151 李建美.标牌压印字符图像获取与处理中的关键技术研究.山东大学博士论文.2008:9.
152 冯德军,马梁,陶华敏.基于置信度分析的导弹目标距离像序贯识别[J],雷达科学与技术,2007,5(5):358.364.
153 林晓帆,丁晓青.最近邻分类器置信度估计的理论分析[J].科学通报,1998,43(3):322-325.
154 CANDES E J.Ridgelets.Theory and Applications[D].Ph.D.Thesis,Department of Statistics,Stanford University,1998.
155 PENNEC E,MALLAT S.Bandelet Image Approximation and Compression [J].SIAM Journal of Multiscale Modeling and Simulation,2005,4(3):992-1039.
156 Candes E J,Donoho L.Curvelet-A surprisingly effective non-adaptive representation for objects with edges[A].TN:Vanderbilt University Press,2000:105-120.
157 DONOHO M N,VETIERLI M.Beyond Wavelets[M].New York:Academic Press,2002:1-27.
158 Wen Dou,Yun Hao,Chen,et al.A general framework for component substitution image fusion:An implementation using the image fusion method[J].Computers and Geosciences,2007,33(2):219-228.
159 Zheng Du,Myong K J.Band Selection of Hyperspectral Images for Automatic Detection of Poultry Skin Tumors[J].IEEE Trans.on Automation Science and Engineering,2007,4(3):332-339.
160 NI Wei,GUO Bao-long,YANG Liu.Data Fusion of Multisensor Remote Sensing Images using Region Based Contourlet Contrast[J].Journal of Astronautics,2007,28(2):364-369.
161 李美丽,王红梅,李言俊等.一种基于非采样Contourlet变换的图像融合算法[J].宇航学报,2008,29(5):1627-1631
162 刘贵喜,杨万海.基于小波分解的图像融合方法及性能评价[J].自动化学报,2002,28(6):927-934.
163 王林艳,陶玲,王惠南.CT与MRI图像融合的评价方法研究.生物医学工程研究[J].2007,25(4):247-250.
164 吴燕,刘重阳,廖桂生.一种新的像素级多聚焦图像融合算法.电子与信息学报[J],2007,29(12):2800-2804.
165 王海晖,彭嘉雄,吴巍.评价多传感器图像融合效果方法的比较.红外与激光工程[J].2004,33(2):189-193.
2 Sung Cheol Park, Min Kyu Park, and Moon Gi Kang. Super-resolution image reconstruction a technical overview. IEEE Signal Processing Magazine 20:2 1-36, May 2003.
3 Michael K. Ng and Nirmal K. Bose. Mathematical analysis of super-resolution methodology. IEEE Signal Processing Magazine. MAY 2003.
4 Sean Borman, Robert Stevenson. Spatial resolution enhancement of low-resolution image sequences: a comprehensive review with directions for future research, Indiana: Laboratory for Image and Signal Analysis in University of Notre Dame, 1998.
5 Rafael Molina, Miguel Vega, Javier Abad, et al. Estimation in Bayesian high-resolution image reconstruction with multisensors. IEEE Transactions on Image Processing, 2003, 12 (12): 996-1011.
6 Max Born and Emil Wolf. Principles of optics. Cambridge University Press, 1999.
7 J.A. Parker, R. V Kenyon, and D. E. Troxel. Comparison of interpolating methods for image resampling. IEEE Transactions on Medical Imaging, 1983,3 (2): 31-39.
8 P. Vandewalle, S. S usstrunk, and M. Vetterli. Super resolution images reconstructed from aliased images. In SPIE/IS&T Visual Communication and Image Processing Conference, Ebrahimi and T.Sikora, Eds. 5150, July 2003:1398-1405.
9 Barbara Zitova, Jan Flusser. Image registration methods: a survey. Image and Vision Computing 21, 2003:977-1000.
10 J.B.Antoine Maintzl and Max A.Viergever.An Overview of Medical Image Registration Methods.Imaging Science Department,Imaging Center Utrecht.
11 P.A.van den Elsen,E.J.D.Pol,and M.A.Viergever.Medical image matching- a review with classification.IEEE Engineering in medicine and biology,12(1):26-39,1993.
12 Lisa Gottesfeld Brown.A survey of image registration techniques Department of Computer Science.Columbia of University.January 12,1992.
13 Jian-xiong Dong,Adam Krzy(?)ak and Ching Y.Suen.An Improved Handwritten Chinese Character Recognition System Using Support Vector Machine.Pattern Recognition Letters.2005,26(12):1849-1856.
14 A.Basu,C.Watters and M.Shepherd.Support Vector Machines for Text Categorization.Proceedings of 36th Annual Hawaii International Conference on System Sciences.2003,1:103-109.
15 A.R.Ahmad,M.Khalid and R.Yusof.Kernel Methods and Support Vector Machines for Handwriting Recognition.Student Conference of Research and Development.2002:309-312.
16 A.Mitiche,J.K.Aggarwa.Pattern Category Assignment by Neural Networks and Nearest Neighbors Rule:A Synopsis and A Characterization.International Journal of Pattern Recognition and Artificial Intelligence.1996,10(5):393-408.
17 l-Seok Oh,Ching Y.Suen.A Class-modular Feed-forward Neural Network for Handwriting Recognition.Pattern Recognition.2002,35(1):229-244.
18 刘建胜,汪同庆,居琰.基于神经网络和学习子空间的OCR识别方法在选票处理中的应用.计算机工程.2002,28(11):36-38.
19 E.Oja.The ALSM Algorithm:an Improved Subspace Method of Classification.Pattern Recognition,1983,16(4):421-427.
20 M.Prakash,M.Narasimha Murty.Hebbian Learning Subspace Method:A New Approach.Pattern Recognition.1997,30(1):141-149.
21 蒋伟峰,刘济林.基于PCA学习子空间算法的有限汉字识别.中国图象图形学报.2001,6(2):186-190.
22 M.Aksela,J.Laaksonen.Adaptive Combination of Adaptive Classifiers for Handwritten Character Recognition.Pattern Recognition Letters.2007,25(1):136-143.
23 L.Xu,A.Krzyzak and C.Y.Suen.Methods for Combining Multiple Classifiers and Their Applications in Handwritten Character Recognition.IEEE Trans.Systems,Man,and Cybernetics.1992,22:418-435.
24 T.K.Ho,J.J.Hull and S.N.Srihari.Decision Combination in Multiple Classifier Systems.IEEE Trans.Pattern Analysis and Machine Intelligence.1994,16(1):66-75.
25 Louisa Lam,Ching Y.Suen.Optimal Combinations of Pattern Classifiers.Pattern Recognition Letters.1995,16(9):945-954.
26 Chien-Hsing Chou,Chin-Chin Lin and Ying-Ho Liu,et al.A Prototype Classification Method and Its Use in a Hybrid Solution for Multi-class Pattern Recognition.Pattern Recognition.2006,39(4):624-634.
27 李新,夏定元.玻璃瓶字符识别中运动图像的获取.光通信技术.2004,(4):62-64.
28 汪蕙,鲍旭东,罗立民.车轮序列号自动识别系统.测控技术.2002,21(7):23-25.
29 戴鲲,张大力.火车标牌识别系统的设计与实现.计算机工程.2001,27(11):106-107,161.
30 苏健平,陈志强.集装箱检测信息自动采集系统的箱号识别策略.核电子与探测技术.2003,23(4):333-336.
31 徐蔚然.基于知识的银行票据二值化方法.中文信息学报.2002,16(2):60-64
32 S.M.Pizer,E.P.Ambum and J.D.Austin,et al.Adaptive Histogram Equalization and Its Variation.Computer Vision Graphics Image Process.1957,39(3):355-368.
33 K.W.Leszczynski,S.Shalev.A Robust Algorithm for Contrast Enhancement by Local Histogram Modification.Image and Vision Computing.1989,7(3):704-711.
34 Y.Choi and R.Krishnapuram.A Robust Approach to Image Enhancement Based on Fuzzy Logic.IEEE Trans.On Image Processing.1997,6(6):685-693.
35 Yeong taeg Kim.Contrast Enhancement Using Brightness Preserving Bi-histogram Equalization.IEEE Trans.on Consumer Electronics.1997,43(1):1-8
36 E.L.Hall.Almost Uniform Distribution for Computer Image Enhancement.IEEE Trans.Comput..1984,C-33:207-208.
37 周妮娜,王敏,黄心汉.车牌字符识别的预处理算法.计算机工程与应用.2003,(15):220-221,232.
38 陈强,朱立新,夏德深.结合Canny算子的图像二值化.计算机辅助设计与图形学报.2005,17(6):1302-1306.
39 李国平.基于莫尔技术的标牌凹凸字符图像获取与识别研究[D].山东大学博士论文.2007:3.
40 Y.J.Zhang.A Survey on Evaluation Methods for Image Segmentation.Pattern Recognition.1996,29(8):1335-1346
41 N.R.Pal,S.K.Pal.A Review on Image Segmentation Techniques.Pattern Recognition.1993,26(9):1277-1294.
42 吴一全,末兆达.图象处理中阈值选取方法30年(1962-1992)的进展(一).数据采集与处理.1993,8(3):193-201.
43 吴一全,末兆达.图象处理中阈值选取方法30年(1962-1992)的进展(二).数据采集与处理.1993,8(4):268-281.
44 Jianguo Wang,Hong Yan,Mending broken handwriting with a macrostructure analysis method to improve recognition[J].Pattern recognition letters,1999,20:855-864.
45 Donggang Yu,Hong Yan,reconstruction of broken handwritten digits based on structural morphological features[J].Pattern recognition,2001, 34:235-254.
46 Adrian P.Whichello,Hong Yan,linking broken character borders with variable sized masks to improve recognition[J].Pattern recognition,1996,29(8):1429-1435.
47 李学勇.金属标牌压印凹凸字符的特征提取和识别方法研究[D].山东大学博士论文,2008:5.
48 Yi Lu,Beverly Haist,Laurel Harmon,et al.An Accurate and Efficient System for Segmenting Machine-printed Text.US Postal Service 5th Advanced Technology Conference,Washington,DC,USA.1992,93-105.
49 E.Lecolinet,O.Baret.Cursive Word Recognition:Methods and Strategies:Springer Verlag,1994.
50 R.Bozinovic,S.N.Shrihari.String Correction Algorithm for Cursive Script Recognition.IEEE Trans On PAMI.1982,4(6):635-663.
51 M.Gilloux.Hidden Markov Models in handwriting Recognition:Springer Verlag,1994.
52 Strathy N W,Suen C Y,Kryzak A.Segmentation of handwritten digits using contour features.In:Second Int.Conf.Document Anal.Recognition,Oct.1993.577-580.
53 Hoschek W.Peer-to-peer Grid Databases for Web Service Discovery,Grid computing:Making the Global Infrastructure a Reality.NOV.2002.
54 Stocia,Morris R,Karger D,Kaashoek M F,Balakrishnan h.Chord:A scalable peer-to-peer lookup service for internet application.Submission to ACM SIGCOMM,2001.
55 Vermal K,ET al.METEOR-S WSDI:A Structure of Registries for semantic publication and discovery of web service.Http://lsdis.cs.uga.edu/lib/ download/MWSDI.pdf,2002.
56 Zhao B Y,Kubiatowicz J,Joseph A D,Tapestry:An infrastructure for Fault-tolerant widearea location and routing.Technical report No.UCB/CSD-01-1141,Computer science division,university of California at Berkeley,April 2001.
57 Zhonglong Zheng,Jie Jiang.Supervised locality persuit embedding for pattern classification.Image and Vision Computing.2006,24(8):819-826.
58 Yuanyan Tang,Jiming Liu,Hong Ma,et al.Wavelet orthonormal decompositions for extraction feature in pattern recognition.International journal of pattern recognition and artificial intelligence.1999,13(6):803-831.
59 沈会良,李志能.基于矩和小波变换的数字字母识别研究.中国图象图形学报.2000,5(3):249-252.
60 S.Omachi,H.Aso.A qualitative adaptation of subspace method for character recognition.System and computers in Japan,2000,31(12):1-10.
61 梁志贞,施鹏飞.核不相关鉴别分析以及它在字符识别中的应用.计算机研究与发展.2006,43(1):132-137.
62 Kukhwan Seo.Comparison of Feature Performance and its Application to Feature Combination in Off-line Handwritten Korean Alphabet Recognition.International Journal of Pattern Recognition and Artificial Intelligence.1998,12(2):251-261.
63 Lionel Prevost,Loic Oudot and Alvaro Moises,et al.Hybrid Generative/Discriminative Classifier for Unconstrained Character Recognition.Pattern Recognition Letters.2005,26(12):1840-1848.
64 An-Bang Wang and Kuo-Chin Fan.Optical Recognition of Handwritten Chinese Characters by Hierarchical Radical Matching Method.Pattern Recognition,2001,34(1):15-35.
65 马俊莉,莫玉龙,王明祥.一种基于改进模板匹配的车牌字符识别方法.小型微型计算机系统.2003,24(9):1670-1672.
66 B.Verma,et al.Fusion of Multiple Handwritten Word Recognition Techniques.Pattern Recognition Letters.2001,(2):991-998.
67 张军,戚飞虎,叶芗芸.用于字符识别的椭圆基函数概率神经网络.红外与毫米波学报.1998,17(2):91-97.
68 居琰,江同庆,刘建胜等.基于集成RBF神经网络的小类别手写体汉字识别系统.计算机工程与应用.2002,(23):100-102,158.
69 Md.Rafiul Hassan,Baikunth Nath and Michael Kirley.A Fusion Model of HMM,ANN and GA for Stock Market Forecasting.Expert Systems with Applications.2007,33(1):171-150.
70 J.J.Buckley,Y.Hayashi.Fuzzy Neural Networks:A Survey.Fuzzy Sets and Systems.1994,66(1):1-13.
71 C.Comes,V.N.Vapnik,Support Vector Networks.Machine Learning.1995,20:273-297.
72 张学工.关于统计学习理论与支持向量机.自动化学报.2000,26(1):32-42.
73 E.Osuna,R.Freund,F.Giori.Training Support Vector Machines:An Application to Face Detection.In:Proc.of CVPR 97,Puerto Rico,1997:130-136.
74 T.Joachims.Text Categorization with Support Vector Machines:Learning with Many Relevant Features.Machine Learning.1998,11398:137-142.
75 K.L.Kim,K.Jung and S.H.Park.Supervised Texture Segmentation Using Support Vector Machines.IEEE Electronics Letters,1999,3(22):1935-1936.
76 N.Marie,I.Guyon,and J.Denker,et al.Writer Adaptation for On-line Handwritten Character Recognition.2nd International Conference On Pattern Recognition and Document Analysis.1993:157-191.
77 梁路宏,艾海舟,肖习攀等.基于模板匹配与支持向量机的人脸检测.计算机学报.2002,25(1):22-29.
78 WANG Zhijun,Ziou D.Costas Armenakis,et al.A comparative analysis of image fusion methods[J].IEEE Transactions on Geoscience and Remote Sensing,2005,43(6):1391-1402.
79 李弼程,彭天强,彭波,等.智能图像处理技术[M].北京:电子工业出版社,2004:269-281.
80 闫敬文,卓琳,屈小波.图像融合研究最新进展.厦门理工学院学报[J],2007,15(4):44-49.
81 J.Rocha,T.Pravlidis,A Shape analysis model wit application to a character recognition system[C].IEEE Trans,Pattern Anal.Mach.Intell.1994,16(4):393-404.
82 Chen Hongxi.A Simplified Method of Edge Growing[J],Journal of LanZhou jiaotong university,2004,23(6):35-38.
83 Liu Hongyan,Li Qi,YANG Dongwei.A Method of Repairing Figure Strokes Based on End-point Direction[J],Journal of university of electronic science and technology of China,2001,30(5):516-519.
84 Basak J,Chanda B.On Edge and Line Linking with Connectionist Mode[J].IEEE Transaction.On Syst,Man,Cybernet,1994,24(3):413-428.
85 Feng Lin,Yan Shipeng,Sun Tao.A Contour Extraction Algorithm of Special Region in Image Registration[J].Computer Technology and Development,2006,16(3):11-13.
86 张燕,曾立波,吴琼水,谢文娟.一种适用于任意形状区域的快速孔洞填充算法.计算机应用研究,2004,12:155-156.
87 Shi,V.Govindaraju,Character image enhancement by selective region growing,Pattern Recogn.1996(17):523-527.
88 G.M.Geraets,A.N.van Daatselaar,J.G.C.Verheij.An efficient filling algorithm for counting regions.Computer Methods and Programs in Biomedicine,2004(76),1-11.
89 王琪,王丽萍,陈凯迪.一种简单的图案填充算法.微计算机信息,2005,21(9-3):116-117.
90 王三福,李莉,张念喜.对区域填充算法的一点改进.天水师范学院学报,2006,26(2):17-20.
91 张志龙,李吉成,沈振康.一种新的快速复杂连通区域扫描线填充算法.计算机工程与应用,2004,40(31):6-8.
92 余腊生,沈德耀.扫描线种子填充算法的改进.计算机工程,2003,29(10):70-72
93 李桂清,李陶深.扫描线种子填充算法的问题及改进.广西大学学报(自然科学版),1998,23(3):207-211.
94 Stark H,Oskoui P.High-resolution image recovery from image-planear rays using convex projections[J].Journal of the Opt.Soc.of America,1989,6(11):1715-1726.
95 M.Irani and S.Peleg.Improving resolution by images registration.Graphical Models and Image Processing,1991,53:231-239.
96 Assaf Zomet,Alex Rav-Acha,Shmuel Peleg:Robust Super-Resolution.CVPR(1) 2001:645-650.
97 Keren D,Peleg S,Brada R.Image sequence enhancement using sub-pixel displacement[C].Proceedings IEEE Conference on Computer Vision and Pattern Recognition.1988:742 - 746.
98 R.Y.Tsai and T.S.Huang.Multipleframe image restoration and registration [C].In advances in computer vision and image processing.Greenwich,CT:JAI Press Inc.1984:317-339.
99 H.C.Andrews,B.R.Hunt.Digital image restoration.Englewood Clifs,N.J.:Prentice-Hall,1977.
100 Xuechuan Wang,et al.Feature extraction and dimensionality reduction algorithms and their applications in vowel recognition[J].Pattern recognition,2003(36):2429-2439.
101 曹建海.金属标牌压印凹凸字符的检测与识别研究[D].济南:山东大学,2004,80-82.
102 Abd-Krim Seghouane,Andrzej Cichocki.Bayesian estimation of the number of principal components[J].Signal Processing,2007,87:562-568.
103 Xuelei Hu,Lei Xu,A comparative investigation on subspace dimension determination[J],Neural Networks,2004(17):1051-1059.
104 Dietmar cordes,Rajesh R.Nandy.Eatimation of the intrinsic dimensionality of fMRI data[J],NeuroImage,2006(29):145-154.
105 Hu M K.Visual pattern recognition by moment invariant[J].IEEE Trans.On Information Theory,1962,8(2):179-187.
106 S.Dudani,K.Breeding,R.McGhee.Aircraft identification by moment invariants[J].IEEE Trans,Comput,C-26.1977:39-45.
107 Y.S.Abu-Mostafa,D.Psaltis.Recognitive aspects of moment invariants [J].IEEE Trans,PAMI-6.1984,698-706.
108 T.H.Resis.The revised fundamental theorem of moment invariants[J].IEEE Trans,PAMI-13.1991,830-834.
109 Dai M,Baylou P,Najim M.An efficient algorithm for computation of shape moments from run-length codes or chain codes[J].Pattern recognition,1992,25(10):1119-1128.
110 芮挺,王金岩,沈春林,等.基于线形分析的特征不变性目标识别[J].计算机工程,2005,31(15):4-6.
111 芮挺,等.基于ICA的特征不变性目标识别[J].小型微型计算机系统,2005,26(3):505-508.
112 王其聪.基于小波分析的矩特征和神经网络的图像识别[D].杭州:浙江工业大学,2005,11-17.
113 王峻峰,等.基于主分量分析的信号白化解相关处理[J].中国机械工程,2005,16(21):1954-1956.
114 T.Korenius,et al.On principal component analysis,cosine and Euclidean measures information retrieval[J].Informat.Sci.(2007),doi:10.1016/j.ins.2007.05.027.
115 E.Salinelli,C.Sgarra.Shift,slope and curvature for a class of yields correlation matrices[J],Linear Algebra Appl.2007,doi:10.1016/j.laa.2007.05.041
116 E.Oja.The ALSM algorithm:an improved subspace method of classification.Recognition[J],1983,16(4):421-427.
117 Tindall D W,Application of neural network techniques to automatic license plate recognition[C].In European Convention on Security and Detection[C].Brighron,England,1995:81-85.
118 Liu wei-yi,Sheng yi-qiang,Qiao Hui et al.Characteristic Dot Matching Method of Realizing Rapidly Recognition of the Number Plate[J],Journal of OPTOELECTRONICS·LASER,2002,13(3):274-276.
119 Song Jiatao,Liu Jilin,Analysis and Extraction of Structural Features of Alphabetic and Digital Characters on Vehicle License Plate[J],Journal of image and graphics,Vol.7(A) No.9.2002.9:945-949.
120 Fu Qingling,Han Liqun.Recognition for handwritten numbers based on artificial neuron network[J],Journal of Beijing Technology and business university(Natural science edition),2004,22(3):43-45.
121 Deng Lihua,Cui Zhiqing,Zhang Jing.Recognition for Handwriting Numbers Based on Artificial Neural Network[J],Journal of China three gorges university(Natural science),2005,27(3):254-256.
122 Trier O D.Jain A K,Taxt T.Feature extraction method for character recognition A survey[J].Pattern Recognition,1996,9(4):641-662.
123 张金国,吕庭豪.基于MATLAB的改进模板匹配方法的机器人目标识别系统,机器人,2003,25(7):623-625.
124 崔政,李壮,两种改进的模板匹配识别算法,计算机过程与设计,2006,27(6):1083-1085.
125 左力,图像处理系统在自动化设备中用作位置反馈的一种方法,机械与电子,2004(1):43-44.
126 Kosuke Mitani,Hitoshi Saji.Robust template matching by using variable size block division.Optomechatronic machine vision,Sapporo,Japan,Sumi,Kazuhiko,2005:298-305.
127 Takahiro Mae,Shun'ichi Kaneko,Takayuki Tanaka.Efficient template matching algorithm based on interval estimations on correlation.Optomechatronic machine vision,Sapporo,Japan,Sumi,Kazuhiko,2005:13-22.
125 Di Stefano L,Mattoccia S.fast template matching using bounded partial correlation,Machine Vision and Applications 2003,3(4):213-221
129 Wang Hongjie,Guo Wengang,Lt) Fuyun etc.Application of laser etching technology[J],Infrared and laser engineering,2004,33(5):469-472.
130 杨蕊红,潘泉,程咏梅.三维飞机目标识别的一种新方法[J].计算机仿真,2006,23(6):82-85.
131 张丽珂,张鹏翀.相关跟踪算法在水下高速运动体识别中的研究,哈尔滨工程大学学报,Vol 27,No4,2006,526-529.
132 徐玉秀,周晓梅,闻邦椿.薄壁圆盘裂纹的应变分形特征及诊断识别研究,振动与冲击,Vol 26,No 5,2007,8-10.
133 M.Turk,A.Pentland.Eigenfaces for Recognition.Journal of Cognitive Neuroscience.1991,3(1):71-86.
134 李学勇,路长厚,李建美.基于重构误差的单类子空间压印凹凸字符识别.机械工程学报,2008,44(5):181-185.
135 S.Mika,G.R(a|¨)tsch,J.Weston,et al.Construction Descriptive and Discriminative Non-Linear Features:Rayleigh Coefficients in Kernel Feature Spaces.IEEE Transaction on Pattern Analysis and Machine Intelligence.2001,25(5):623-628.
136 K.R.Muller,S.Mika,G.Ratsch,et al.An Introduction to Kernel-Based Learning Algorithms.IEEE Transactions on Neural Network.2001,12(2):181-201.
137 P.N.Belhumeur,J.P.Hespanha,D.J.Kriegman.Eigenfaces Vs.Fisherfaces:Recognition Using Class Specific Linear Projection.IEEE Trans On PAMI.1997,19(7):711-720.
138 J.W.Lu,K.N.Plataniotis,A.N.Venetsanopoulos.Face Recognition Using Kernel Direct Discriminant Analysis Algorithms.IEEE Transactions on Neural Networks.2003,14(1):117-126.
139 M.S.Bartlet,J.R.Movellan,T.J.Sejnowski.Face Recognition by Independent Component Analysis.IEEE Trans.On Neural networks.2002,13(6):450-146.
140 孙即祥.现代模式识别.长沙:国防科技大学出版社,2002
141 周彦平,舒锐,陶坤宇,等.空间目标光电探测与识别技术的研究.光学技术,2007,33(1),68.73+76.
142 阎建国,高亮,卢京潮.图象处理技术在车牌识别中的应用.电子技 术应用.2000,(1):1 1 7-1 87
143 Wai-Tak Wong,Frank Y.Shih and Jung Liu.Shape-based Image Retrieval Using Support Vector Machines,Fourier Descriptors and Self-organizing Maps.Information Sciences.2007,177(8):1878-1891
144 Chert Zhi-jun,Lin Yu-chi,Zhao Mei-rong,etc.Pretreatment Algorithm of Numeric Character Auto Recognition in View Field of Eye Lens on Universal Tools Microscope[J],Journal of Optoelectronics·Laser,2005,16(1):80-82.
145 Xue Bingru,Yang Jingyu,Lou Zhen.Etc.Eliminate Glitch and Glitch Join in Handwriting Chinese Characters[J].Journal of NanJing university of science and technology,1999.23.(2):141-144(in Chinese)
146 Niu Xin,Shen Lansun.Research on License Plate Recognition Technology[J],Measurement & Control technology,1999,18(12):14-17.
147 Xuan Guorong,Yang Jie,Ye Chengzhou,Number-Plate Character Recognition[J].Journal of Shanghai Jiaotong university,2000,34(5):672-675.
148 Dahai Cheng,Hong Yan.Recognition of handwritten digits based on contour information[J].Pattern Recognition,1998,31(3):235-255.
149 Z.Z.Li,H.J,Li.Recognition of handwritten characters by parts with multiple orientations[J].Mathematical and computer modeling,2002,35:441-479.
150 Adnan Amin.Recognition of hand-printed characters based on structural description and inductive logic programming[J].Pattern recognition letters,2003(24):3187-3196.
151 李建美.标牌压印字符图像获取与处理中的关键技术研究.山东大学博士论文.2008:9.
152 冯德军,马梁,陶华敏.基于置信度分析的导弹目标距离像序贯识别[J],雷达科学与技术,2007,5(5):358.364.
153 林晓帆,丁晓青.最近邻分类器置信度估计的理论分析[J].科学通报,1998,43(3):322-325.
154 CANDES E J.Ridgelets.Theory and Applications[D].Ph.D.Thesis,Department of Statistics,Stanford University,1998.
155 PENNEC E,MALLAT S.Bandelet Image Approximation and Compression [J].SIAM Journal of Multiscale Modeling and Simulation,2005,4(3):992-1039.
156 Candes E J,Donoho L.Curvelet-A surprisingly effective non-adaptive representation for objects with edges[A].TN:Vanderbilt University Press,2000:105-120.
157 DONOHO M N,VETIERLI M.Beyond Wavelets[M].New York:Academic Press,2002:1-27.
158 Wen Dou,Yun Hao,Chen,et al.A general framework for component substitution image fusion:An implementation using the image fusion method[J].Computers and Geosciences,2007,33(2):219-228.
159 Zheng Du,Myong K J.Band Selection of Hyperspectral Images for Automatic Detection of Poultry Skin Tumors[J].IEEE Trans.on Automation Science and Engineering,2007,4(3):332-339.
160 NI Wei,GUO Bao-long,YANG Liu.Data Fusion of Multisensor Remote Sensing Images using Region Based Contourlet Contrast[J].Journal of Astronautics,2007,28(2):364-369.
161 李美丽,王红梅,李言俊等.一种基于非采样Contourlet变换的图像融合算法[J].宇航学报,2008,29(5):1627-1631
162 刘贵喜,杨万海.基于小波分解的图像融合方法及性能评价[J].自动化学报,2002,28(6):927-934.
163 王林艳,陶玲,王惠南.CT与MRI图像融合的评价方法研究.生物医学工程研究[J].2007,25(4):247-250.
164 吴燕,刘重阳,廖桂生.一种新的像素级多聚焦图像融合算法.电子与信息学报[J],2007,29(12):2800-2804.
165 王海晖,彭嘉雄,吴巍.评价多传感器图像融合效果方法的比较.红外与激光工程[J].2004,33(2):189-193.