航空气象地图的分层化OCR系统及其若干关键技术的研究
|
摘要
OCR(Optical Character Recognition光学字符识别)系统技术是一种专门针对电子文本信息化处理的系统。随着电子文本的日新月异的发展,目前国内外针对常规性对象(26个大小写字母和10个数字)的主流OCR系统已经显现出无法满足现实需求的情况,尤其遇到像航空气象地图这样的复杂背景下的大信息量(其不仅包含线条,而且包含着字符和特殊气象符号)电子文本而言可以说是束手无策。
本文依托企业项目“航空气象地图分层化OCR技术的研究”,在分析国内外的相关理论及关键技术的基础上,以架构航空气象地图的分层化OCR系统结构为目标,而且对其中的前景区域和背景区域的图像分割算法、图文分离算法、线条的重组识别算法、字符特征的提取和识别等一系列相关的关键技术和迫切需要解决的效果问题展开了深入而细致的相应研究和讨论,其主要的研究内容及成果如下:
(1).提出了一种有效的图像前景区域和背景区域的分割模型(二维直方图熵值斜分算法),此外又根据K-L距离理论,提出了一种可避免繁琐计算,更能全面直观反映指标的仿K-L距离评判函数。该种分割方法建立在局部区域信息统计和全局区域信息统计的整体之上,可以有效的避免了在复杂背景下常规彩色分割方法失效的情况发生,而且又克服了常规的灰度分割法中的双刃剑问题:如果仅仅采用局部分割法容易造成全局信息上的分割错误和如果仅仅采用全局分割法容易造成局部信息上缺损和不完善。
(2).根据形态学的相关理论推导出了一个有效的图文分离算法,而且给出了形态学方法中的关键部分:结构元素的主要参数。对比目前常用的图文分离算法,该方法具有实现简单,速度快、分离之后的结果完整性好等优点。
(3).提出了一种专门针对线条提取重组、识别的快速算法,可以填补目前暂无有效的线条重组、识别算法的空白。该算法主要依据线条与线条之间的数学关系表达式理论和粒子群快速算法(PSO)理论下完成,它在具有了粒子群算法的较快速度的优点之外,还具有较高的重组准确度,从而可以为间断的实线进行修复。此外,根据线条类型之间的差异(虚线符合规律分布、间断直线不符合规律分布),提出了利用能量函数来区分其之间的可靠识别方法。
(4).提出了另外一种改进型复数矩的数学表达式,并在该式的基础上进行了矩不变量的推导和矩不变量阶数范围的证明。该表达式主要根据目前最为先进的中心矩方法、复数矩方法上整合得到,不仅具有中心矩的位置不变性优点,也具有了复数矩的多坐标系转化能力。此外,也根据相关的定理和实验证明出了对于不变量特征的选取不能仅仅局限在独立与非独立范围上,应该转化为在全局上选取最优。
(5).提出了一种基于多层结构的Winner-Update标准互相关矩不变量的特征匹配方法。该方法主要依据Jensen’s和Cauchy-Schwarz不等式理论,在Winner-Update方法和深度优先搜索的DGA图的辅助下,能够有效的解决标准互相关函数的计算量繁琐问题以及上小节提到的特征不变量的优良选取问题。此外,该方法运用了多学科的知识交叉,利用了数据库技术中的Hash表来有效的提高最终结果的搜索和信息存储优化等问题。
(6).依据以上提出的单个字符识别算法和仿生学滴水分割算法的相关理论,提出了针对粘连字符的分割识别算法。其中重点针对仿生学滴水算法中存在的问题,利用相关的交叉学科理论(经典的牛顿物理运动学理论)进行了相应改进和完善,从而使仿生学滴水算法的效果得到了大幅度的提高,可以在花费较短的时间内保证目前所归纳的三种粘连字符(线性粘连、非线性粘连和粘连重合)的分割准确性和识别率。
应用了以上理论及关键技术,成功设计和完成了针对航空气象地图的分层化OCR系统处理平台。对比目前常规的系统测试表明:该系统具有很强的信息分析和处理能力,不仅对于系统中的图文分离算法和图像分割算法之后的结果能够保证了信息的完整性和准确性,而且最终也能够较好的完成字符、线条的重组识别(数据识别率高达98%以上),完全达到实际工作的要求,很好地达到了本文研究的目的。
OCR (Optical Characters Recognition) system is one system which is dealt with the digital document. Along with the development of digital document, the traditional OCR system has been represented the weakness. Specially, when meets the digital document such as Aerial Meteorological Maps which is in the complex circumstance and abundant data including the characters, signs and lines it couldn’t resolve.
The subject investigated in this dissertation came from the commercial project“OCR System for the Aerial Meteorological Maps with Digitalization and hiberarchy”. Based on the analysis of the reasearch status and existing problems of the theories and related technologies for OCR system, the research work, which would be discussed about the related important fundamental theory and approaches for Image Segmentation, the Seperation between the figure and text and Object recognition, has been done to achieve the target of developing the experimental prototype of OCR System for the Aerial Meteorological Maps with Digitalization and hiberarchy. The main research contents and findings are under follow:
(1) We propose an effective approach for segmentation of the foreground and background based on the Oblique 2-D Histogram of Entropy. Moreover, according to the theory of K-L distance, we propose another measurement due to derease the complexity and the cost of time. The whole approach is based on the combination between the part information and whole information, which could resolve two edges sword problem as the segmentation in part information would bring the errors of the segmentation in the whole, the whole segmentation would bring the half-baked information in the part area.
(2) For the seperation approach between the figure and text, we are mainly depended on the theoretical proof by the morphology. But in this approach there is one important structure item which is decided to the effect of whole. So through the theoretical derivation and experiment, we prove the size of the item and analyze the related reasons for effection. Compared with the traditional approaches, this approach represents well in the time, speed and percent of recognition.
(3) We propose one new effective approach for line recompose、recognition which could fill out the blank in this area. According to the mathematical expression for the line to line and PSO algorithm, we discuss and analyze further and systematically the related theories, so the proposed approach own the merits that is not only fast but also is the accurate for the recomposition which could be repaired for Real-line. Furthermore, we also find the discrepancy between the different styles of lines (Dashed-line and Real-line), which Dash-line is counted by the result of regular distribution, Real-line vice versa. So the energy function could achieve this goal to separate.
(5) We propose one novel moment expression. According to it, we deduce the moment invariants and proof the range of moment invariants orders. This approach is mainly based on the Center Moment and Complex Moment, so it owns the merits from two aspects: not only has none influences by the orientation, but also could change into other expressions in the different polars. Moreover, we also point out the problem for the moment invariants that not dependent or independent invariants are the best. If want to do better, we should select the invariants in the whole orders.
(6) For the single characters pattern matching, we propose the multi-level Normalized Cross Correlation algorithm. This approach by the Jensen’s and Cauchy-Schwarz inequality, DGA graphical structure and Breath-First Searching rules, and the winner-update algorithm could resolve well for the problems which are the better invariants need to select again in the whole orders and the high cost of time. Moreover, this approach used the theory of database in the Hash Table could improve the performance in the searching final result and allocate the memory rationally.
(7) Related to single character recogniton and the bionic Drop-Falling Algorithm for segmentation, we would expand the approach into resolving the recognition of merged-characters. Specially, aiming to the existed problems in the process of Drop-Falling Algorithm, we introduce the theory of kinematics into algorithm. So the approach would be more reasonable and perfect. For experimental results, it has better performances cost the short time wherever in the linear merged, nonlinear merged and overlapped.
The theory and key technologies mentioned above employed, a prototype of OCR system has been fabricated sucessfully. It is shown by its test results that can genertate the better recognition percent for the characters or lines (above 98%), ensure the intact results after the image segmentation and seperation between the text and figures. The research work of this dissertation is helpful to advance the development of OCR system.
本文依托企业项目“航空气象地图分层化OCR技术的研究”,在分析国内外的相关理论及关键技术的基础上,以架构航空气象地图的分层化OCR系统结构为目标,而且对其中的前景区域和背景区域的图像分割算法、图文分离算法、线条的重组识别算法、字符特征的提取和识别等一系列相关的关键技术和迫切需要解决的效果问题展开了深入而细致的相应研究和讨论,其主要的研究内容及成果如下:
(1).提出了一种有效的图像前景区域和背景区域的分割模型(二维直方图熵值斜分算法),此外又根据K-L距离理论,提出了一种可避免繁琐计算,更能全面直观反映指标的仿K-L距离评判函数。该种分割方法建立在局部区域信息统计和全局区域信息统计的整体之上,可以有效的避免了在复杂背景下常规彩色分割方法失效的情况发生,而且又克服了常规的灰度分割法中的双刃剑问题:如果仅仅采用局部分割法容易造成全局信息上的分割错误和如果仅仅采用全局分割法容易造成局部信息上缺损和不完善。
(2).根据形态学的相关理论推导出了一个有效的图文分离算法,而且给出了形态学方法中的关键部分:结构元素的主要参数。对比目前常用的图文分离算法,该方法具有实现简单,速度快、分离之后的结果完整性好等优点。
(3).提出了一种专门针对线条提取重组、识别的快速算法,可以填补目前暂无有效的线条重组、识别算法的空白。该算法主要依据线条与线条之间的数学关系表达式理论和粒子群快速算法(PSO)理论下完成,它在具有了粒子群算法的较快速度的优点之外,还具有较高的重组准确度,从而可以为间断的实线进行修复。此外,根据线条类型之间的差异(虚线符合规律分布、间断直线不符合规律分布),提出了利用能量函数来区分其之间的可靠识别方法。
(4).提出了另外一种改进型复数矩的数学表达式,并在该式的基础上进行了矩不变量的推导和矩不变量阶数范围的证明。该表达式主要根据目前最为先进的中心矩方法、复数矩方法上整合得到,不仅具有中心矩的位置不变性优点,也具有了复数矩的多坐标系转化能力。此外,也根据相关的定理和实验证明出了对于不变量特征的选取不能仅仅局限在独立与非独立范围上,应该转化为在全局上选取最优。
(5).提出了一种基于多层结构的Winner-Update标准互相关矩不变量的特征匹配方法。该方法主要依据Jensen’s和Cauchy-Schwarz不等式理论,在Winner-Update方法和深度优先搜索的DGA图的辅助下,能够有效的解决标准互相关函数的计算量繁琐问题以及上小节提到的特征不变量的优良选取问题。此外,该方法运用了多学科的知识交叉,利用了数据库技术中的Hash表来有效的提高最终结果的搜索和信息存储优化等问题。
(6).依据以上提出的单个字符识别算法和仿生学滴水分割算法的相关理论,提出了针对粘连字符的分割识别算法。其中重点针对仿生学滴水算法中存在的问题,利用相关的交叉学科理论(经典的牛顿物理运动学理论)进行了相应改进和完善,从而使仿生学滴水算法的效果得到了大幅度的提高,可以在花费较短的时间内保证目前所归纳的三种粘连字符(线性粘连、非线性粘连和粘连重合)的分割准确性和识别率。
应用了以上理论及关键技术,成功设计和完成了针对航空气象地图的分层化OCR系统处理平台。对比目前常规的系统测试表明:该系统具有很强的信息分析和处理能力,不仅对于系统中的图文分离算法和图像分割算法之后的结果能够保证了信息的完整性和准确性,而且最终也能够较好的完成字符、线条的重组识别(数据识别率高达98%以上),完全达到实际工作的要求,很好地达到了本文研究的目的。
OCR (Optical Characters Recognition) system is one system which is dealt with the digital document. Along with the development of digital document, the traditional OCR system has been represented the weakness. Specially, when meets the digital document such as Aerial Meteorological Maps which is in the complex circumstance and abundant data including the characters, signs and lines it couldn’t resolve.
The subject investigated in this dissertation came from the commercial project“OCR System for the Aerial Meteorological Maps with Digitalization and hiberarchy”. Based on the analysis of the reasearch status and existing problems of the theories and related technologies for OCR system, the research work, which would be discussed about the related important fundamental theory and approaches for Image Segmentation, the Seperation between the figure and text and Object recognition, has been done to achieve the target of developing the experimental prototype of OCR System for the Aerial Meteorological Maps with Digitalization and hiberarchy. The main research contents and findings are under follow:
(1) We propose an effective approach for segmentation of the foreground and background based on the Oblique 2-D Histogram of Entropy. Moreover, according to the theory of K-L distance, we propose another measurement due to derease the complexity and the cost of time. The whole approach is based on the combination between the part information and whole information, which could resolve two edges sword problem as the segmentation in part information would bring the errors of the segmentation in the whole, the whole segmentation would bring the half-baked information in the part area.
(2) For the seperation approach between the figure and text, we are mainly depended on the theoretical proof by the morphology. But in this approach there is one important structure item which is decided to the effect of whole. So through the theoretical derivation and experiment, we prove the size of the item and analyze the related reasons for effection. Compared with the traditional approaches, this approach represents well in the time, speed and percent of recognition.
(3) We propose one new effective approach for line recompose、recognition which could fill out the blank in this area. According to the mathematical expression for the line to line and PSO algorithm, we discuss and analyze further and systematically the related theories, so the proposed approach own the merits that is not only fast but also is the accurate for the recomposition which could be repaired for Real-line. Furthermore, we also find the discrepancy between the different styles of lines (Dashed-line and Real-line), which Dash-line is counted by the result of regular distribution, Real-line vice versa. So the energy function could achieve this goal to separate.
(5) We propose one novel moment expression. According to it, we deduce the moment invariants and proof the range of moment invariants orders. This approach is mainly based on the Center Moment and Complex Moment, so it owns the merits from two aspects: not only has none influences by the orientation, but also could change into other expressions in the different polars. Moreover, we also point out the problem for the moment invariants that not dependent or independent invariants are the best. If want to do better, we should select the invariants in the whole orders.
(6) For the single characters pattern matching, we propose the multi-level Normalized Cross Correlation algorithm. This approach by the Jensen’s and Cauchy-Schwarz inequality, DGA graphical structure and Breath-First Searching rules, and the winner-update algorithm could resolve well for the problems which are the better invariants need to select again in the whole orders and the high cost of time. Moreover, this approach used the theory of database in the Hash Table could improve the performance in the searching final result and allocate the memory rationally.
(7) Related to single character recogniton and the bionic Drop-Falling Algorithm for segmentation, we would expand the approach into resolving the recognition of merged-characters. Specially, aiming to the existed problems in the process of Drop-Falling Algorithm, we introduce the theory of kinematics into algorithm. So the approach would be more reasonable and perfect. For experimental results, it has better performances cost the short time wherever in the linear merged, nonlinear merged and overlapped.
The theory and key technologies mentioned above employed, a prototype of OCR system has been fabricated sucessfully. It is shown by its test results that can genertate the better recognition percent for the characters or lines (above 98%), ensure the intact results after the image segmentation and seperation between the text and figures. The research work of this dissertation is helpful to advance the development of OCR system.
引文
[1] U. Garain and B. B. Chaudhuri. Segmentation of Touching Symbols for OCR of Printed Mathematical Expression: A Approach based on Multifactorical Analysis. 2005 International Conference on Document Analysis Recogniton (ICDAR’05). Vol 1:177-181
[2] M. Demi, F. Faita and V. Gemignani. A pair of on-center and off-center filters derived from the first absolute central moment: a pair of on-center and off-center filters. 2005 International Conference on Image Processing (ICIP’05). Vol 3:594-552
[3] I. Ymasaki. Quantitative Evaluation of Print Quality for Optical Character Recognition Systems. IEEE Transactions on System, Man and Cybernetics, 1978, 8(5):371-381
[4] R. S. Apsey. Human Factors of Constrained Handprint for OCR. IEEE Transactions on System, Man and Cybernetics, 1978, 8(4):292-296
[5] M. C. Rahier and P. G. A. Jenspers. Dedicated LSI for a Microprocessor-Controlled Hand-Carried OCR System. IEEE Journals of Solid-State Circuits, 1980, 15(1):15-24
[6] M. C. Rahier and P. G. A. Jenspers. Dedicated LSI for a Microprocessor-Controlled Hand-Carried OCR System. IEEE Transactions on Computers, 1980, 29(2):79-88
[7] J. D. Legat, P. D. Muelenaere and P. G. A. Jenspers. A Full Custom Integrated Circuit For Document Analysis System. IEEE Journals of Solid-State Circuits, 1985, 20(3):730-740
[8] F. W. M. Stentiford. Automatic Feature Design for Optical Character Recognition Using Evolutionary Search Procedure. IEEE Transactions on Pattern Analysis and Machine Intelligent, 1985, 7(3):349-353
[9] R. Kasturi and J. Alemany. Information Extraction from Images of Paper-Based Maps. IEEE Transactions on Software Engineering, 1988, 14(5):671-675
[10] L. A. Fletcher and R. Kasturi. A Robust Algorithm for Text String Separation from Mixed/TextGraphics Images. IEEE Transactions on Pattern Analysis and Machine Intelligent, 1988, 10(6):910-918
[11] L. Boatto, V. Consorti et al.. An Interpretation System for Land Register Maps. IEEE Transactions on Computers, 1992, 25(7):25-33
[12] C. P. Lai and R. Kasturi. Detection of Dimension Sets in Engineering Drawings. IEEE Transactions on Pattern Analysis and Machine Intelligent, 1994, 16(8):848-855
[13] M. E. Dehkordi, N. Sherkat and R. J. Withrow. A Principal Component Approach to Classification Handwrittern Words. 1999 International Conference on Document Analysis Recogniton (ICDAR’99), pp: 781-784
[14] E. Bruzzone and M. C. Coffetti. An Algorithm for Extracting Cursive Text Lines. 1999 International Conference on Document Analysis Recogniton (ICDAR’99), pp: 749-752
[15] M. Thulke and V. M?rgner. Quality Evaluation of Document Segmentation Results. 1999 International Conference on Document Analysis Recogniton (ICDAR’99), pp: 1
[16] C. M. Tstai and H. J. Lee. Binarization of Color Document Image via Luminance and Saturation Color Features. IEEE Transactions on Image Processing, 2002, 11(4): 434-451
[17] K. V. Kostas, A. I. Ginnis, and P.D. Kaklis. A Scan-Line Algorithm for Clustering Line Segments. 2004 ACM International Conference on Shape Modeling, pp. 379-392
[18] A. Dawoud. Iterative Cross Section Sequence Graph for Handwritten Character Segmentation. IEEE Transactions on Image Processing, 2007, 16(8): 2150-2154
[19] C. Monteleoni and M. K??ri?inen. Practical Online Active Learning for Classification. 2007 International Conference on Computer Vision and Pattern Recognition (CVPR’07), Vol. 1, pp: 1-8
[20] M. Seeger and C. Dance. Binarising Camera Images for OCR. 2001 International Conference on Document Analysis Recogniton (ICDAR’01), pp: 54-58
[21] D. J. Lee and S. W. Lee. A new methodology for gray-scale character segmentation and recognition. 1995 International Conference on Document Analysis Recogniton (ICDAR’95), pp: 524-527
[22] S. W. Lee, D. J. Lee and H. S. Park. A new methodology for gray-scale character segmentation and recognition. IEEE Transactions on Pattern Analysis and Machine Intelligent, 1996, 18(10):1045-1050
[23] Y. Ariki and Y. Motegi. Segmentation and recognition of handwritten characters using subspace method.1995 International Conference on Document Analysis Recogniton (ICDAR’95), pp: 120-123
[24] S. Ariyoshi. A character segmentation method for Japanese printed documents coping with touching character problems. 1992 International Conference on Pattern Recognition (ICPR’92), pp: 313-316
[25] J. H. Si, F. Yang and X. D. Tian. A new algorithm of mixed Chinese-English character segmentation based on irregularty degree. 2008 International Conference on Machine Learning and Cybernetics (ICMLC’92), vol. 1: 2461-2465
[26] B. Sankur and M. Sezgin. Image Thresholding Techniques: A Suvey over Categories. Pattern Recognition, 2001, Under Reviewer.
[27] B. Sankur and M. Sezgin. Survey over Image Thresholding techniques and quantitative performance evaluation. Journal of Electronic Imaging. 2004, 13(1): 146-165
[28] J. Angulo and J. Serra. Color Segmentation By Order Mergings. 2003 International Conference on Image Processing (ICIP’03). Vol 2:125-128
[29] X. Yan, Y. B. Chen, Q. M. Liao, W. H. Leung and S. M. Fung. A Novel Binarization System for Degraded Document Images. 2007 International Conference on Document Analysis Recogniton (ICDAR’07), pp: 287-291
[30] J. N. Kapur, P. K. Sahoo and A. K. C. Wong. A new method for grey-level picture thresholding using the entropy of the histogram. Comput. Vis. Graph. Image Process, 1985, 29: 273-285
[31] A. S. Abutaleb. Automatic thresholding of grey-level pictures using two-dimensional entropy. Comput. Vis. Graph. Image Process, 1989, 47: 22-32
[32] P. K. Sahoo, G. Arora. Image Thresholding using two-dimensional Tsallis-Havrda-Charvát entropy. Pattern Recognition, 2006, 27(6): 520-528
[33] Y. Q. Wu, Z. Pan and W. Y. Wu. Tsallis-Havrda-Charvát Entropy Image Thresholding based on Two-dimensional Histogram Obique Segmentation. Chinese Journal of Optical Electronic Engineering, 2008, 35(1): 53-58
[34] C.–I. Chang, Y. Du, J. Wang, S.–M. Guo and P. D. Thouin. Survey and comparative analysis of entropy and relative entropy thresholding techniques. 2006, IEE Proceeding on Vision Image and Signal Processing (VISG’06), 153(6), pp: 837-850
[35] P. K. Sahoo, G. Arora. A thresholding method based on two-dimensional Renyi’s entropy. Pattern Recognition, 2004, 37(6): 1149-1161
[36] C. Tsallis. Possible generation of Boltzman-Gibbs Statistics. Journal of Physics. 1988, 52(1): 479-487
[37] N. R. Pal and S. K. Pal. Entropic Thresholding. Signal Process, 1989, 16: 97-108.
[38] J. Kittler and J. Illingworth. Minimum error thresholding. Pattern Recognition, 1986, 19(1): 41-47
[39] S.–K Lee, C.–S. Lo, C.–M. Wang, P.–C. Chung , C. -I. Chang, C.–W. Yang and P.–C. Hsu. A computer-aided design mammography screening system for detection and classification of microcalcifications. Journal of Medical Information, 2000, 60(1): 29-57
[40] S. Kullback and R. A. Leibler. On Information and Sufficiency. The Annals of Mathematical Statistics. 1951, 22(1):79-86
[41] W. Niblack. An Introduction to Digital Image Processing. Englewood Cliffs, Prentice Hall, 1986, 115-116
[42] N. Otsu. A Threshold Selection Method from Gray-level Histograms. IEEE Transactions on System, Man and Cybernetics, 1979, 9(1):62-66
[43] P. K. Sahoo, S. Soltani, A. K. C. Wong and Y. C. Chen. A survey of thresholding Techniques. Comput. Vis. Graph. Image Process, 1988, 41: 233-260
[44] S. U. Lee, S. Y. Chung and R. H. Park. A comparative performance study of several global thresholding techniques for segmentation. Comput. Vis. Graph. Image Process, 1990, 52: 171-190
[45] R. Gonzalez and J. Woods. Digital image processing. 1992, Addison-Wesley
[46] I. Pitas, S. W. Lee and A. N. Venetsanopoulos. Morphological Shape Decomposition. IEEE Transactions on Pattern Analysis and Machine Intelligent, 1990, 12(1):38-45
[47] A. Rosenfield. Axial Representation of Shape. Comput. Vis. Graph. Image Process, 1986, 33: 156-173
[48] L. Lam, S. W. Lee and C. Y. Suen. Thinning Methodologies-A Comprehensive Survey. IEEE Transactions on Pattern Analysis and Machine Intelligent, 1992, 14(9):869-885
[49] L. A. Fletcher and R. Kasturi. A Robust Algorithm for Text String Separation from Mixed Text/Graphics Images. IEEE Transactions on Pattern Analysis and Machine Intelligent, 1988, 10(6):910-918
[50] R. Kasturi, S. T. Bow, W. El-Masri, J. Shah, J. R. Gattiker, and U. B. Mokate. A System for interpretation of line drawings. IEEE Transactions on Pattern Analysis and Machine Intelligent, 1990, 12(10):978-992
[51] D. Dori and W. Liu. Vector-based segmentation of text connected to graphics in engineering drawings. in International Proceedings of the 6th International Workshop on Advances in Structural and Syntactical Pattern Recognition, Springer, 1996, 1121:322-331
[52] Z. Lu. Dectection of text regions from digital engineering drawings. IEEE Transactions on Pattern Analysis and Machine Intelligent, 1998, 20(4):431-439
[53] H. Luo, G. Agam, and I. Dinstein, Directional mathematical morphology approach for line thnning and extraction of character strings from maps and line drawings. 1995 International Conference on Document Analysis Recogniton (ICDAR’95), pp: 257-260
[54] J. Kennedy, R. Eberhart and Y. Shi. Swarm Intelligence. Morgan Kaufman. New York. 2001
[55] V. D. Merwe and A. P. Engelbrecht. Data clustering using particle swarm optimization. 2003 IEEE International Proceeding on Evolutionary Computation (CEC’03), pp: 215-220
[56] J. F. Blinn. Line in Space. Part 5: A Tale Of Two Lines. IEEE Magazine Computer Graphics and Application, 2003, 23(6): 84-97
[57] J. F. Blinn. Line in Space. Part 1: The 4D Cross Product. IEEE Magazine Computer Graphics and Application, 2001, 23(2): 72-79
[58] D. Dori and W. Y. Liu. Vector-based segmentation of text connected to graphics in engineering drawings. Advances in Structural and Syntactical Pattern Recognition, P. Perner, P. Wang, A. Rosenfeld (eds.), Springer, 1996, pp. 322–331
[59] D. Dori, W. Y. Liu and M. Peleg. How to Win a Dashed Line Detection Contest. Kasturi R, Tombre K (eds), Graphics Recognition–Methods and Applications (Lecture Notes in Computer Science, 1072). Springer-Verlag, Berlin, 1996, pp 286–300
[60] G. Wolberg. Monotonic Cubic Spline Interpolation. 1999 International Proceeding on Computer Graphics (IPIG’99), pp: 188-195
[61] T. Lundahl, W. J. Ohley, S. M. Kay and R. Siffert. Fractional Brownian Motion: A Maximum Likelihood Estimator and Its Application to Image Texture. IEEE Transctions on Medical Imaging, 1986, 5(3): 152-161
[62] J. M. Keller, R. M. Crownover and R. Y. Chen. Characteristics of Natural Scenes Related to the Fractal Dimension. IEEE Transactions on Pattern Analysis and Machine Intelligent, 1987, 9(5):621-627
[63] C. M. Bishop. Pattern Recognition and Machine Learning. U. K. Springer-Verlag. 2006
[64] T. Hamamuri, T. Akagi and B. Irie. An Analytic Word Recognition Algorithm Using a Posteriori Probability. 2007 International Conference on Document Analysis Recogniton (ICDAR’07), pp: 669-673
[65] T. Hamamuri, T. Akagi and B. Irie. An A Posteriori Probability Calculation Method for AnalyticWord Recognition Applicable to Address Recognition. 2009 International Conference on Document Analysis Recogniton (ICDAR’09), vol. 1: 391-395
[66] J. Kautsky, J. Flusser and F. Sroubek. Implicit Invariants and Object Recognition. 2007 Biennial Conference of Australian Pattern Recogniton on Digital Image Computing Techniques and Applications (DICTA’07), vol.1: 462-469
[67] Y. Shinagawa. Homotopic Image Pseudo-Invariants for Openset Object Recognition and Image Retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligent, 2008, 30(11):1891- 1901
[68] S. Nilufar, N. Ray and H. Zhang. Optimum kernel function design from scale space features for object detection. 2009 International Conference on Image Processing (ICIP’09). Vol 1:861-864
[69] C. J. Liu. Gabor-based kernel PCA with fractional power polynomial models for face recognition. IEEE Transactions on Pattern Analysis and Machine Intelligent, 2004, 26(5):572-581
[70] M. Hu. Visual pattern recognition by moment invariants. IRE Trans. of Information Theory, 1962, 8: 179-187
[71] E. B. Elliot. Algebra of Quantics. 1913, Oxford Uni. Press, New York
[72] I. Balslev, K. D?ring, R. D. Eriksen. Weighted Central Moment in Pattern Recognition. Pattern Recogniton, 2000, 21(5): 381-384
[73] S. Maitra. Moment Invariants. 1979 International Proceeding of IEEE, 67(4):697-699
[74] C.–H. The, R. T. Chin. On Image Analysis by the Methods of Moments. IEEE Transactions on Pattern Analysis and Machine Intelligent, 1988, 10(4):496-513
[75] Y. S. ABU-MUSTAFA and D. Psaltis. Recognitive Aspect of Moment Invariants. IEEE Transactions on Pattern Analysis and Machine Intelligent, 1984, 6(6):698-706
[76] A. Wallin, O. Kubler. Complete sets of complex Zernike moment invariants and the role of the pseudo invariants. IEEE Transactions on Pattern Analysis and Machine Intelligent, 1995, 17(11):1106-1110
[77] J. Flusser. On the Independence of Rotation Moment Invariants. Pattern Recognition, 2000, 33(9):1405-1410
[78] J. Flusser, T. Suk. Rotation Moment Invariants for Recognition of Symmetric Objects. IEEE Transactions on Image Processing, 2006, 15(12):3784-3790
[79] M. Schlemmer, M. Heringer, et al.. Moment Invariants for the Analysis of 2-D Flow Fields. IEEE Transactions on Visualization and Computer Graphics, 2007, 13(6): 1743-1750
[80] B. Ng*, R. Abugharbieh, X. M. Huang, M. J. Mckeown. Spatial Characterization of fMRI Activation Maps Using Invariant 3-D Moment Descriptors. IEEE Transactions on Medical Imaging, 2009, 28(2): 261-268
[81] J. Flusser. Moment Invariants in Image Analysis. 2006 International Proceeding of World Academy of Science, Engineering and Technology (WASET’06), vol. 11: 196-201
[82] G. I. Salama and A. Y. Abbott. Moment Invariants and Quantization Effects. 1998 International Conference on Computer Vision and Pattern Recognition (CVPR’98), Vol. 1: 157-163
[83] Avanindra and S. Chaudhuri. Robust Detection of Skew in Document Images. IEEE Transa- ctions on Image Processing, 1997, 6(2):344-349
[84] X. Chen and T.–J. Cham. Discriminative Distance Measures for Image Matching. 2004 International Conference on Pattern Recognition (ICPR’04), Vol. 3: 691-695.
[85] M. Ben-Bassat and L. Zaidenberg. Contextual Template Matching: A Distance Measure for Patterns with Hierarchically Dependent Features. IEEE Transactions on Pattern Analysis and Machine Intelligent, 1984, 6(2):201-211
[86] W. J. Williams and R. B. Rutledge. A generalized distortion analysis of a cross-correlation radar. 1965 International Proceeding of IEEE, 53(2): 200-201.
[87] J. P. Lewis. Fast Template Matching. Vision Interface, 1995, 1:120-123
[88] M. M. Donnel. Box-filtering Techniques. Comput. Vis. Graph. Image Process, 1981, 17 : 65-70
[89] P. Viola and M. Jones. Robust Real-time Face Detection. International Journal of Computer Vision, 2004, 52(2): 137-154.
[90] L. G. Brown. A Survey of Image Registeration Techniques. ACM Transactions on Computer Survey, 1992, 24(4): 325-376
[91] R. J. Prokop, A. P. Reeves. A survey of moment-based techniques for unoccluded object representation and recognition. Graphical Models and Image Processing, 1992, 54: 438-460
[92] L. D. L. Stefano and S. Mattoccia. A sufficient condition based on the Cauchy-Schwarz inequality for efficient template-matching. 2003 International Conference on Image Process (ICIP’03), vol.1: 14-17
[93] L. D. L. Stefano and S. Mattoccia. Fast Template Matching Using Bounded Partial Correlation. Machine Vision Learning, 2003, 13(4): 213-221
[94] Y. S. Chen, Y. P. Hung and C. S. Fuh. Fast Algorithm for Nearest Neighbor Search Based on a Lower Bound Tree. 2001 International Conference on Computer Vision (ICCV’01), vol. 1:446-453
[95] S. D. Wei and S. H. Lai. Fast Template Matching Based on Normalized Cross Correlation With Adaptive Multilevel Winner Update. IEEE Transactions on Image Processing, 2008, 17(11): 2227-2235
[96] S. D. Wei and S. H. Lai. Efficient Normalized Cross Correlation Based on Adaptive Multilevel Successive Elimination. 2007 Asian Conference on Computer Vision (ACCV’07), Part 1: 638-646
[97] C. H. Benett, G. Brassard, C. Crépeau, and U. M. Maurer. Generalized privacy amplification. IEEE Transactions on Information Theory, 1995, 41: 1915–1923
[98] J. L. Carter and M. N.Wegman. Universal classes of hash functions. Journal of Computer System Science, 1979, 18:143–154
[99] [99] T. Cover. A proof of data compression theorem of Slepian and Wolf for ergodic sources. IEEE Transactions on Information Theory, 1975, IT-21:226–228
[100] T. Cover and J. Thomas, Elements of Information Theory. New York: Wiley, 1991
[101] I. Csiszár. Linear codes for sources and source networks: Error exponents, universal coding. IEEE Transactions on Information Theory, 1982, IT-28: 585–592
[102] I. Csiszár and J. K?rner. Towards a general theory of source networks. IEEE Tranactions on Information Theory, 1980, IT-26:155–165
[103] J. Song, Li, M. R. Lyu and S. Cai. Recognition of Merged Characters Based on Forepart Prediction, Necessity-Sufficiency Matching, and Character-Adaptive Masking. IEEE Transactions on System, Man, Cybernetics. Part B: Cybernetics, 2005, 35(1): 2-11
[104] R. G. Casey and E. Lecolinet. A survey of methods and strategies in character segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligent, 1996, 18(7): 690-706
[105] T. Bayer and U. Krebel.Cut classification for segmentation. 1993 International Conference on Document Analysis Recognition (ICDAR’93), vol. 1: 565-568
[106] T. Bayer, U. Krebel, and M. Hammelsbeck.Segmenting merged characters. 1992 International Conference on Pattern Recognition (ICPR’92), vol. 1: 346-349
[107] Z. K. Lu, Z. R. Chi and W. C. Siu. Extraction and optimization of B-spline PBD templates for recognition of connected handwritten digit strings. IEEE Transactions on Pattern Analysis and Machine Intelligent, 2002, 24(1):132-139
[108] X. B. Liu and Y. D. Jia. Character Stroke Extraction Based on B-spline Curve Matching by Constrained Alternating Optimization. 2007 International Conference on Document Analysis Recognition (ICDAR’07), vol. 1: 13-17
[109] U. Garain and B. B. Chaudhuri. Segmentation of Touching Characters in Printed Devnagari and Bangla Scripts Using Fuzzy Multifactorial Analysis. IEEE Transactions on System, Man, Cybernetics. Part C: Reviews and Application, 2002, 32(4): 449-459
[110] S. Marinai, M. Gori and G. Soda. Artificial Neural Networks for Document Analysis and Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligent, 2007, 27(1): 23-35
[111] A. Dawoud. Iterative Cross Section Sequence Graph for Handwritten Character Segmentation. IEEE Transactions on Image Processing, 2007, 16(8): 2150-2154
[112] C. L. Liu, M. Koga and H. Fujisawa.Lexicon-Driven Segmentation and Recognition of Handwritten Character Strings For Janpanese Address Reading. IEEE Transactions on Pattern Analysis and Machine Intelligent, 2002, 24(11): 1425-1437
[113] S. Madhvanah and V. Govindadaraju. The Role of Holistic Paradigms in Handwrittern Word Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligent, 2001, 23(2): 149-164
[114] G. Mori and J. Malik. Recognition Objects in Adervesarial Clutter: Breaking A Visual CAPTCHA. 2003 International Conference on Computer Vision and Pattern Recognition (CVPR’03), vol. 1: 18-20
[115] J. Rocha and T. Pavlidis. Character recognition without segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligent, 1995, 17(9): 903-909.
[116] T. Nartker. IRSI Annual Report. Ph. D Dissertation, University of Nevada, Las Vegas, NV, 1993
[117] H. J. Lee and J. S Wang. Design of a Mathematical Expression Understanding System. Pattern Recognition Letters, 1997,18(3): 289-298
[118] Y. Lu. On the segmentation of touching characters. 1993 International Conference on Document Analysis Recognition (ICDAR’93), pp. 440-443
[119] S. Liang, M. Ahmadi and M. Shridhar. Segmentation of touching character in the printed document recognition. 1993 International Conference on Document Analysis Recognition (ICDAR’93), 1993, pp. 569-572
[120] F. Yin and C.–L. Liu. A Variational Bayes Method for Handwritten Text Line Segmentation. 2009 International Conference on Document Analysis Recognition (ICDAR’09), vol 1: 440-443
[121] J. Wang and J. Jean. Segmentation of merged characters by Neutral Networks and shortest path. Pattern Recognition, 1994, 27(5): 649-658
[122] G. Congedo, G. Dimauro, S. Impedovo and G. Pirlo. Segmentation of Numeric Strings. 1995 International Conference on Document Analysis Recognition (ICDAR’95), vol. 1: 1038-1041
[123] C. A.B. Carlos, E. Roe and E. B. Lacerda. Segmentation of Overlapping Cursive Handwritten Digits. 2008 ACM Conference on Symbol Document Engineering, vol 1: 271-278
[124] S. Khan, Character Segmentation Heuristics of Check Amount Verification, Master Thesis, Massachusetts Institute of Technology. 1998
[125] J. Punnoose, An Improved Segmentation Module for Identification of Handwritten Numerals, Master Thesis, Massachusetts Institute of Technology. 1999
[126] S. Dey, Adding Feedback to Improve Segmentation and Recognition of Handwritten Numerals, Master Thesis, Massachusetts Institute of Technology. 1999
[127] R. Ma, J. Du, Y. H. Gu and Y. Y. Yan, An Improved Drop-fall Algorithm Based on Backgrou- nd Analysis for Handwritten Digits Segmentation. 2009 Global Congress on Intelligent Systems (CIS’09), vol. 1: 374-378
[128] S. J. Lent. B.B.C. test chart 57, a new grey-scale reflectance chart for colour cameras. Radio and Electronic Engineering, 1971, 41(5): 237-240.
[129] T. Taxt. Recognition of Handwritten Symbols. Pattern Recognition, 1987, 23(11): 1155-11.
[130]宋怀波,路长厚,王富春.基于小区域字符模板匹配的金属标牌字符识别.武汉理工大学学报, 2007, 29(6):125-127
[131]邓红耀,管庶安,宋秀丽.投影和模版匹配相结合分割车牌字符.计算机工程与设计,2008,29(6):1568-1570
[132]崔正,李壮.两种改进的模版匹配识别算法.计算工程与设计,2006,27(6):1083-1085
[133]陈兵旗,孙明. Visual C++实用图像处理专业教程.北京:清华大学出版社,2004.
[134]熊伟,谢剑薇,曾峦.检测骨架图形特征点的新方法.红外和激光工程, 2002, 31(4):301-304
[2] M. Demi, F. Faita and V. Gemignani. A pair of on-center and off-center filters derived from the first absolute central moment: a pair of on-center and off-center filters. 2005 International Conference on Image Processing (ICIP’05). Vol 3:594-552
[3] I. Ymasaki. Quantitative Evaluation of Print Quality for Optical Character Recognition Systems. IEEE Transactions on System, Man and Cybernetics, 1978, 8(5):371-381
[4] R. S. Apsey. Human Factors of Constrained Handprint for OCR. IEEE Transactions on System, Man and Cybernetics, 1978, 8(4):292-296
[5] M. C. Rahier and P. G. A. Jenspers. Dedicated LSI for a Microprocessor-Controlled Hand-Carried OCR System. IEEE Journals of Solid-State Circuits, 1980, 15(1):15-24
[6] M. C. Rahier and P. G. A. Jenspers. Dedicated LSI for a Microprocessor-Controlled Hand-Carried OCR System. IEEE Transactions on Computers, 1980, 29(2):79-88
[7] J. D. Legat, P. D. Muelenaere and P. G. A. Jenspers. A Full Custom Integrated Circuit For Document Analysis System. IEEE Journals of Solid-State Circuits, 1985, 20(3):730-740
[8] F. W. M. Stentiford. Automatic Feature Design for Optical Character Recognition Using Evolutionary Search Procedure. IEEE Transactions on Pattern Analysis and Machine Intelligent, 1985, 7(3):349-353
[9] R. Kasturi and J. Alemany. Information Extraction from Images of Paper-Based Maps. IEEE Transactions on Software Engineering, 1988, 14(5):671-675
[10] L. A. Fletcher and R. Kasturi. A Robust Algorithm for Text String Separation from Mixed/TextGraphics Images. IEEE Transactions on Pattern Analysis and Machine Intelligent, 1988, 10(6):910-918
[11] L. Boatto, V. Consorti et al.. An Interpretation System for Land Register Maps. IEEE Transactions on Computers, 1992, 25(7):25-33
[12] C. P. Lai and R. Kasturi. Detection of Dimension Sets in Engineering Drawings. IEEE Transactions on Pattern Analysis and Machine Intelligent, 1994, 16(8):848-855
[13] M. E. Dehkordi, N. Sherkat and R. J. Withrow. A Principal Component Approach to Classification Handwrittern Words. 1999 International Conference on Document Analysis Recogniton (ICDAR’99), pp: 781-784
[14] E. Bruzzone and M. C. Coffetti. An Algorithm for Extracting Cursive Text Lines. 1999 International Conference on Document Analysis Recogniton (ICDAR’99), pp: 749-752
[15] M. Thulke and V. M?rgner. Quality Evaluation of Document Segmentation Results. 1999 International Conference on Document Analysis Recogniton (ICDAR’99), pp: 1
[16] C. M. Tstai and H. J. Lee. Binarization of Color Document Image via Luminance and Saturation Color Features. IEEE Transactions on Image Processing, 2002, 11(4): 434-451
[17] K. V. Kostas, A. I. Ginnis, and P.D. Kaklis. A Scan-Line Algorithm for Clustering Line Segments. 2004 ACM International Conference on Shape Modeling, pp. 379-392
[18] A. Dawoud. Iterative Cross Section Sequence Graph for Handwritten Character Segmentation. IEEE Transactions on Image Processing, 2007, 16(8): 2150-2154
[19] C. Monteleoni and M. K??ri?inen. Practical Online Active Learning for Classification. 2007 International Conference on Computer Vision and Pattern Recognition (CVPR’07), Vol. 1, pp: 1-8
[20] M. Seeger and C. Dance. Binarising Camera Images for OCR. 2001 International Conference on Document Analysis Recogniton (ICDAR’01), pp: 54-58
[21] D. J. Lee and S. W. Lee. A new methodology for gray-scale character segmentation and recognition. 1995 International Conference on Document Analysis Recogniton (ICDAR’95), pp: 524-527
[22] S. W. Lee, D. J. Lee and H. S. Park. A new methodology for gray-scale character segmentation and recognition. IEEE Transactions on Pattern Analysis and Machine Intelligent, 1996, 18(10):1045-1050
[23] Y. Ariki and Y. Motegi. Segmentation and recognition of handwritten characters using subspace method.1995 International Conference on Document Analysis Recogniton (ICDAR’95), pp: 120-123
[24] S. Ariyoshi. A character segmentation method for Japanese printed documents coping with touching character problems. 1992 International Conference on Pattern Recognition (ICPR’92), pp: 313-316
[25] J. H. Si, F. Yang and X. D. Tian. A new algorithm of mixed Chinese-English character segmentation based on irregularty degree. 2008 International Conference on Machine Learning and Cybernetics (ICMLC’92), vol. 1: 2461-2465
[26] B. Sankur and M. Sezgin. Image Thresholding Techniques: A Suvey over Categories. Pattern Recognition, 2001, Under Reviewer.
[27] B. Sankur and M. Sezgin. Survey over Image Thresholding techniques and quantitative performance evaluation. Journal of Electronic Imaging. 2004, 13(1): 146-165
[28] J. Angulo and J. Serra. Color Segmentation By Order Mergings. 2003 International Conference on Image Processing (ICIP’03). Vol 2:125-128
[29] X. Yan, Y. B. Chen, Q. M. Liao, W. H. Leung and S. M. Fung. A Novel Binarization System for Degraded Document Images. 2007 International Conference on Document Analysis Recogniton (ICDAR’07), pp: 287-291
[30] J. N. Kapur, P. K. Sahoo and A. K. C. Wong. A new method for grey-level picture thresholding using the entropy of the histogram. Comput. Vis. Graph. Image Process, 1985, 29: 273-285
[31] A. S. Abutaleb. Automatic thresholding of grey-level pictures using two-dimensional entropy. Comput. Vis. Graph. Image Process, 1989, 47: 22-32
[32] P. K. Sahoo, G. Arora. Image Thresholding using two-dimensional Tsallis-Havrda-Charvát entropy. Pattern Recognition, 2006, 27(6): 520-528
[33] Y. Q. Wu, Z. Pan and W. Y. Wu. Tsallis-Havrda-Charvát Entropy Image Thresholding based on Two-dimensional Histogram Obique Segmentation. Chinese Journal of Optical Electronic Engineering, 2008, 35(1): 53-58
[34] C.–I. Chang, Y. Du, J. Wang, S.–M. Guo and P. D. Thouin. Survey and comparative analysis of entropy and relative entropy thresholding techniques. 2006, IEE Proceeding on Vision Image and Signal Processing (VISG’06), 153(6), pp: 837-850
[35] P. K. Sahoo, G. Arora. A thresholding method based on two-dimensional Renyi’s entropy. Pattern Recognition, 2004, 37(6): 1149-1161
[36] C. Tsallis. Possible generation of Boltzman-Gibbs Statistics. Journal of Physics. 1988, 52(1): 479-487
[37] N. R. Pal and S. K. Pal. Entropic Thresholding. Signal Process, 1989, 16: 97-108.
[38] J. Kittler and J. Illingworth. Minimum error thresholding. Pattern Recognition, 1986, 19(1): 41-47
[39] S.–K Lee, C.–S. Lo, C.–M. Wang, P.–C. Chung , C. -I. Chang, C.–W. Yang and P.–C. Hsu. A computer-aided design mammography screening system for detection and classification of microcalcifications. Journal of Medical Information, 2000, 60(1): 29-57
[40] S. Kullback and R. A. Leibler. On Information and Sufficiency. The Annals of Mathematical Statistics. 1951, 22(1):79-86
[41] W. Niblack. An Introduction to Digital Image Processing. Englewood Cliffs, Prentice Hall, 1986, 115-116
[42] N. Otsu. A Threshold Selection Method from Gray-level Histograms. IEEE Transactions on System, Man and Cybernetics, 1979, 9(1):62-66
[43] P. K. Sahoo, S. Soltani, A. K. C. Wong and Y. C. Chen. A survey of thresholding Techniques. Comput. Vis. Graph. Image Process, 1988, 41: 233-260
[44] S. U. Lee, S. Y. Chung and R. H. Park. A comparative performance study of several global thresholding techniques for segmentation. Comput. Vis. Graph. Image Process, 1990, 52: 171-190
[45] R. Gonzalez and J. Woods. Digital image processing. 1992, Addison-Wesley
[46] I. Pitas, S. W. Lee and A. N. Venetsanopoulos. Morphological Shape Decomposition. IEEE Transactions on Pattern Analysis and Machine Intelligent, 1990, 12(1):38-45
[47] A. Rosenfield. Axial Representation of Shape. Comput. Vis. Graph. Image Process, 1986, 33: 156-173
[48] L. Lam, S. W. Lee and C. Y. Suen. Thinning Methodologies-A Comprehensive Survey. IEEE Transactions on Pattern Analysis and Machine Intelligent, 1992, 14(9):869-885
[49] L. A. Fletcher and R. Kasturi. A Robust Algorithm for Text String Separation from Mixed Text/Graphics Images. IEEE Transactions on Pattern Analysis and Machine Intelligent, 1988, 10(6):910-918
[50] R. Kasturi, S. T. Bow, W. El-Masri, J. Shah, J. R. Gattiker, and U. B. Mokate. A System for interpretation of line drawings. IEEE Transactions on Pattern Analysis and Machine Intelligent, 1990, 12(10):978-992
[51] D. Dori and W. Liu. Vector-based segmentation of text connected to graphics in engineering drawings. in International Proceedings of the 6th International Workshop on Advances in Structural and Syntactical Pattern Recognition, Springer, 1996, 1121:322-331
[52] Z. Lu. Dectection of text regions from digital engineering drawings. IEEE Transactions on Pattern Analysis and Machine Intelligent, 1998, 20(4):431-439
[53] H. Luo, G. Agam, and I. Dinstein, Directional mathematical morphology approach for line thnning and extraction of character strings from maps and line drawings. 1995 International Conference on Document Analysis Recogniton (ICDAR’95), pp: 257-260
[54] J. Kennedy, R. Eberhart and Y. Shi. Swarm Intelligence. Morgan Kaufman. New York. 2001
[55] V. D. Merwe and A. P. Engelbrecht. Data clustering using particle swarm optimization. 2003 IEEE International Proceeding on Evolutionary Computation (CEC’03), pp: 215-220
[56] J. F. Blinn. Line in Space. Part 5: A Tale Of Two Lines. IEEE Magazine Computer Graphics and Application, 2003, 23(6): 84-97
[57] J. F. Blinn. Line in Space. Part 1: The 4D Cross Product. IEEE Magazine Computer Graphics and Application, 2001, 23(2): 72-79
[58] D. Dori and W. Y. Liu. Vector-based segmentation of text connected to graphics in engineering drawings. Advances in Structural and Syntactical Pattern Recognition, P. Perner, P. Wang, A. Rosenfeld (eds.), Springer, 1996, pp. 322–331
[59] D. Dori, W. Y. Liu and M. Peleg. How to Win a Dashed Line Detection Contest. Kasturi R, Tombre K (eds), Graphics Recognition–Methods and Applications (Lecture Notes in Computer Science, 1072). Springer-Verlag, Berlin, 1996, pp 286–300
[60] G. Wolberg. Monotonic Cubic Spline Interpolation. 1999 International Proceeding on Computer Graphics (IPIG’99), pp: 188-195
[61] T. Lundahl, W. J. Ohley, S. M. Kay and R. Siffert. Fractional Brownian Motion: A Maximum Likelihood Estimator and Its Application to Image Texture. IEEE Transctions on Medical Imaging, 1986, 5(3): 152-161
[62] J. M. Keller, R. M. Crownover and R. Y. Chen. Characteristics of Natural Scenes Related to the Fractal Dimension. IEEE Transactions on Pattern Analysis and Machine Intelligent, 1987, 9(5):621-627
[63] C. M. Bishop. Pattern Recognition and Machine Learning. U. K. Springer-Verlag. 2006
[64] T. Hamamuri, T. Akagi and B. Irie. An Analytic Word Recognition Algorithm Using a Posteriori Probability. 2007 International Conference on Document Analysis Recogniton (ICDAR’07), pp: 669-673
[65] T. Hamamuri, T. Akagi and B. Irie. An A Posteriori Probability Calculation Method for AnalyticWord Recognition Applicable to Address Recognition. 2009 International Conference on Document Analysis Recogniton (ICDAR’09), vol. 1: 391-395
[66] J. Kautsky, J. Flusser and F. Sroubek. Implicit Invariants and Object Recognition. 2007 Biennial Conference of Australian Pattern Recogniton on Digital Image Computing Techniques and Applications (DICTA’07), vol.1: 462-469
[67] Y. Shinagawa. Homotopic Image Pseudo-Invariants for Openset Object Recognition and Image Retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligent, 2008, 30(11):1891- 1901
[68] S. Nilufar, N. Ray and H. Zhang. Optimum kernel function design from scale space features for object detection. 2009 International Conference on Image Processing (ICIP’09). Vol 1:861-864
[69] C. J. Liu. Gabor-based kernel PCA with fractional power polynomial models for face recognition. IEEE Transactions on Pattern Analysis and Machine Intelligent, 2004, 26(5):572-581
[70] M. Hu. Visual pattern recognition by moment invariants. IRE Trans. of Information Theory, 1962, 8: 179-187
[71] E. B. Elliot. Algebra of Quantics. 1913, Oxford Uni. Press, New York
[72] I. Balslev, K. D?ring, R. D. Eriksen. Weighted Central Moment in Pattern Recognition. Pattern Recogniton, 2000, 21(5): 381-384
[73] S. Maitra. Moment Invariants. 1979 International Proceeding of IEEE, 67(4):697-699
[74] C.–H. The, R. T. Chin. On Image Analysis by the Methods of Moments. IEEE Transactions on Pattern Analysis and Machine Intelligent, 1988, 10(4):496-513
[75] Y. S. ABU-MUSTAFA and D. Psaltis. Recognitive Aspect of Moment Invariants. IEEE Transactions on Pattern Analysis and Machine Intelligent, 1984, 6(6):698-706
[76] A. Wallin, O. Kubler. Complete sets of complex Zernike moment invariants and the role of the pseudo invariants. IEEE Transactions on Pattern Analysis and Machine Intelligent, 1995, 17(11):1106-1110
[77] J. Flusser. On the Independence of Rotation Moment Invariants. Pattern Recognition, 2000, 33(9):1405-1410
[78] J. Flusser, T. Suk. Rotation Moment Invariants for Recognition of Symmetric Objects. IEEE Transactions on Image Processing, 2006, 15(12):3784-3790
[79] M. Schlemmer, M. Heringer, et al.. Moment Invariants for the Analysis of 2-D Flow Fields. IEEE Transactions on Visualization and Computer Graphics, 2007, 13(6): 1743-1750
[80] B. Ng*, R. Abugharbieh, X. M. Huang, M. J. Mckeown. Spatial Characterization of fMRI Activation Maps Using Invariant 3-D Moment Descriptors. IEEE Transactions on Medical Imaging, 2009, 28(2): 261-268
[81] J. Flusser. Moment Invariants in Image Analysis. 2006 International Proceeding of World Academy of Science, Engineering and Technology (WASET’06), vol. 11: 196-201
[82] G. I. Salama and A. Y. Abbott. Moment Invariants and Quantization Effects. 1998 International Conference on Computer Vision and Pattern Recognition (CVPR’98), Vol. 1: 157-163
[83] Avanindra and S. Chaudhuri. Robust Detection of Skew in Document Images. IEEE Transa- ctions on Image Processing, 1997, 6(2):344-349
[84] X. Chen and T.–J. Cham. Discriminative Distance Measures for Image Matching. 2004 International Conference on Pattern Recognition (ICPR’04), Vol. 3: 691-695.
[85] M. Ben-Bassat and L. Zaidenberg. Contextual Template Matching: A Distance Measure for Patterns with Hierarchically Dependent Features. IEEE Transactions on Pattern Analysis and Machine Intelligent, 1984, 6(2):201-211
[86] W. J. Williams and R. B. Rutledge. A generalized distortion analysis of a cross-correlation radar. 1965 International Proceeding of IEEE, 53(2): 200-201.
[87] J. P. Lewis. Fast Template Matching. Vision Interface, 1995, 1:120-123
[88] M. M. Donnel. Box-filtering Techniques. Comput. Vis. Graph. Image Process, 1981, 17 : 65-70
[89] P. Viola and M. Jones. Robust Real-time Face Detection. International Journal of Computer Vision, 2004, 52(2): 137-154.
[90] L. G. Brown. A Survey of Image Registeration Techniques. ACM Transactions on Computer Survey, 1992, 24(4): 325-376
[91] R. J. Prokop, A. P. Reeves. A survey of moment-based techniques for unoccluded object representation and recognition. Graphical Models and Image Processing, 1992, 54: 438-460
[92] L. D. L. Stefano and S. Mattoccia. A sufficient condition based on the Cauchy-Schwarz inequality for efficient template-matching. 2003 International Conference on Image Process (ICIP’03), vol.1: 14-17
[93] L. D. L. Stefano and S. Mattoccia. Fast Template Matching Using Bounded Partial Correlation. Machine Vision Learning, 2003, 13(4): 213-221
[94] Y. S. Chen, Y. P. Hung and C. S. Fuh. Fast Algorithm for Nearest Neighbor Search Based on a Lower Bound Tree. 2001 International Conference on Computer Vision (ICCV’01), vol. 1:446-453
[95] S. D. Wei and S. H. Lai. Fast Template Matching Based on Normalized Cross Correlation With Adaptive Multilevel Winner Update. IEEE Transactions on Image Processing, 2008, 17(11): 2227-2235
[96] S. D. Wei and S. H. Lai. Efficient Normalized Cross Correlation Based on Adaptive Multilevel Successive Elimination. 2007 Asian Conference on Computer Vision (ACCV’07), Part 1: 638-646
[97] C. H. Benett, G. Brassard, C. Crépeau, and U. M. Maurer. Generalized privacy amplification. IEEE Transactions on Information Theory, 1995, 41: 1915–1923
[98] J. L. Carter and M. N.Wegman. Universal classes of hash functions. Journal of Computer System Science, 1979, 18:143–154
[99] [99] T. Cover. A proof of data compression theorem of Slepian and Wolf for ergodic sources. IEEE Transactions on Information Theory, 1975, IT-21:226–228
[100] T. Cover and J. Thomas, Elements of Information Theory. New York: Wiley, 1991
[101] I. Csiszár. Linear codes for sources and source networks: Error exponents, universal coding. IEEE Transactions on Information Theory, 1982, IT-28: 585–592
[102] I. Csiszár and J. K?rner. Towards a general theory of source networks. IEEE Tranactions on Information Theory, 1980, IT-26:155–165
[103] J. Song, Li, M. R. Lyu and S. Cai. Recognition of Merged Characters Based on Forepart Prediction, Necessity-Sufficiency Matching, and Character-Adaptive Masking. IEEE Transactions on System, Man, Cybernetics. Part B: Cybernetics, 2005, 35(1): 2-11
[104] R. G. Casey and E. Lecolinet. A survey of methods and strategies in character segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligent, 1996, 18(7): 690-706
[105] T. Bayer and U. Krebel.Cut classification for segmentation. 1993 International Conference on Document Analysis Recognition (ICDAR’93), vol. 1: 565-568
[106] T. Bayer, U. Krebel, and M. Hammelsbeck.Segmenting merged characters. 1992 International Conference on Pattern Recognition (ICPR’92), vol. 1: 346-349
[107] Z. K. Lu, Z. R. Chi and W. C. Siu. Extraction and optimization of B-spline PBD templates for recognition of connected handwritten digit strings. IEEE Transactions on Pattern Analysis and Machine Intelligent, 2002, 24(1):132-139
[108] X. B. Liu and Y. D. Jia. Character Stroke Extraction Based on B-spline Curve Matching by Constrained Alternating Optimization. 2007 International Conference on Document Analysis Recognition (ICDAR’07), vol. 1: 13-17
[109] U. Garain and B. B. Chaudhuri. Segmentation of Touching Characters in Printed Devnagari and Bangla Scripts Using Fuzzy Multifactorial Analysis. IEEE Transactions on System, Man, Cybernetics. Part C: Reviews and Application, 2002, 32(4): 449-459
[110] S. Marinai, M. Gori and G. Soda. Artificial Neural Networks for Document Analysis and Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligent, 2007, 27(1): 23-35
[111] A. Dawoud. Iterative Cross Section Sequence Graph for Handwritten Character Segmentation. IEEE Transactions on Image Processing, 2007, 16(8): 2150-2154
[112] C. L. Liu, M. Koga and H. Fujisawa.Lexicon-Driven Segmentation and Recognition of Handwritten Character Strings For Janpanese Address Reading. IEEE Transactions on Pattern Analysis and Machine Intelligent, 2002, 24(11): 1425-1437
[113] S. Madhvanah and V. Govindadaraju. The Role of Holistic Paradigms in Handwrittern Word Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligent, 2001, 23(2): 149-164
[114] G. Mori and J. Malik. Recognition Objects in Adervesarial Clutter: Breaking A Visual CAPTCHA. 2003 International Conference on Computer Vision and Pattern Recognition (CVPR’03), vol. 1: 18-20
[115] J. Rocha and T. Pavlidis. Character recognition without segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligent, 1995, 17(9): 903-909.
[116] T. Nartker. IRSI Annual Report. Ph. D Dissertation, University of Nevada, Las Vegas, NV, 1993
[117] H. J. Lee and J. S Wang. Design of a Mathematical Expression Understanding System. Pattern Recognition Letters, 1997,18(3): 289-298
[118] Y. Lu. On the segmentation of touching characters. 1993 International Conference on Document Analysis Recognition (ICDAR’93), pp. 440-443
[119] S. Liang, M. Ahmadi and M. Shridhar. Segmentation of touching character in the printed document recognition. 1993 International Conference on Document Analysis Recognition (ICDAR’93), 1993, pp. 569-572
[120] F. Yin and C.–L. Liu. A Variational Bayes Method for Handwritten Text Line Segmentation. 2009 International Conference on Document Analysis Recognition (ICDAR’09), vol 1: 440-443
[121] J. Wang and J. Jean. Segmentation of merged characters by Neutral Networks and shortest path. Pattern Recognition, 1994, 27(5): 649-658
[122] G. Congedo, G. Dimauro, S. Impedovo and G. Pirlo. Segmentation of Numeric Strings. 1995 International Conference on Document Analysis Recognition (ICDAR’95), vol. 1: 1038-1041
[123] C. A.B. Carlos, E. Roe and E. B. Lacerda. Segmentation of Overlapping Cursive Handwritten Digits. 2008 ACM Conference on Symbol Document Engineering, vol 1: 271-278
[124] S. Khan, Character Segmentation Heuristics of Check Amount Verification, Master Thesis, Massachusetts Institute of Technology. 1998
[125] J. Punnoose, An Improved Segmentation Module for Identification of Handwritten Numerals, Master Thesis, Massachusetts Institute of Technology. 1999
[126] S. Dey, Adding Feedback to Improve Segmentation and Recognition of Handwritten Numerals, Master Thesis, Massachusetts Institute of Technology. 1999
[127] R. Ma, J. Du, Y. H. Gu and Y. Y. Yan, An Improved Drop-fall Algorithm Based on Backgrou- nd Analysis for Handwritten Digits Segmentation. 2009 Global Congress on Intelligent Systems (CIS’09), vol. 1: 374-378
[128] S. J. Lent. B.B.C. test chart 57, a new grey-scale reflectance chart for colour cameras. Radio and Electronic Engineering, 1971, 41(5): 237-240.
[129] T. Taxt. Recognition of Handwritten Symbols. Pattern Recognition, 1987, 23(11): 1155-11.
[130]宋怀波,路长厚,王富春.基于小区域字符模板匹配的金属标牌字符识别.武汉理工大学学报, 2007, 29(6):125-127
[131]邓红耀,管庶安,宋秀丽.投影和模版匹配相结合分割车牌字符.计算机工程与设计,2008,29(6):1568-1570
[132]崔正,李壮.两种改进的模版匹配识别算法.计算工程与设计,2006,27(6):1083-1085
[133]陈兵旗,孙明. Visual C++实用图像处理专业教程.北京:清华大学出版社,2004.
[134]熊伟,谢剑薇,曾峦.检测骨架图形特征点的新方法.红外和激光工程, 2002, 31(4):301-304