在本論文中，我們提出方法來解決一些自動文件處理系統所遇到的問題。由於光學文字辨識（Optical Character Recognition, OCR）核心是由大量的字元樣本所訓練，而這些樣本通常是單一的黑白字元影像，而且沒有太嚴重的雜訊在其中。因此，本論文要解決的問題包括：文件影像的二值化、OCR核心的加速、手寫文字行的切割、受干擾字的辨識等。
文件通常由數個具有不同底色的區塊所組成，本論文首先提出一個區塊基礎的方法來做文件影像的二值化。我們先以一個兩層式區塊抽取方法，將文件影像細分成數個區塊，每個區塊內有個別的背景亮度。相連元件偵測法（connected-component detection）以及偏頗群長投影法（biased run-length projection）分別用在這兩層區塊抽取。對於每個區塊，我們分析像素的亮度分佈，來決定背景亮度所出現的範圍；利用此範圍，我們便可將像素分為前景與背景。對於不屬於所有區塊的其他像素，我們利用對整張影像求出的整體門檻值（global threshold），對其做二值化。我們所提方法的處理速度，較之其他區域調整方法（local adaptive methods）為快；而利用辨識準確性所評估的結果，顯示我們的方法較之其他整體門檻化方法（global thresholding methods）為佳。
本論文也描述了我們手寫中文辨識核心的建構方法。兩類統計特徵：通過筆畫數（crossing counts）及邊緣方向數（contour-direction counts），分別用在大分類（pre-classification）及細比對（detail matching）。為求在維持高辨識率的條件下提高比對速度，本系統採用了候選群選擇模組（candidate-cluster selection module）及改良的分支界定細比對模組（modified branch-and-bound detail-matching module），來加快整體的辨識速度。在PentiumII-233的個人電腦上，以工研院電通所的中文手寫資料庫CCL/HCCR測試的結果，平均辨識率約為89.95%，1秒鐘約可辨識8~10個字。
由於辨識核心只能辨認抽取出的單一字元，本論文提出一個以辨識為基礎的字元切割方法。首先利用機率式維特比演算法（probabilistic Viterbi algorithm）求出文字行中所有可能的切割途徑，再利用中文字的特性將一些不合理或多餘的途徑去除，剩下的候選途徑用來建構一個切割圖（segmentation graph）。圖中的節點代表一個候選途徑，並用邊線連接兩個距離夠近的節點，每條邊線的成本利用辨識距離、字元方正度、和字元內部空格來決定。最後，最佳的切割路徑就訂在從切割圖中找出之最短路線（shortest path）上的每個節點。
在表格文件的處理過程，常常會發現有些填入資料寫在格線上，即使可將這些受干擾字（interfered characters）抽取出來，因有格線橫亙其中，破壞該文字的特徵，往往導致辨認錯誤。本論文利用干擾線去除（interfering-line removal）及特徵權重調整（feature weight adjustment）的方法來辨認此類受干擾字。我們先利用霍夫轉換（Hough transform）及投影外廓（projection-profiles），找出該擾線的位置；再利用黑群的偵測與分類，來區分干擾點與字元點，將所有干擾點去除，就可得到乾淨字元（clean characters）。為辨認效果不甚理想的乾淨字元，我們修改辨識核心，將干擾線通過的區域所抽出的特徵，在比對過程的權重降低，以減少干擾線對該字元辨識的影響，達到被干擾字的辨識效果，就如同這些字未受干擾一樣好。

In this thesis, we propose methods for solving several problems in an automatic document processing system. Since OCR engines are usually trained by character samples which are binary images without obvious interference, those problems explored in this thesis include document image binarization, the speedup of OCR engine, handwritten character segmentation, and interfered character recognition.
A document generally consists of several blocks with different background intensity values. This thesis initially proposes a block-based method for binarizing these document images. We first apply a two-layer block extraction method to separate documents into several rectangular blocks whose background intensity values are individual. Connected-component detection and biased run-length projection are used in the first and the second layer, respectively. For each block, we analyze the distribution of intensity to determine background intensity values. The union of background intensity values is then adopted to binarize this block image. For those pixels outside all extracted blocks, we binarize them according to the global threshold value calculated from the entire document image. The speed of this proposed approach is greater than that of any local adaptive method. According to the evaluation of recognition accuracy, the binarization results of this method are still more satisfactory than that of any global thresholding method.
This thesis also describes the implementation of our OCR engine for handwritten Chinese characters. Two statistical features, crossing counts and contour-direction counts, are used in pre-classification and detail-matching module respectively. In order to reduce the processing time without losing recognition accuracy, this system applied a candidate-cluster selection module and a modified branch-and-bound detail-matching module to speed up the OCR engine. Efficiency experiments are performed on 5401 100 Chinese characters selected from the database CCL/HCCR. The average recognition rate of this OCR engine is 89.95% and about 8~10 characters per second are recognized.
Since OCR engines only recognize single characters extracted from text-lines, this thesis proposes a recognition-based character segmentation method. A probabilistic Viterbi algorithm is first used to detect possible nonlinear segmentation routes for a given text-line. Several properties of Chinese characters are then considered to remove irrational or redundant segmentation routes. The remaining routes, called candidate segmentation routes, are used to construct a segment graph. Each node of the graph represents a candidate route and an edge connects two nodes whose distance is less than a threshold. The cost in each edge is a function of character recognition distances, squareness of characters, and internal gaps in characters. Finally, we locate optimal segmentation routes on the nodes of the shortest path identified from the segmentation graph.
In form documents, several filled-in data are overwritten onto form lines. These interfered characters are always mis-recognized even though they can be extracted. This thesis finally presents a method for recognizing these interfered characters by removing interfering-lines and adjusting feature weights. We first detect interfering-lines by the Hough transform and projection-profiles. Black-run detection and classification are then applied to distinguish interfering pixels and character pixels. In order to recognize several dissatisfactory clean characters generated by eliminating interfering pixels, the OCR engine is refined by adjusting the weights of features extracted from areas passed by interfering-lines. By reducing the influence of interfering-lines, the recognition accuracy of interfered characters is improved closely to that of characters without interference.

封面
ABSTRACT (IN CHINESE)
ABSTRACT (IN ENGLISH)
ACKNOWLEDGEMENTS
TABLE OF CONTENTS
LIST OF FIGURES
LIST OF TABLES
CHAPTER 1. INTRODUCTION
1.1 Motivation
1.2 System Architecture
1.3 Thesis Organization
CHAPTER 2. SURVER OF RELATED RESEARCHES
2.1 Document Image Binarization
2.2 Character Recognition and Its Speedup
2.3 Character Segmentation
2.4 Interfered Character Recovery
CHAPTER 3. DOCUMENT IMAGE BINARIZATION
3.1 Motivation
3.2 Image Transformation, Reduction and Smearing
3.3 Two-layer Block Extraction by Connected-component Detection and Biased Runlength Projection
3.4 Background Intensity Values Determaination and Background Pixels Removing
3.5 Experimental Results and Analysis
3.6 Discussion
CHAPTER 4. OCR ENGINE IMPLEMENTAION AND SPEEDUP
4.1 Motivation
4.2 Extraction of Statistical Features
4.3 Implementation of Our OCR Engine for Chinese Characters
4.4 Experimental Results and Analysis
4.5 Discussion
CHAPTER 5. RECOGNITION-BASED CHINESE CHARACTER SEGMENTATION
5.1 Motivation
5.2 Preparation of Probabilistic Viterbi Algorithm
5.3 Derivation of Non-linear Segmentation Routes
5.4 Optimal Segmentation Routes Identification
5.5 Experimental Results and Analysis
5.6 Discussion
CHAPTER 6. INTERFERED CHINESE CHARACTER RECOGNITION
6.1 Motivation
6.2 Detection of Interfering-lines in Arbitrary Directions
6.3 Separating Interfering-lines from Interfered Characters Images
6.4 Refinement of Character Recognition Engine
6.5 Experimental Results and Analysis
6.6 Discussion
CHAPTER 7. CONCLUSIONS
7.1 Conclusions
7.2 Future Researches
BIBLIOGRAPHY
VITA
PUBLICATION LIST OF YI-HONG TSENG

1. F. H. Cheng and W. H. Hsu, "Research on Chinese OCR in Taiwan," International Journal of Pattern Recognition and Artificial Intelligence, vol. 5, nos. 1? pp. 139-164, June 1991.
2. V. K. Govindan and A. P. Shivaprasad, "Chinese Recognition - a Review," Pattern Recognition, vol. 23, no. 7, pp. 671-683, 1990.
3. C. C. Tappert, C. Y. Suen, and T. W. Wakahara, "The State of Art in On-line Handwriting Recognition," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. PAMI-12, no. 8, pp. 787-808, Aug. 1990.
4. G. Nagy, "Chinese Character Recognition: a Twenty-five-year Retrospective," Proc. 9th Intl Conf. Pattern Recognition, pp. 163-167, 1988.
5. T. Y. Young and K. S. Fu, Handbook Pattern Recognition and Image Processing, Academic Press, New York, 1986.
6. S. Mori, K. Yamamoto, and M. Yasuda, "Research on Machine Recognition of Handcrafted Characters," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. PAMI-6, no. 4, pp. 386-405, July 1984.
7. N. C. Wang, A Handwritten Chinese Text Recognition System with a Contextual Postprocessing Module, Master thesis, Institute of Computer Science and Information Engineering, National Chiao Tung University, Hsinchu, Taiwan, 1991.
8. H. J. Lee and C. H. C. Chien, "A Markov Language Model in Handwritten Chinese Text Recognition," Proc. 2nd Int. Conf. Document Analysis and Recognition, pp. 72-75, 1993.
9. C. Y. Suen, "N-gram Statistics for Natureal Language Understanding and Text Processing," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. PAMI-1, no. 2, pp. 164-172, July 1979.
10. C. H. Tung, A Study on Handwritten Chinese Text Recognition, Ph.D. dissertation, Institute of Computer Science and Information Engineering, National Chiao Tung University, Hsinchu, Taiwan, 1994.
11. Friedrich M. Whal, Kwan Y. Wong, and Richard G. Casey, "Block Segmentation and Text Extraction in Mixed Text/Image Documents," Computer Vision, Graphics and Image Processing, vol. 20, pp. 375-390, 1982.
12. K. Y. Wong, R.G. Casey and F. M. Wahl, "Document Analysis System," IBM J. Research and Development, vol. 26, no. 6, pp. 647-656, 1982.
13. D. K. Panjwani and G. Healey, "Markov Random Field Models for Unsupervised Segmentation of Textured Color Images," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. PAMI-17, no. 10, pp. 939-954, 1995.
14. M. Okamoto and M. Takahashi, "A Hybrid Page Segmentation Method," Proc. 2nd Int. Conf. Document Analysis and Recognition, pp. 743-748, 1993.
15. Y. Hirayama, "A Block Segmentation Method for Document Images with Complicated Column Structures," Proc. 2nd Int. Conf. Document Analysis and Recognition, pp. 91-94, 1993.
16. U. Pal, and B. B. Chaudhuri, "An improved document skew angle estimation technique," Pattern Recognition Letters, vol: 17, no. 8, pp. 899-904, 1996.
17. Y. Bin and A. K. Jain "A robust and fast skew detection algorithm for generic documents," Pattern Recognition, vol, 29, no. 10, pp. 1599-1629, 1996.
18. H. F. Jiang, C. C. Han, and K. C. Fan, "A fast approach to the detection and correction of skew documents," Pattern Recognition Letters, vol, 18, no. 7, pp. 675-686, 1997.
19. B. Gatos, N. Papamarkos, and C. Chamzas, "Skew detection and text line position determination in digitized documents," Pattern Recognition, vol. 30, no. 9, pp. 1505-1519, 1997.
20. K. S. Fu, Syntactic Pattern Recognition and Applications, Prentice-Hall, Englewood Cliffs, New Jersey, 1982.
21. G. Y. Tang and T. S. Huang, "A Syntactic-semantic Approach to Image Understanding and Creation," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. PAMI-1, no. 2, pp. 135-144, April 1979.
22. K. S. Fu, "A Step Towards Unification of Syntacic and Statistical Pattern Recognition," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. PAMI-5, no. 2, pp. 200-205, March 1986.
23. P. R. Devijver and J. Kittler, Pattern Recognition: A Statistical Approach, Prentice-Hall, Englewood Cliffs, New Jersey, 1982.
24. T. Y. Tu and Y. L. Ma, "Character Recognition by Stochastic Sectionalgram Approach," Pattern Recognition, vol. 21, no. 5, pp. 593-601, 1989.
25. C. H. Leung, Y. S. Cheung, and Y. L. Wong, "Knowledge-based Stroke-matching method for Chinese Character Recognition," IEEE Trans. on System, Man, and Cybernetics, vol. SMC-17, no. 6, pp. 993-999, 1987.
26. H. J. Lee and B. Chen, "Recognition of Handwritten Chinese Characters via Short Line Segments," Pattern Recognition, vol. 25, no. 5, pp. 543-552, 1992.
27. F. H. Cheng, W. H. Hsu, and C. A. Chen, "Fuzzy approach to Solve the Recognition Problem of Handwritten Chinese Characters," Pattern Recognition, vol. 23, no. 11, pp. 133-141, 1989.
28. C. W. Liao and J. S. Huang, "A Transformation Invariant Matching Algorithm for Handwritten Chinese Character Recognition," Pattern Recognition, vol. 23, no. 11, pp. 1167-1188, 1990.
29. H. Yamada, K. Yamamoto, and T. Saito, "A Nonlinear Normalization Method for Handprinted Kanji Character Recognition - Line Density Equalization," Pattern Recognition, vol. 23, no. 9, pp. 1023-1029, 1990.
30. J. Tsukumo and H. Tanaka, "Classification of Handprinted Chinese Characters Using Nonlinear Normalization and Correction Methods," Proc. 9th Intern. Conf. on Pattern Recognition, pp. 168-171, 1988.
31. T. Taxt, J. B. Olafsdottir, and M. Dehlen, "Recognition of Handwritten Symbols," Pattern Rectonition, vol. 23, no. 11, pp. 1153-1166, 1990.
32. P. P. Wang and R. C. Shian, "Machine Recognition of Printed Chinese Characters via Transformation Algorithm," Pattern Recognition, vol. 5, pp. 303-321, 1973.
33. J. S. Huang and M. L. Chung, "Separating Similar Complex Chinese Characters by Walsh Transform," Pattern Recognition, vol. 20, pp. 425-428, 1987.
34. S. W. Lee et al. "Multiresolution recognition of unconstrained handwritten numerals with wavelet transform and multilayer cluster neural network," Pattern Recognition, vol. 29, no. 12, pp. 1953-1961, 1996.
35. P. Wunsch and A.F. Laine, "Wavelet descriptors for multiresolution recognition of handprinted characters," Pattern Recognition, vol. 28, no. 8, pp. 1237-1249, 1995.
36. G. L. Cash and M. Hatamian, "Optical Character Recognition by the Method of Moments," Computer Vision, Graphics, and Image Processing, vol. 34, pp. 291-310, 1987.
37. S. S. El-Dabi, R. Ramsis, and A. Kamel, "Arabic Character Recognition System: A Statistical Approach for Recognition Cursive Typewritten Text," Pattern Recognition, vol. 23, no. 5, pp. 485-495, 1990.
38. P. K. Sahoo, S.Soltani, and A. K. C. Wong, "A Survey of Thresholding Techniques," Computer Vision, Graphics, and Image Processing, vol. 41, pp. 233-260, 1988.
39. S. U. Lee and S. Y. Chung, "A Comparative Performance Study of Several Global Thresholding Techniques for Segmentation," Computer Vision, Graphics, and Image Processing, vol. 52, pp. 171-190, 1990.
40. N. Otsu, "A Thresholding Selection Method from Gray-Scale Histogram," IEEE Trans. Systems, Men, and Cybernetics, vol. 9, pp. 62-66, 1979.
41. W. H. Tsai, "Moment-Preserving Thresholding: A New Approach," Computer Vision, Graphics, and Image Processing, vol. 29, pp. 377-393, 1985.
42. G. Johannsen and J. Bille, "A Threshold Selection Method Using Information Measures," Proc. sixth Intl Conf. Pattern Recognition, pp. 140-143, Munich, West Germany, 1982.
43. J. N. Kapur, P. K. Sahoo, and A. K. C. Wong, "A New Method for Gray-Level Picture Thresholding Using the Entropy of the Histogram," Computer Vision, Graphics, and Image Processing, vol. 29, pp. 273-285, 1985.
44. J. Kittler and J. Illingworth, "On Threshold Selection Using Clustering Criteria," IEEE Trans. Systems, Man, and Cybernetics, vol. 15, pp. 652-655, 1985.
45. j. D. Trier and A. K. Jain, "Goal-Directed Evaluation of Binarization Method," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 17, pp. 1191-1201, 1995.
46. W. Niblack, An Introduction to Digital Image Processing, pp. 115-116, Englewood Cliffs, N.J.: Prentice Hall, 1986.
47. J. Bernsen, "Dynamic Thresholding of Gray-Level Images," Proc. 8th Intl Conf. Pattern Recognition, pp. 1,251-1,255, Paris, 1986.
48. L. Eikvil, T. Taxt, and K. Moen, "A Fast Adaptive Method for Binarization of Document Images," Proc. 1st Intl Document Analysis and Recognition, pp. 435-443, Saint-Malo, France, 1991.
49. J. M. White and G. D. Rohrer, "Image Thresholding for Character Image Extraction and Other Applications Requiring Character Image Extraction," IBM J. Research and Development, vol. 27, pp. 400-411, 1983.
50. Y. Lu, "Machine Printed Character Segmentation - an Overview", Pattern Recognition, vol. 28, no. 1, pp. 67-80, 1996.
51. Y. Lu and M. Shridhar, "Character Segmentation in Handwritten Words - an Overview", Pattern Recognition, vol. 29, no. 1, pp. 77-96, 1996.
52. Richard G. Casey and Eric Lecolinet, "A Survey of Methods and Strategies in Character Segmentation", IEEE Trans. Pattern Anal. Mach. Intell., vol. 18, no. 7, pp. 690-706, 1996.
53. J. Wang and J. Jean, "Segmentation of Merged Characters by Neural Networks and Shortest Path," Pattern Recognition, vol. 27, No. 5, pp. 649-658, 1994.
54. S. W. Lee, D. J. Lee and H. S. Park, "A New Methodology for Gray-Scale Character Segmentation and Recognition", IEEE Trans. Pattern Anal. Mach. Intell., vol. 18, no. 10, pp. 1045-1050, 1996.
55. R. G. Casey and D. R. Ferguson, "Intelligent Forms Processing," IBM Systems Journal, vol. 29, no. 3, pp. 435-450, 1990.
56. R. G. Casey and D. R. Ferguson, K. Mohiuddin and E. Walach, "Intelligent Forms Processing," Machine Vision and Applications, vol. 5, pp. 143-155, 1993.
57. J. L. Chen and H. J. Lee, "An Efficient Algorithm for Form Structure Extraction Using Strip Projection," Pattern Recognition, vol. 31, no. 9, pp. 1353-1368, 1998.
58. C. T. Ho and L. H. Chen, "A High-speed Algorithm for Line Detection," Pattern Recognition Letters, vol. 17, pp. 467-473, 1996.
59. X. N. Chen and D. C. Tseng, "Form-structure Extraction for Table-form Recognition," Proc. of 8th IPPR Conf. on Computer Vision, Graphics and Image Processing, Taiwan, pp. 496-503, 1995.
60. V. Govindaraju and S. N. Srihari, "Separating Handwritten Text from Interfering Strokes," From Pixels to Features III: Frontiers in Handwriting Recognition, Elsevier Science Publisher, pp. 17-28, 1992.
61. S. Liang, M. Ahmadi, M. Shridhar, "Segmentation of Interference Marks Using Morphological Approach," Proc. Third Int. Conf. Document Analysis and Recognition, pp. 1042-1046, Montreal, Canada, 1995.
62. Bin Yu and Anil K. Jain, "A Generic System for Form Dropout," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 18, no. 11, pp. 1127-1134, 1996.
63. W. Huang, G. Rong and Z. Bian, "Strokes Removing from Static Handwriting," Proc. Third Int. Conf. Document Analysis and Recognition, pp. 861-864, Montreal, Canada, 1995.
64. J. Y. Yoo et. al. "Line Removal and Restoration of Handwritten Characters on the Form Documents," Proc. Fourth Int. Conf. Document Analysis and Recognition, pp. 128-131, Ulm, Germany, 1997.
65. M. D. Garris, "Method and evaluation of character stroke preservation on handprint recognition," NIST Internal Report 5687, July 1995.
66. Q. Zhang, Q. R. Wang and R. Boyle, "A Clustering Algorithm for Data-Sets with a Large Number of Classes," Pattern Recognition, vol. 24, no. 4, pp. 331-340, 1991.
67. C. H. Tung, H. J. Lee, and J. Y. Tsai, "Multi-stage Pre-candidate Selection in Handwritten Chinese Character Recognition Systems," Pattern Recognition, vol. 27, no. 8, pp. 1093-1102, 1994.
68. R. G. Casey and G. Nagy, "Decision Tree Design Using a Probabilistic Model," IEEE Trans. Pattern Analysis and Machine Intelligence, pp. 334-341, 1984.
69. Y. X. Gu, Q. R. Wang, and C. Y. Suen, "Application of Multilayer Decision Tree in Computer Recognition of Chinese Characters," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. PAMI-5, pp. 83-89, 1983.
70. Q. R. Wang amd C. Y. Suen, "Analysis and Design of a Decision Tree Based on Entropy Reduction and Its Application to Large Character Set Recognition," IEEE Trans. on Pattern Analysis and Machine Intelligence, pp. 253-260, 1984.
71. Kamgar-Parsi B. and L. N. Kanal, "An Improved Branch and Bound Algorithm for computing k-neighbours," Pattern Recognition Letters, vol. 3, pp. 7-12, 1985.
72. H. Niemann, R. Goppert, "An Efficient Branch-and-Bound Nearest Neighbour Classifier," Pattern Recognition Letters, vol. 7 pp. 67-72, 1988.
73. S. Shuji, M. Michihiko and I. Katsuo, "A Fast Algorithm for the Minimum Distance Classifier and Its Application to Kanji Character Recognition," Proc. 3rd ICDAR, pp. 283-286, 1995.
74. K. C. Fan, "Document analysis and lossless reproduction (II)", Technical Report, National Science Council, R.O.C., 1995, 7.
75. I. C. Jou, Y. G. Chau, R. H. Ju and J. Y. Lee, "Modeling for Chinese character patterns," Proc. CVGIP, Taiwan, R.O.C., pp. 131-134, 1994.
76. H. H. Tseng and W. H. Tsai, "Chinese character font recognition using Fourier spectrum features and back-propagation neural network," Proc. CVGIP, Taiwan, R.O.C., pp. 206-213, 1996.
77. J. Tsukumo and K. Asai, "Machine Printed Chinese and Japanese Characters Recognition Method and Experiments for Reading Japanese pocket books," IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, pp. 162-167. June 1986.
78. L. Tu et al., "Recognition of Handprinted Chinese Characters by Feature matching," Int. Conf. on Computer Processing of Chinese and Oriental Languages, pp. 154-157, 1991.
79. C. H. Tung, H. J. Lee, "Increasing Character Recognition Accuracy by Detection and Correction of Erroneously-identified Characters," Pattern Recognition, vol. 27, no. 9, pp. 1259-1266, 1994.
80. R. Oka, "Handwritten Chinese-Japanese Characters Recognition by Cellular Feature," Proc. 6th Intern. Conf. on Pattern Recognition, pp. 783-785, IEEE, October 1991.
81. S. H. Kim and J. I. Doh, "Off-line Recognition of Korean Scripts Using Distance matching and neural network classifiers," Proc. of the Third ICDAR, pp. 34-37, August, 1995.
82. C. C. Kuo, "Evaluation and Speeding Up of Statistical Chinese Character Recognition," Master Thesis, Department of Computer Science and Information Engineering, National Chiao Tung University, Taiwan, R.O.C., 1996.
83. K. Fukunaga, Introduction to Statistical Pattern Recognition, Academic Press, 1990.
84. G. J. Klir and B. Yuan, "Fuzzy sets and fuzzy logic," Prentice Hall Inc., 1995.
85. G. D. Formey, Jr., "The Viterbi Algorithm", IEEE Proc., vol. 61, pp. 268-278, 1973.
86. R. C. Gonzalez and R. E. Woods, Digital Image Processing, Addison-Wesley, 1992.
87. T. F. Li and S. S. Yu, "Handprinted Chinese Character Recognition Using the Probability Distribution Feature," Int. Jour. of Pattern Recognition and Artificial Intelligence, vol. 8, no. 5, pp. 1241-1258, 1994.
88. E. Horowitz and S. Sahni, Fundamentals of Computer Algorithms, Computer Science Press, Inc., 1978.
89. L. R. Rabiner and B. H. Juang, "An introduction to hidden Markov models," IEEE ASSP Mag., pp. 4-16, Jan. 1986.
90. A. Kundu, Y. He and P. Bahl, "Recognition of handwritten word: First and second order hidden Markov model based approach", Pattern Recognition. vol. 22, pp. 283-297, 1989.
91. Y. H. Tseng, C. C. Kuo and H. J. Lee, "Speeding-up Character Recognition and Applying the Results to Automatic Document Reading," Pattern Recognition, vol. 31, no. 11, pp. 1601-1612, 1998.