臺灣博碩士論文加值系統

在光學字元辨識實際工業應用中，外在的光源、字元尺寸、字型和位移旋轉都是影響辨識結果的因素，因此本研究探討相關係數法﹙correlation coefficient﹚、樣板比對法﹙template matching﹚、環形投影法﹙ring projection﹚、細線化法﹙thinning﹚和本研究所提出的四分法（quartering）五種辨識方法，利用計算字元的相似度係數，以進行各種影響因子的分析，並比較五種方法受到不同因素影響後的辨識能力。
本研究主要針對IC字元辨識，藉由探討目前多種光學字元辨識技術，分析各種辨識方法受到環境因素影響的程度，並且根據各種辨識方法的特性，進而提出一個結合現有辨識技術，建立階段式的辨識步驟，以解決只使用單一種字元辨識方法所產生的字元誤判情況。利用字元間的相似度係數信賴區間（confidence interval）箱形圖（box plots）的方法，將字元箱形圖有重疊者之字元分為同一群組，針對每一個階段中之每個群組內的字元再選用相對適合的辨識方法以建立子分群，使得字元間有明顯的差異性，重複此分群步驟直至每一字元成為單獨一個字群。進行辨識時，是依據已經建立好之分群模式，在每一階段中之每個群組內使用選定的辨識方法進行辨識。使用本研究所提之多階混合式辨識策略，可以提升字元辨識成功率，避免誤判字元的發生。

In this research we aim at the optical character recognition (OCR) techniques for IC marks in electronic industry. We analyze four existing OCR techniques including correlation coefficient method, template matching method, ring projection method, and thinning method, and a new quartering method proposed in this research. These five OCR techniques evaluated are computationally simple and easily implemented. The effects of lighting, font, scale, translation and rotation on the similarity measures are evaluated for each OCR method.
The characters of IC marks include 26 upper-case alphabets and numerical 10 digits. Since none of the five OCR methods aforementioned can reliably recognition all 36 characters, this research employs a multi-stage, hybrid-method strategy to maximize the recognition rate. In the training phase, the correlation coefficient method is initially used to group similar characters into a subgroup. Characters in the subgroup are further partitioned into smaller group using one of the remaining methods. The partition procedure is recursively repeated until there is only one character in each subgroup. The selected OCR method for each character group in each stage is then used for character classification in the recognition phase. Experiments on various IC marks have shown that the proposed algorithm can achieve 100% recognition rate.

中文摘要……………………………………………………………………………... Ⅰ
英文摘要……………………………………………………………………………... Ⅱ
誌謝…………………………………………………………………………………... Ⅲ
目錄…………………………………………………………………………………... Ⅳ
表目錄………………………………………………………………………………... Ⅵ
圖目錄………………………………………………………………………………... Ⅶ
第一章 緒論…………………………………………………………………………. 1
1.1 研究目的與範疇………………………………………………………………… 1
1.2 研究方法簡介…………………………………………………………………… 2
第二章 文獻回顧……………………………………………………………………. 5
2.1 手寫字體辨識…………………………………………………………………… 5
2.2 印刷體字形辨識 8
第三章 研究方法……………………………………………………………………. 10
3.1 研究方法敘述…………………………………………………………………… 10
3.1.1 相關係數法………………………………………………………………... 10
3.1.2 樣板比對法………………………………………………………………... 11
3.1.3 環形投影法………………………………………………………………... 13
3.1.4 細線化法…………………………………………………………………... 18
3.1.5 四分法……………………………………………………………………... 19
3.2 字元位置之搜尋與字元尺寸調整……………………………………………… 22
3.3 旋轉角度的搜尋法……………………………………………………………… 29
3.4 多階混合式之字元辨識策略…………………………………………………… 33
第四章 實驗結果與分析……………………………………………………………. 39
4.1 硬體設定系統架構與實驗環境………………………………………………… 41
4.2 各種影響因素與辨識方法的比較……………………………………………… 43
4.2.1 光源影響因素辨識實驗結果……………………………………………... 43
4.2.2 尺寸因素影響因素辨識結果……………………………………………... 45
4.2.3 不同字型影響因素辨識結果……………………………………………... 47
4.2.4 旋轉位移影響因素辨識結果……………………………………………... 51
4.2.5 各辨識方法分析…………………………………………………………... 53
4.3 字元分群與辨識結果…………………………………………………………… 55
4.3.1 分群模式一︰建立第一組樣本之分群模式與第一組樣本字元之測試... 59
4.3.2 分群模式二︰建立第二組樣本之分群模式與第二組樣本字元之測試... 76
4.3.3 分群模式三︰分群模式一之子分群模式與第二組樣本字元之測試…... 83
4.3.4 分群模式四︰以第三組樣本建立分群模式四
與測試第三組IC樣本字元………………………………………………. 87
4.4 實驗結果之結論……………………………………………………………….. 109
第五章 結論與建議…………………………………………………………………111
參考文獻……………………………………………………………………………..113
附錄 A 五種辨識方法對於各影響因素之平均相似度值和平均標準差………... 116
附錄 B 各分群模式之第二階段或第三階段各種辨識方法之信賴區間相形圖... 129
附錄 C 第一階段分別使用四種辨識方法分群結果……………………………... 139
附錄 D 五種字元辨識方法程式介紹 ……………………………………………. 144

Borgefors, G., 1988, "Hierarchical chamfer matching: A parametric edge matching algorithm", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 10, No. 6, pp. 849-865.
Cash, G. L., and Hatamian, M., 1987, "Optical character recognition by rhe method of moment", CVGIP, Vol. 39, pp. 291-310.
Chaudhuri, B. B. and Pal, U., 1998, "A complete printed Bangla OCR system", Pattern Recognition, Vol. 31, No. 5, pp. 531-549.
Cordella, L. P., Stefano, C. D., and Vento, M., 1995, "A neural network classifier for OCR using structural descriptions", Machine Vision and Applications, Vol. 8, No. 5, pp. 336-342.
Hong, C., Loudon, G., Wu, Y., and Zitserman, R., 1998, "Segmentation and recognition of continuous handwriting Chinese text", International Journal of Pattern Recognition and Artificial Intelligence, Vol. 12, No. 2, pp. 223-232.
Horn, B. K. P., 1990, Robot Vision, MIT Press Edition Horuh, New York.
Jain, R., Kasturi, R., and Schunck, B. G., 1995, Machine Vision, Mcgraw-hill International Editions, Singapore.
Kim, S.-Y. and Lee, S.-W., 1998, "Gray-scale nonlinear shape normalization method for handwritten oriental character recognition", International Journal of Pattern Recognition and Artificial Intelligence, Vol. 12, No. 1, pp. 81-95.
Kimura, F., Wakabayashi, T., Tsuruoka, S, and Miyake, Y., 1997, "Improvement of handwritten Japanese character recognition using weighted direction code histogram", Pattern Recognition, Vol. 30, No. 8, pp. 1329-1337.
Kneer, S., Augustin, E., Baret O., and Price D., 1998, "Hidden Markov model based word recognition and its application to legal amount reading on French checks", Computer Vision and Image Understanding, Vol. 70, No. 3, pp. 404-419.
Kwon, J.-O., Sin, B., and Kim, J. H., 1997, "Recognition of on-line cursive Korean characters combining statistical and structural methods", Pattern Recognition, Vol. 30, No. 8, pp. 1255-1263.
Lai, M. T. Y. and Suen, C. Y., 1981, "Automatic recognition of characters by Fourier descriptors and boundary encoding", Pattern Recognition, Vol. 14, No. 1, pp. 383-393.
Liu, H.-C. and Srinath, M. D., 1990, "Partial shape classification using contour matching in distance transformation", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 12, No. 11, pp. 1072-1079.
Lee, S.-W. and Kim, Y. J., 1995, "Direct extraction of topographic feature for gray scale character recognition", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 17, No. 7, pp. 724-729.
Lee, S.-W., Lee, D.-J., and Park, H.-S., 1996, "A new methodology for gray-scale character segmentation and recognition", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 18, No. 10, pp. 1045-1050.
Lippman, R. P., 1987, "An introduction to computing with neural net", IEEE ASSP Magazine, Vol. 4, pp. 4-22.
Mori, S., Suen, C. Y., and Yamamoto, K., 1992, "Historical review of OCR research and development", Proceedings of The IEEE, Vol. 80, No. 7, pp. 1029-1057.
Nagy, G., 1982, "Optical character recognition-Theory and practice", Handbook of Statistics, P. R. Krishnaiah and L. N. Kanal, Eds., Vol. 2, Amsterdam: North-Holland, pp. 621-649.
Park, H.-S., Song, H.-H., and Lee, S.-W., 1998, "A self-organizing hierarchical classifier for multi-lingual large-set oriental character recognition", International Journal of Pattern Recognition and Artificial Intelligence, Vol. 12, No. 2, pp. 191-208.
Parker, J. R., 1997, Algorithms for image processing and computer vision, John Wiley & Sons, Canada.
Romero, R. D., Touretzky, D. S., and Thibadeau, R. H., 1997, "Optical Chinese character recognition using probabilistic neural networks", Pattern Recognition, Vol. 30, No. 8, pp. 1279-1292.
Sawaki, M. and Hagita, N., 1998, "Text-line extraction and character recognition of document headlines with graphical designs using complementary similarity measure", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 20, No. 10, pp. 1103-1109.
Seo K., Kim J., Yoom, J., and Chung, K., 1998,"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, Vol. 12, No. 2, pp. 251-261.
Sin, B.-K. and Kim, J. H., 1998, "Network-based approach to Korean handwriting analysis", International Journal of Pattern Recognition and Artificial Intelligence, Vol. 12, No. 2, pp. 233-249.
Tang, Y. Y., Cheng, H. D., and Suen, C. Y., 1991, "Transformation-ring- projection algorithm and its VLSI implementation", International Journal of Pattern Recognition and Artificial Intelligence, Vol. 5, pp. 25-56.
Tseng, Y.-H., Kuo, C.-C., and Lee, H.-J., 1998, "Typeface identification for printed Chinese character", International Journal of Pattern Recognition and Artificial Intelligence, Vol. 12, No. 2, pp. 173-190.
Yasuda, M., Yamamoto, K., and Yamada, H., 1997, "Effect of the perturbed correlation method for optical character recognition", Pattern Recognition, Vol. 30, No. 8, pp. 1315-1320.
Yuen, P. C., Frng, G. C., and Tang, Y. Y., 1998, "Printed Chinese character similarity measurement using ring projection and distance transform", International Journal of Pattern Recognition and Artificial Intelligence, Vol. 12, No. 2, pp. 209-221.
Zhang, T. Y. and Suen, C. Y., 1984, "A fast parallel algorithm for thining digital patterns," Communications of the ACM, Vol. 27, No. 3, pp. 236-239.
Zramdini, A. and Ingold, R., 1998, "Optical font recognition using typographical features", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 20, No. 8, pp. 877-882.