臺灣博碩士論文加值系統

一般的文件處理系統包含兩個部份:文字切割與文字辨識。在本論文提出了一個有效率之文字切割系統。
這個系統含有兩個模組: 文件分析與文字切割。在文件分析部份，我們先進行縮圖與抽取連通元件(Connected-Components) ，接著將連通元件分為圖形或文字元件。在抽取出文件上之文字元件後，我們將文字元件合併成文字區塊，並檢查圖元件內是否有文字元件。若有，則抽取出來並合併至文字區塊中。最後，對所有的文字區塊切割出一行行之文字。
當區塊的文字行被切開後，針對每個文字區塊，我們先檢查區塊中是否有首字放大情形。若有，則抽取之。最後，我們針對每個文字行執行文字切割以切出中文﹑英文與數字。
在我們的實驗中，文字切割的正確率約98.9% ，對於一份內含1158個的文件所需時間為5秒。由此證明了我們系統的效率。

A general document processing system usually includes two major modules: character segmentation module and character recognition module. In this thesis, we present an automatic system to segment characters efficiently. Our character segmentation system contains two modules: document layout analysis and character segmentation. In the document layout analysis module, we first perform image reduction and connected-components extraction. In the component classification procedure, the connected-components be classified as image components or text components. In the block segmentation procedure, we merge all text components into text blocks . The extraction of text components from image components can group all text components into text blocks. Finally, we perform text line segmentation to segment all text lines in the text blocks.
After all text lines have been segmented, we found and extracted the initial caps if they exist in the text blocks. Finally we segment the Chinese characters, English letters and numerals in the character segmentation module.
In our experiment, the character segmentation rate of our system is about 98.9% and the processing time is about 5 seconds per page with 1158 characters. This proves the effectiveness of our proposed system.

ABSTRACT IN CHINESEi
ABSTRACT IN ENGLISHii
ACKNOWLEDGEMENTSiii
TABLE OF CONTENTSiv
LIST OF FIGURESvi
LIST OF TABLESviii
Chapter 1. Introduction1
1.1 Motivation1
1.2 Problem Definition3
1.2.1 Block identification3
1.2.2 Character Segmentation4
1.3 Survey of Related Research5
1.4 System Description and Assumptions7
1.4.1 System Description7
1.4.2 Assumptions8
1.5 Thesis Organization10
Chapter 2. Document Layout Analysis11
2.1 Image Reducing11
2.2 Connected-Components Extraction13
2.3 Connected-Components Classification17
2.3.1 Features17
2.3.1.1 Component size17
2.3.1.2 Stroke width of components18
2.3.2 Procedure of connected-components classification20
2.4 Text Block Segmentation20
2.5 Text Components Extraction from Image Components22
2.6 Text Line Segmentation27
Chapter 3. Character Segmentation29
3.1 Initial Cap Detection and Extraction30
3.1.1 Initial cap detection30
3.1.2 Initial cap extraction30
3.2 Character Segmentation33
3.2.1 Projection of the count of connected-components33
3.2.2 Check of the component size33
3.2.3 Check for long consecutive half-component sequence33
3.2.4 Check for short consecutive half-component sequence35
3.2.5 Recognition-based character segmentation for half-components sequences38
Chapter 4. Experimental Results and Analysis41
Chapter 5. Conclusions and Future Works48
Reference52

[1] Y. Lu, "Machine Printed Character Segmentation - an Overview," Pattern Recognition, Vol. 28, No. 1, pp. 67-80, 1995.
[2] Y. Lu and M. Shridhar, "Character Segmentation in Handwritten Words - an OverView, "Pattern Recognition, Vol. 29, No. 1, pp. 77-96, 1996.
[3] E. Lecolient and J-V. Moreau, " An new system for automatic segmentation and recognition of unconstrained zip codes," in Proceedings Sixth Sixth Scandinavian Conference Image Analysis, Oulu, Finland, June 1989, pp. 585.
[4] H. Fujisawa and Y. Nakano, "Segmentation Methods for Character Recognition: From Segmentation to Document Structure Analysis," PROCEEDING OF THE IEEE, vol. 80, no 7, pp. 1079-1091, July 1992.
[5] J. Wang and J. Jean, "Segmentation of merged characters by neural networks and shortest path," Pattern Recognition, Vol. 27, No. 5, pp. 649-658, May 1994.
[6] C.-C Chiang and S.-S Yu, "An iterative character segmentation method for irregularly formatted Chinese documents," in Proceedings of the 5th Optical Character Recognition and Document Analysis, Chung Li, Taiwan, 1996, pp. 61-67.
[7] R.G Casey and D.R. Ferguson, "Intelligent Forms Processing," IBM System Journal, vol. 29, no. 3, pp. 435-450, 1990.
[8] T. H. Hildebrandt and W. Liu, "Optical recognition of handwritten Chinese characters advances since 1980," Pattern Recognition, Vol. 26, No. 2, pp. 205-225, 1993.
[9] T. F. Li and S. S. Yu, "Handprinted Chinese character recognition using the probability distribution feature," Intern. Journal of Pattern Recognition and Artificial Intelligence, Vol. 8, No. 5, pp. 1241-1258, 1994.
[10] R. Oka, "Handwritten Chinese-Japanese characters recognition by cellular feature," Proc. 6th Intern. Conf. on Pattern Recognition, pp. 783-785, IEEE, October 1991.
[11] R. C. Gonzalez and R.E. Woods, Digital Image processing, Addision-Wesley publishing company, 1993.
[12] K. Fukunaga, Introduction to Statistical Pattern Recognition, Second Edition, Academic Press, Inc., 1990
[13] Nikhil R. Pal and Snakar K. Pal, "A Review on Image Segmentation Techniques," Pattern Recognition, Vol. 26, NO. 9, pp. 1277-1294, 1993.