臺灣博碩士論文加值系統

本論文提出一以下往上方式作文件分析與重排的方法。首先，提出用邊緣偵測及區塊生長演算法找基本區塊的方法。利用這種方法有幾個好處，第一可以避免彩色圖片經過印刷、掃描後的雜訊干擾。第二，可以快速地取得基本區塊。接下來利用一新提出的區塊辨識演算法，利用區塊的結構以及統計特徵，判斷這些區塊為文字或是圖像區塊，再將相同屬性的區塊合併成大的區塊。在合併文字區塊的過程中，我們可以找到文字區塊的文字走向以及文字列印方向，還可以利用文字大小的特徵將文字區塊作簡單的分析。在文件重排方面，我們根據先前的結果，找到文章區塊的每一行文字，利用二值化後水平與垂直投影的特性，將每行文字作切字處理，進而找出文字區塊中的文字閱讀順序，將文章重排到新的文件中。良好的實驗結果，證明了所提出的方法是可行而且實用的。

A bottom-up approach to image document analysis and rearrangement is proposed in this study. First, an edge detection algorithm and a region-growing algorithm are proposed to extract the basic blocks. Two advantages can be obtained by employing these algorithms. First, the distortion effect caused by printing or scanning can be avoided. Second, these techniques are faster than color-quantization techniques. After basic block extraction, several features are used to classify extracted blocks into text blocks and graphic blocks. Some improved methods for merging text blocks into text areas and graphic blocks into graphic areas are also proposed. In the stage of text block merging, the direction of article reading is obtained. Some information is used to analyze text areas. For article rearrangement, we can use the segmented result to obtain the text lines in the text area, then segment the characters by characteristics of vertical and horizontal projections. After the reading orders of the characters in the text area are analyzed, article rearrangement is performed. Good experimental results prove the feasibility and practicability of the proposed approaches.

Chapter 1 Introduction
1.1 Motivation
1.2 Survey of Related Studies
1.3 Brief Description of Proposed Approach
1.3.1 Definition of terminologies
1.3.2 Assumption
1.3.3 Overview of proposed approach
1.4 Thesis Organization
Chapter 2 Segmentation of Basic Blocks
2.1 Introduction
2.2 Segmentation of Basic Blocks
2.2.1 Edge detection operation
2.2.2 Modified Region growing algorithm
2.3 Experimental Results
Chapter 3 Basic Block Recogntion
3.1 Introduction
3.2 Features for Recognition of Basic Blocks
3.2.1 Size feature
3.2.2 Statistical features
3.3 Recognition of Basic Text and Graphic Blocks
Chapter 4 Text and Graphic Area Construction
4.1 Introduction
4.2 Merge of False Blocks
4.2.1 Merge of overlapping false blocks
4.2.2 Merge of neighboring false blocks
4.3 Merge of Text Line Blocks
4.4 Merge of Punctuation Marks
4.5 Merge of Text Blocks into Text Areas
4.6 Merge of Graphic Areas
4.7 Experimental Results
Chapter 5 Character Segmentation
5.1 Introduction
5.2 Text Line Segmentation in Text Blocks
5.2.1 Text line segmentation in vertical text blocks
5.2.2 Text line segmentation in horizontal text blocks
5.3 Character Segmentation in Text Line Blocks
5.3.1 Character segmentation in vertical text line blocks
5.3.2 Character segmentation in horizontal text line blocks
5.4 Experimental Results
Chapter 6 Rearrangement of Articles
6.1 Introduction
6.2 Rearrangement of Articles
6.2.1 Rearrangement for vertical direction
6.2.2 Rearrangement for horizontal direction
6.3 Experimental Results
Chapter 7 Experimental Results and Discussions
7.1 Experimental Results
7.2 Discussions
Chapter 8 Conclusions and Suggestions for Future Research
8.1 Conclusions
8.2 Suggestions for Future Works
References

[1] F.M Wahl, K. Y. Wong, and R. G. Casey. “Block Segmentation and Text Extraction in Mixed Text/Image Documents,” Computer Graphics and Image Processing 20, pp. 375-390, 1982.
[2] H.Wang, S.Z Li, and S. Ragupathi. “Document Segmentation and Classification with Top-Down Approach,” in 1997 1st Int. Conf. On Knowledge-Based Intelligent Electronic System, p243-247, 1997.
[3] D. Wang and S. N. Srihari, “ Classification of newspaper image blocks using texture analysis,“ Computer Vision, Graphics, and Image Processing, Vol. 47, pp 327-352, 1989.
[4] L.A Fletcher and R. Kasturi, “ An Robust Algorithm For Text String Separation from Mixed Text/Graphics Images,” IEEE trans. Pattern Analysis and Machine Intelligence, Vol. 10, pp 910-918, 1998.
[5] L. Cinque, L. Lombardi, and G. Manzini, “ A Multiresolution Approach for Page Segmentation,” Pattern Recognition Letters, pp. 217-225, 1998.
[6] C.L. Tan, amd P. O. NG, “ Text Extraction Using Pyramid”, Pattern Recognition, Vol. 31, No. 1, pp. 63-72, 1998.
[7] Y. H. Chuang and W.H. Tsai, ” Segmentation of Texts, Graphics, and Special Components for Color Document Image Analysis,” in Proc. Int. Conf. Computer Vision, Graphics, and Image Processing, Taoyuan, Taiwan, Republic of China, pp. 471-478, August 1995.
[8] Y. S. Lin and W. H. Tsai, “ Image Segmentation for Color Document Analysis,” in Proc. Int. Conf. Computer Vision, Graphics, and Image Processing, Taoyuan, Taiwan, Republic of China, pp. 471-478, August 1995.
[9] A. K. Jain and B. Yu, “Automatic Text Location in Images and Video Frames,“ Pattern Recognition, vol.31, no.12, pp.2055-76, Dec. 1998.
[10] H. M Suen and J. F. Wang, ”Preprocessing of Color-Printed Document Images for Automatic Character Recognition,” Ph.D. Dissertation, Department of Computer Science and Information Engineer, National Cheng Kung University, 1998.
[11] W. L. Hwang and F. Chang, “ Character Extraction From Documents Using Wavelet Maxima,” Image and Vision Computing, 16, pp. 307-315, 1998.
[12] J. H. Bae, L. C. Jung, J. W. Kim, H. J. Kim, “ Segmentation of Touching Character Using an MLP,” Pattern Recognition Letters, 19, pp. 701-709, 1998.
[13] Y. C. Yang and C. S. Fuh, “ Chinese Character Segmentation in Machine Printed Documents,” in 7th Optical Character Recognition and Document Analysis Workshop, November 1997, pp. 2.20-2.23.
[14] R. C. Gonzalez and R. E. Woods, Digital Image Processing, Addision Wesley, pp197-201, 1992.
[15] W. H. Tsai, “Moment-Preserving Thresholding: A New Approach,” Computer Vision, Graphics and Image Processing, Vol.29, No 3, pp. 377-393, 1985.
[16] K. C. Fan and L. S. Wang, “Document Segmentation and Classification,” Proc. of 1997 IPPR Conf. On CVGIP, Taichung, Taiwan, ROC, pp 273-283, 1997.
[17] M. Sawaki and N. Hagita, “ Text line Extraction and Character Recognition of Document Headline With Graphical Designs Using Complementary Similarity Measure,” IEEE trans. Pattern Analysis and Machine Intelligence, Vol. 20, No 10, 1998, pp 1103-1109.