臺灣博碩士論文加值系統

現今每日收送的辦公文件為數相當龐大。由於這些文件以紙上形式為多，故發展文件影像分析系統，將紙上形式的文件轉換成電子形式，其重要性急遽的增加。在文件掃瞄的過程中，我們必須確保文件方向的正確性，以避免後續文件分析上的錯誤發生。本論文提出了兩種偵測二值化文件中之傾斜角度的方法。第一個方法是利用模糊c迴歸模型 (fuzzy c-regression models) 來偵測傾斜之角度。第二個方法是依據投影之字行間正交相關 (projection-based interline cross-correlation) 法於掃瞄之影像上。此法針對隨機選取之小區域做相關性的運算，一改從前針對整張影像作運算的缺失。所提出之兩種傾斜角度偵測方法皆不需要圖文分離之繁複的前處理步驟，可大幅地降低其複雜度。於本論文中，將介紹一些文件分析技巧之前處理步驟，包括 run-length smoothing 、 black-white transition 、 及一些區域選擇之方法，這些技術將使得所提出之傾斜矯正系統所適用的文件型態更加的廣泛。最後，一新的內差技術，稱為以邊緣為依據之比例雙線性內差 (edge-directed ratio bilinear interpolation) 技術，將於本論文中詳細的描述。

Since the number of daily-received paper-based office documents is overwhelming, the development of document image analysis, which converts the paper-based documents into electronic forms becomes increasingly important. During the scanning process, we must assure that the document is in the right orientation to avoid mistakes in the following analysis. We describe two algorithms for skew detection in binary document images. The first method is based on fuzzy c-regression models (FCRM). The second method is based on projection-based interline cross-correlation in the scanned image. Instead of finding the correlation for the entire images, it is calculated over small regions selected randomly. For both two methods, they do not require prior segmentation of the document into text and graphics regions and greatly reduce the complexity of the operation. In this thesis, several image analysis techniques, including run-length smoothing, black-white transition, and operating window selection, are used to broaden the document types for skew detection. A new interpolation technique, which is called edge-directed ratio bilinear interpolation technique, is also presented here.

摘要 i
Abstract ii
誌謝 iii
Contents iv
List of Tables vi
List of Figures vii
Chapter 1 Introduction 1
Chapter 2 Skew Correction System Architecture 5
Chapter 3 Fuzzy C-Regression Models (FCRM) 8
3.1 FCRM-based Skew Detection Structure 8
3.2 Image Analysis 10
3.3 Operating Window Selection 13
3.4 Fast Interpolation Technique 16
3.5 Introduction to FCRM 21
3.6 Skew Detection based on FCRM 25
Chapter 4 Projection-based Interline Cross-Correlation 27
4.1 Interslice Cross-Correlation 27
4.2 Skew Detection Using Projection-based Interline Cross-Correlation Method 31
4.3 Skew Angle Selection 34
Chapter 5 Edge-directed Ratio Bilinear Interpolation 37
5.1 Brief Review of Traditional Image Interpolation Techniques 38
5.1.1 Direct and Inverse Mapping Method 39
5.1.2 Nearest Neighbor Interpolation 40
5.1.3 Bilinear Interpolation 41
5.2 Proposed Image Interpolation Technique 43
5.2.1 Involved Interpolation Concepts 43
5.2.2 Edge Angle Evaluation 45
5.2.3 Ratio Bilinear Interpolation 48
5.2.4 Validation 53
Chapter 6 Experimental Results 58
6.1 Manipulation of Skew Correction System 58
6.2 Testing Images 61
6.3 Accuracy of Skew Detection 65
6.4 Computational Time for Skew Detection 71
6.5 Special Applications 73
6.6 Discussions 80
Chapter 7 Conclusions 81
References 83

[1] Dengel, “ANASTASIL: A System for Low-level and High-level Geometric Analysis of Printed Documents,” in Structured Document Image Analysis, H. S. Baird, et al., Eds. New York: Springer-Verlag, pp. 70—99, 1992.
[2] S. U. Kumar and R. Kasturi, “Text Data Extraction from Microfilm Images of Punched Cards,” in Proceedings 10th International Conference Pattern Recognition, pp. 230—233, 1992.
[3] G. Ciadiella et al., “An Experimental System for Office Document Handling and Text Recognition,” in Proceedings 9th International Conference Pattern Recognition, pp. 739—743, 1988.
[4] H.S. Baird, “The Skew Angle of Printed Documents,” in Proceedings of the Conference of the Society of Photographic Scientists and Engineers, pp. 21-24, 1987.
[5] W. Postl, “Detection of Linear Oblique Structures and Skew Scan in Digitized Documents,” in Proceedings 8th International Conference Pattern Recognition, pp. 739—743, 1986.
[6] A. Hashizume, P. S. Yeh, and A. Rosenfeld, “A Method of Detecting the Orientation of Aligned Components,” in Pattern Recognition Letters, Vol. 4, pp. 125—132, 1986.
[7] L. A. Fletchler and R. A. Kasturi,“A Robust Algorithm for Text String Separation from Mixed Text/Graphics Images,” in IEEE Trans. Pattern Anal. Machine Intell., Vol. 10, pp. 910—918, Oct. 1988.
[8] D. S. Le, G. R. Thoma, and H. Wechsler, “Automated Page Orientation and Skew Angle Detection for Binary Document Images,” in Pattern Recognition, pp. 1325—1344, Oct. 1994.
[9] H. Yan, “Skew Correction of Document Images Using Interline Cross-Correlation,” in CVGIP Graphic Models Image Processing, Vol. 55, pp. 538—543, Nov. 1993.
[10] Richard J. Hathaway and James C. Bezdek, “Switching Regression Models and Fuzzy Clustering,” in IEEE Transactions on Fuzzy Systems, Vol. 1, no. 3. Aug. 1993.
[11] Chung-Chun Kung and Chih-Chien Lin, “Fuzzy C-Regression Model with A New Cluster Validity Criterion,” in Proceedings of the 2002 IEEE International Conference on Fuzzy Systems, Vol. 2 ,2002.
[12] Avanindra and Subhasis Chaudhuri, “Robust Detection of Skew in Document Images,” in IEEE Transactions on Image Processing, Vol. 6, no. 2, pp. 344—349, Feb. 1997.
[13] P.-Y. Yin, “Skew Detection and Block Classification of Printed Documents,” in Image and Vision Computing, Vol. 19, no. 8, pp. 567—579, May 2001.
[14] E. Kavallieratou, N. Fakotakis, G. Kokkinakis, “Skew Angle Estimation for Printed and Handwritten Documents Using the Wigner—Ville Distribution,” in Image and Vision Computing, Vol. 20, no. 11, pp. 813—824, Sep. 2002.
[15] C. Lee, M. Eden and M. Unser, “High-quality Image Resizing Using Oblique Projection Operators,” in IEEE Transactions on Image Processing, Vol. 7, no. 5, pp. 679—692, May 1998.
[16] M. Unser, A. Aldroubi and M. Eden, “Enlargement or Reduction of Digital Images with Minimum Loss of Information,” in IEEE Transactions on Image Processing, Vol. 4, no. 3, pp. 247—258, Mar. 1995.
[17] K. P. Hong, J. K. Paik, H. J. Kim and C. H. Lee, “An Edge-preserving Image Interpolation System for A Digital Camcorder,” in IEEE Transactions on Consumer Electronics, Vol. 42, no. 3, pp. 279—284, Aug. 1996.
[18] K. Jensen and D. Anastassiou, “Subpixel Edge Localization and the Interpolation of Still Images,” in IEEE Transactions on Image Processing, Vol. 4, no. 3, pp. 285—295, 1995.
[19] Z. Li and G. Hu, “On Edge Preservation in Multiresolution Images,” in GVGIP: Graphical Models and Image Processing, Vol. 54, no. 6, pp. 461—472, 1992.
[20] S. Dube and Li Hong, “An Adaptive Algorithm for Image Resolution Enhancement,” in Conference Record of the Thirty-Fourth Asilomar Conference on Signals, Systems and Computers, Vol. 2, pp. 1731—1734, 2000.
[21] S. W. Lee and J. K. Paik, “Image Interpolation Using Adaptive Fast B-spline Filtering,” in Proc. of IEEE Int. Conf. on Acoustics, Speech, Signal Processing, Vol. 5, pp. 177-180, 1993.
[22] M. S. Longuet-Higgins, “Statistical Properties of an Isotropic Random Surface,” Phil. Trans. Royal Soc., London, A, 250, pp.151-171, 1957.
[23] N. Memon and X. Wu, “Recent Developments in Context-based Predictive Techniques for Lossless Image Compression,” in The Computer Journal, Vol.40, No.2/3, pp. 127-136, 1997.
[24] H. Derin and H. Elliot, “Modeling and Segmentation of Noisy and Textured Images Using Gibbs Random Field,” in IEEE Trans. on Pattern Anal. Mach. Intell., Vol.9, pp. 39-55, 1987.
[25] Y. H. Lee and S. Tantaratana, “Decision-based Order Statistics Filters,” in IEEE Trans. on Acoust. Speed and Signal Processing, Vol. 38, pp. 406-420, March 1990.
[26] W. Woods, “Two-dimensional Discrete Markovian Fields,” in IEEE Trans. on Information Theory, Vol.18, pp. 232-240, 1972.
[27] A. Said and W. A. Pealrman, “A New, Fast and Efficient Image Codec Based on Set Partitioning of Hierarchical Trees,” in IEEE Trans. on Circuits Syst. Video Technology, Vol. 6, pp. 243-250, 1996.
[28] Her-Chang Pu and Chin-Teng Lin, “A Neural-Network-based Image Resolution Enhancement Scheme for Image Resizing,” in International Journal of Image and Graphics, Vol. 2, No. 4, pp. 503-517, 2002.