本論文係有關文件傾斜校正系統之設計與實現，相關的研究工作包含四大部分：
第一部分為數位文件影像二值化演算法之軟體設計。
第二部分為二值化文件影像斜角偵測演算法之軟體設計，並在分析其優缺點後，為改善計算效能與斜角偵測準確度而發展出視窗式Coarse-fine斜角偵測演算法，它結合了Interline Cross-correlation與Projection Profile兩種演算法以找出文件之傾斜角度。
第三部分為二值化文件影像旋轉演算法之軟體設計，利用Coarse-fine斜角偵測演算法所找出的角度來校正傾斜的文件影像。
第四部分為文件傾斜校正系統之可靠度評估與執行效能，實驗證明在各種文件影像中文件傾斜校正系統都能運作良好。
　　整體而言，本論文係完成一個文件傾斜校正系統之軟體設計，並探討其中演算法之優劣;經各種不同的文件影像實驗，證實本論文所發展的演算法有極佳的角度偵測與校正效果，此可以改善後續的文件影像分析系統之辨識正確率。

This thesis is related to the design and implementation of a document skew correction system. The research work includes four parts.
The first part is about software design of the binarization algorithm for digital document images.
The second part is about software design of the skew detection algorithms for binary document images. After analyzing the advantages and disadvantages of these algorithms, a window-based coarse-fine skew detection algorithm has been developed to improve the computational performance and the accuracy of skew detection. Such an algorithm combines both Interline cross-correlation and projection profile algorithms to find the skew angle of a binary document image.
The third part is about software design of the rotation algorithm for binary document images. The skewed document can be corrected by using the angle that is computed by the coarse-fine skew detection algorithm.
The fourth part is about the evaluation of reliability and run-time performance of the document skew correction system. Experiments have proved that the document skew correction system can operate very well in various kinds of document images.
　On the whole, this thesis has accomplished the software design of a document skew correction system and has discussed the advantages and disadvantages of the related algorithm. After being verified by various kinds of document images, the algorithm developed in this thesis has shown very good performance for skew detection and correction. This can improve the recognition rate of a document image analysis system.

[1] 翁智賢,影像處理演算處理器之軟/硬體整合設計與實現, 國立台 灣科技大學碩士學位論文, 民國九十六年。

[2] 黃寅修,邊界與邊角偵測演算處理器之軟/硬整合設計與實現,國立 台灣科技大學碩士學位論文, 民國九十六年。

[3] 許志豪,影像二值化演算處理器之軟/硬整合設計與實現,國立 台灣科技大學碩士學位論文,民國九十八年。

[4] 李皇達,中文文件影像分析系統之設計與實現, 國立台灣科技大
學碩士學位論文,民國九十八年。

[5] 徐千洋著，Linux函式庫參考手冊，旗標出版股份有限公司，民國九十年四月初版。

[6] A. Amin and S. Fischer, “A Document Skew Detection Method Using
the Hough Transform,” Pattern Analysis & Applications, Volume 3, Number 3 / September 2000.

[7] Boiangiu Costin-Anton, Bogdan Raducanu, and Andrei-Cristian
Spataru, “High-precision orientation and skew detection for texts in
scanned documents,” ICCP 2009, Aug. 2009, pp. 145-148.

[8] Ming Chen and Xiaoqing Ding,“A robust skew detection algorithm
for grayscale document image,” Document Analysis and Recognition,
ICDAR'99, 1999.

[9] Robert M. Haralick and Linda G. Shapiro, Computer and Robot Vision, Vol.1, Addision Wesley Publishing Company, 1992.

[10] Y. Ishitani, “Document skew detection based on local region
complexity,” Document Analysis and Recognition, ICDAR, 1993,
pp. 49-52.

[11] Zhiyong Ju and Guoqing Gu, “Algorithm of document skew
detection based on character vertices,” Intelligent Information
Technology Application, vol. 2, 2009, pp. 23-26.

[12] K. Mahata and A. G. Ramakrishnan, “A novel scheme for image
rotation for document processing,” Proceedings of International
Conference on Image Processing, vol. 2, Sep. 2000, pp. 594-596.

[13]W. Niblack, An Introduction to Image Processing, Prentice-Hall, En-
glewood Cliffs, NJ, 1986, pp. 115-116.

[14] J. H. Park, I. H. Jang, and N. C. Kim, “Skew correction of business
card image in PDA,” IEEE Conference on Communications,
Computer, and Signal Processing, vol. 2, Aug. 2003, pp. 724-727.

[15] Milan Sonka, Vaclav Hlavac, and Roger Boyle, Image Processing,
Analysis, and Machine Vision, 2nd ed., PWS Publishing,1999.

[16] J. Sauvola and M. Pietikainen, ”Adaptive document Image binarizat-
ion,” Pattern Recognition, 33, 2000, pp. 225-236.
[17] Hong Yan, “Skew correction of document images using interline
cross-correlation,” Graphical Models and Image Processing,
vol. 55, Nov. 1993, pp. 538-543.

[18] Z. Yu, J. Dong, Z. Wei, and J. Shen, “A fast image rotation
algorithm for optical character recognition of chinese documents,”
International Conference on Communications, Circuits, and System
Proceedings, vol. 1, June 2006, pp. 485-489.