A fast algorithm for skew detection of document images using morphology

被引：41
作者：
Das A.K. [1 ]
Chanda B. [2 ]
机构：
[1] Computer Science and Technology Department, Bengal Engineering College
[2] Electronics and Communication Sciences Unit, Indian Statistical Institute
来源：
International Journal on Document Analysis and Recognition | 2001年 / 4卷 / 2期
关键词：
Document processing; Mathematical morphology; OCR; Skew detection; Text segmentation;
D O I：
10.1007/PL00010902
中图分类号：
学科分类号：
摘要：
Any paper document when converted to electronic form through standard digitizing devices, like scanners, is subject to a small tilt or skew. Meanwhile, a de-skewed document allows a more compact representation of its components, particularly text objects, such as words, lines, and paragraphs, where they can be represented by their rectilinear bounding boxes. This simplified representation leads to more efficient, robust, as well as simpler algorithms for document image analysis including optical character recognition (OCR). This paper presents a new method for automatic detection of skew in a document image using mathematical morphology. The proposed algorithm is extremely fast as well as independent of script forms. © 2001 Springer-Verlag Berlin Heidelberg.
引用
收藏
页码：109 / 114
页数：5
相关论文
共 23 条
  • [1] Das A.K., Chanda B., Fast algorithms for morphological operations for sequential machines, Proc. 3rd Int. Conf. on Advances in Pattern Recognition and Digital Techniques, pp. 258-266, (1993)
  • [2] Akiyama T., Hagita N., Automated entry systems for printed documents, Pattern Recognition, 23, 11, pp. 1141-1153, (1990)
  • [3] Baird H.S., The skew angle of printed docuemnts, Proc. Soc. Photogr. Sci. Eng, 40, pp. 21-24, (1987)
  • [4] Chen S., Haralick R., Phillips I., Automatic text skew estimation in document images, Proc. 3rd Int. Conf. on Document Analysis and Recognition, pp. 1153-1156, (1995)
  • [5] Das A.K., Chanda B., Text segmentation from document images: A morphological approach, J. Inst. Eng. (I), 77, pp. 50-56, (1996)
  • [6] Fan K.C., Liu C.H., Wang Y.K., Segmentation and classification of mixed text/graphics/image documents, Pattern Recognition Lett, 15, pp. 1201-1209, (1994)
  • [7] Hashizume A., Yeh P.S., Rosenfeld A., A method for detectingthe orientation of aligned components, Pattern Recognition Lett, 4, pp. 125-132, (1986)
  • [8] Hinds S., Fisher J., D'Amato D.P., A document skew detection method usingrun length encodingand the Hough transform, Proc. 10th Int. Conf. Pattern Recognition, pp. 464-468, (1990)
  • [9] Hou H.S., Digital Document Processing, (1983)
  • [10] Jiang X., Bunke H., Widmer-Kljajo D., Skew detection of document images by focused nearest-neighbor clustering, Proc. ICDAR99 5th Int. Conf. on Document Analysis and Recognition, pp. 629-632, (1999)
123