Title :
Quadratic spline wavelet approach to automatic extraction of baselines from document images
Author :
Tang, Yuan Y. ; Yang, Lihua ; Liu, Jiming
Author_Institution :
Dept. of Comput. Studies, Hong Kong Baptist Univ., Kowloon, Hong Kong
Abstract :
The paper presents a wavelet based approach to edge detection in document processing. According to local analysis of the document images using wavelet theory, a novel method is developed to detect the edges in document processing, including extraction of the contours of characters and extraction of the reference lines in the form document images with gray levels. In this method, the quadratic spline wavelet is utilized. Experiments have been contacted. The positive results show the effectiveness of the application of the quadratic spline wavelet to edge detection, especially to extract the reference lines and image boundaries in document processing
Keywords :
document image processing; edge detection; feature extraction; splines (mathematics); wavelet transforms; automatic baseline extraction; contours; document image processing; edge detection; form document images; gray levels; image boundaries; local analysis; quadratic spline wavelet approach; reference lines; wavelet based approach; wavelet theory; Character recognition; Image analysis; Image edge detection; Multiresolution analysis; Pattern analysis; Pattern recognition; Signal analysis; Spline; Text analysis; Wavelet analysis;
Conference_Titel :
Document Analysis and Recognition, 1997., Proceedings of the Fourth International Conference on
Conference_Location :
Ulm
Print_ISBN :
0-8186-7898-4
DOI :
10.1109/ICDAR.1997.620596