Title :
Page decomposition and signature finding via shape classification and geometric layout
Author_Institution :
Bell Labs., Lucent Technol., Murray Hill, NJ, USA
Abstract :
Consider the problem of decomposing a page image into text ruling lines, signatures, other line art, and other material. A fast classifier based on a skeletonization of the image and various curve-fitting techniques gives an initial labeling, followed by Baird´s language-free layout analysis and a post-processor that uses the geometric layout to refine the decisions about text versus non-text
Keywords :
curve fitting; document image processing; image classification; image thinning; optical character recognition; OCR; curve fitting; document image processing; geometric layout; image skeletonization; language-free layout analysis; line art; page decomposition; shape classification; signature finding; text ruling lines; Art; Curve fitting; Image analysis; Image segmentation; Image storage; Labeling; Optical character recognition software; Shape; Skeleton; Text analysis;
Conference_Titel :
Document Analysis and Recognition, 1999. ICDAR '99. Proceedings of the Fifth International Conference on
Conference_Location :
Bangalore
Print_ISBN :
0-7695-0318-7
DOI :
10.1109/ICDAR.1999.791848