DocumentCode
2338527
Title
Background identification based segmentation and multilayer tree representation of document images
Author
Cheng, Hui ; Fan, Zhigang
Author_Institution
Sarnoff Corp., Princeton, NJ, USA
Volume
3
fYear
2002
fDate
24-28 June 2002
Firstpage
1005
Abstract
We propose a segmentation algorithm for color document images called background identification based segmentation (BISeg). This algorithm efficiently locates and classifies objects in an image by identifying both the main background (paper background) and local backgrounds. In addition, BISeg generates a tree representation of document images, and the resulting segmentation can be used for many document processing applications including enhancement, rendering, editing and compression.
Keywords
document image processing; image classification; image colour analysis; image segmentation; object detection; trees (mathematics); background identification; background identification based segmentation; color document images; document editing; image compression; image enhancement; image segmentation; multilayer tree representation; rendering; Algorithm design and analysis; Graphics; Image coding; Image processing; Image resolution; Image segmentation; Nonhomogeneous media; Object segmentation; Printing; Rendering (computer graphics);
fLanguage
English
Publisher
ieee
Conference_Titel
Image Processing. 2002. Proceedings. 2002 International Conference on
ISSN
1522-4880
Print_ISBN
0-7803-7622-6
Type
conf
DOI
10.1109/ICIP.2002.1039145
Filename
1039145
Link To Document