Geometric structure analysis is a prerequisite to create electronic documents from logical components extracted from document images. This paper presents a knowledge-based method for sophisticated geometric structure analysis of technical journal pages. The proposed knowledge base encodes geometric characteristics that are not only common in technical journals but also publication-specific in the form of rules. The method takes the hybrid of top-down and bottom-up techniques and consists of two phases: region segmentation and identification. Generally, the result of the segmentation process does not have a one-to-one matching with composite layout components. Therefore, the proposed method identifies nontext objects, such as images, drawings, and tables, as well as text objects, such as text lines and equations, by splitting or grouping segmented regions into composite layout components. Experimental results with 372 images scanned from the IEEE Transactions on Pattern Analysis and Machine Intelligence show that the proposed method has performed geometric structure analysis successfully on more than 99 percent of the test images, resulting in impressive performance compared with previous works.
|Number of pages
|IEEE transactions on pattern analysis and machine intelligence
|Published - 2000 Nov
Bibliographical noteFunding Information:
This work was supported in part by the Yonsei University Research Fund of 1999. The authors would like to thank the reviewers and the associate editor for their helpful and constructive comments.
All Science Journal Classification (ASJC) codes
- Computer Vision and Pattern Recognition
- Computational Theory and Mathematics
- Artificial Intelligence
- Applied Mathematics