CSDL Home IEEE Transactions on Pattern Analysis & Machine Intelligence 2000 vol.22 Issue No.11 - November
Issue No.11 - November (2000 vol.22)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/34.888708
<p><b>Abstract</b>—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 <it>IEEE Transactions on Pattern Analysis and Machine Intelligence</it> 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.</p>
Document image analysis, geometric structure analysis, region segmentation, region identification, knowledge-based approach.
Kyong-Ho Lee, Yoon-Chul Choy, Sung-Bae Cho, "Geometric Structure Analysis of Document Images: A Knowledge-Based Approach", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.22, no. 11, pp. 1224-1240, November 2000, doi:10.1109/34.888708