Geometric structure analysis of document images: A knowledge-based approach

Geometric structure analysis is a prerequisite to create electronic documen ts from logical components extracted from document images. This paper prese nts 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 pub lication-specific in the farm of rules. The method takes the hybrid of top- down and bottom-up techniques and consists of two phases: region segmentati on and identification. Generally, the result of the segmentation process do es not have a one-to-one matching with composite layout components. Therefo re, 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 percen t of the test images, resulting in impressive performance compared with pre vious works.