In a document analysis system, block segmentation and block classification are very important. The former segments a particular document image into homogeneous rectangular blocks. The latter classifies the segmented blocks into categories. These classified blocks may then be processed by suitable recognition systems. In this paper, we formalize the structure styles of general documents, and then propose both a robust hierarchical method of block segmentation and a simple method of block classification. The proposed block segmentation method takes a top-down hierarchical approach based on the spatial features and formalized concepts of document structure. This method is essentially independent of the document style, and can perform a type of structural analysis of the document image. The classification approach is based on a new scheme of statistical textual features, and classifies the segmented blocks into four categories: text blocks, title letter blocks, line drawing (or graphics) blocks, and halftone phonograph blocks. The proposed approaches were implemented using the C programming language in an X-Window environment under the UNIX operating system. The performance of each approach was experimentally evaluated, for both effectiveness and computational efficiency, using actual test images.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.