Abstract
In this paper, we describe experimental methods of recognizing the document structures of various types of documents in the framework of document understanding. Namely, we interpret document structures with individually characterized document knowledge. The document understanding process is divided into three procedures: the first is the recognition of document structures from a two-dimensional point of view; the second is the recognition of item relationships from a one-dimensional point of view; and the third is the recognition of characters from a zero-dimensional point of view. The procedure for recognizing structures plays the most important role in document understanding. This procedure extracts and classifies the logical item blocks from paper-based documents distinctly.
We discuss the structure recognition methods for three classes of documents: 1) table-form documents, filled-in forms, cataloging lists, etc. — each item block is surrounded by horizontal and vertical line segments; 2) library cataloging cards, name cards, letters, etc. — each item block is separated by spaces; 3) newspapers, pamphlets, etc. — each item block is constructed hierarchically and by combining under roughly specified layouts. The structure recognition procedure is characterized by individual recognition methods: in class 1 documents, binary trees indicating the connective relationships among neighboring item blocks, which are surrounded by line segments; in class 2 documents, binary trees defining the spatial and geometric relationships among neighboring item blocks, which are separated by spaces; and in class 3 documents, composition rules specifying the constructive relationships among neighboring item blocks, which are represented by adjacent relationship graphs. The methods are effective under the knowledge-based frame-work and are integrated complementarily from the top-down (model-driven) and bottom-up (data-driven) approaches. Of course, the integration means vary according to document classes.
Similar content being viewed by others
References
Baird HS (1990) Anatomy of a page reader, Proc. MVA 1990, pp 483–486
Ejiri M (1989) Knowledge-based approaches to practical image processing. Proc. MIV 1989, pp 1–8
Dengel A, Barth G (1988) High level document analysis guided by geometric aspects. Int J Pattern Recognition and Artiflcal Intelligence 2:641–655
Higashino I, Fujisawa H, Nakano Y, Ejiri M (1986) A knowledge-based segmentation method for document understanding. Proc. 8th ICPR, pp 745–748
Kise K, Momota K, Yamaoka M, Sugiyama J (1990) Model-based understanding of document images. Proc. MVA 1990, pp 471–474
Luo Q, Watanabe T, Yoshida Y, Inagaki Y (1990) Recognition of document structure on the basis of spatial and geometric relationships between document items. Proc. MVA 1990, pp 461–464
Luo Q, Watanabe T, Sugie N (1992) A structure recognition method for Japanese newspapers. Proc. Symposium on Document Analysis and Information Retrieval, pp 217–234
Maderluchner G (1990) Symbolic substraction of fixed formatted graphics and text fonts filled in forms. Proc. MVA 1990, pp 457–460
Nagy G (1986) Hierarchical representation of optical scanned documents. Proc. 7th ICPR, pp 347–349
Sueu CY (1986) Character recognition by computer and applications. In: Yong TY, Fu KS (eds) Handbook of pattern recognition and image processing. Academic Press, San Diego New York, p 705
Toyoda J, Noguchi Y, Nishimura Y (1982) Study of extracting Japanese newspaper article. Proc. 6th ICPR, pp 1113–1115
Tsujimoto S, Asada H (1990) Understanding multi-articled documents. Proc. 10th ICPR, pp 551–556
Watanabe T, Luo Q, Mizogami M, Yoshida Y, Inagaki Y (1989) Automatic extraction and classification of data items from library cataloging cards by a knowledge-based approach. Proc. MIV 1989, pp 67–71
Watanabe T, Luo Q, Yoshida Y, Inagaki Y (1991a) A stepwise recognition method of library cataloging cards on the basis of various kinds of knowledge. Proc. 10th IPCCC, pp 821–827
Watanabe T, Naruse H, Luo Q, Sugie N (1991b) Structure Analysis of table-form documents on the basis of the recognition of vertical and horizontal line segments. Proc. 1st ICAAR, pp 63–39
Watanabe T, Luo Q, Fukumura T (1992) A framework of layout recognition for document understanding. Proc. Symposium on Document Analysis and Information Retrieval, pp 77–95
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Watanabe, T., Luo, Q. & Sugie, N. Structure recognition methods for various types of documents. Machine Vis. Apps. 6, 163–176 (1993). https://doi.org/10.1007/BF01211939
Issue Date:
DOI: https://doi.org/10.1007/BF01211939