Document image segmentation as selection of Voronoi edges

Author

Kise, Koichi ; Sato, Akinori ; Matsumoto, Keinosuke

Author_Institution

Dept. of Comput. & Syst. Sci., Osaka Prefecture Univ., Japan

fYear

1997

fDate

35601

Firstpage

32

Lastpage

39

Abstract

This paper presents a method of document image segmentation for pages with document components of arbitrary shape as well as any skew angles. The characteristics of the proposed method are as follows: the Voronoi diagram is constructed based on the connected components to obtain the candidates of boundaries of document components; and the candidates are utilized to estimate the inter-character, inter-line and inter-column gaps without the use of domain specific parameters so as to select the boundaries. From the experimental results for 80 images with non-Manhattan layout and the skews of 0°~450. We have confirmed that the method is effective for extraction of column regions and as efficient as other methods based on connected component analysis

Keywords

computational geometry; diagrams; document image processing; edge detection; image segmentation; Voronoi diagram; Voronoi edge selection; arbitrary shape document components; column region extraction; connected component analysis; document image segmentation; domain specific parameters; inter-character gaps; inter-column gaps; inter-line gaps; nonManhattan layout; skew angles; Euclidean distance; Image analysis; Image segmentation; Shape; Text analysis; White spaces;

fLanguage

English

Publisher

ieee

Conference_Titel

Document Image Analysis, 1997. (DIA '97) Proceedings., Workshop on

Conference_Location

San Juan

Print_ISBN

0-8186-8055-5

Type

conf

DOI

10.1109/DIA.1997.627089

Filename

627089