Automatic character location and segmentation in color scene images

Author

Wang, Hao

Author_Institution

Visual Commun. Lab., Nokia Res. Center, Beijing, China

fYear

2001

Firstpage

2

Lastpage

7

Abstract

This paper describes a connected component (CC)-based approach to automatic text location and segmentation in natural scene images. A multi-group decomposition scheme is used to deal with the complexity of the color background. Connected component extraction is implemented using the block adjacency graph (BAG) algorithm after noise filtering and runlength smearing (RLS) operation. Some heuristic features and priority adaptive segmentation (PAS) of characters are proposed in block candidate verification and grayscale-based recognition. A prototype system is completed and the experimental results prove the effectiveness of the proposed method

Keywords

feature extraction; filtering theory; image colour analysis; image segmentation; natural scenes; optical character recognition; BAG algorithm; automatic character location; automatic text location; block adjacency graph; block candidate verification; color background; color scene images; complexity; connected component extraction; grayscale-based recognition; heuristic features; multi-group decomposition scheme; natural scene images; noise filtering; priority adaptive segmentation; runlength smearing; Colored noise; Digital cameras; Flowcharts; Gray-scale; Histograms; Image analysis; Image color analysis; Image decomposition; Image segmentation; Layout;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Analysis and Processing, 2001. Proceedings. 11th International Conference on

Conference_Location

Palermo

Print_ISBN

0-7695-1183-X

Type

conf

DOI

10.1109/ICIAP.2001.956977

Filename

956977