Binarization of Degraded Characters Using Tensor Voting Based Color Clustering

Author

Madhubalan, Kavitha ; Lee, Gueesang

Author_Institution

Dept. of Electron. & Comput. Eng., Chonnam Nat. Univ., Gwangju, South Korea

fYear

2011

fDate

Aug. 31 2011-Sept. 2 2011

Firstpage

299

Lastpage

305

Abstract

In this paper, a new method of binarizing degraded characters from scene images is presented. The proposed method helps in obtaining a binarized result even with multicolored characters subjected to heavy degradation. Color information is used in the proposed binarization method to help to separate the character from the image background and to obtain a clean representation of the final result. Images from the ICDAR 2003 robust character recognition database are used to compare the effectiveness and accuracy of the proposed algorithm with other methods.

Keywords

character recognition; image colour analysis; image representation; pattern clustering; ICDAR 2003 robust character recognition database; character separation; color clustering; degraded character binarization; image background; image representation; multicolored characters; tensor voting; Clustering algorithms; Colored noise; Feature extraction; Image color analysis; Lighting; Tensile stress; Tensor voting; color image segmentation; scene text recognition; text binarization;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer and Information Technology (CIT), 2011 IEEE 11th International Conference on

Conference_Location

Pafos

Print_ISBN

978-1-4577-0383-6

Electronic_ISBN

978-0-7695-4388-8

Type

conf

DOI

10.1109/CIT.2011.55

Filename

6036777