A Cognitive Vision Approach for Image Segmentation Thresholding Images of Historical Documents with Back-to-Front Interference

Author

Filho, C.J.A. ; Mello, C.B. ; Andrade, J.D. ; Falcao, D.M.A. ; Lima, Marlon P. ; Santos, W.P. ; Oliveira, Adriano L. I.

Author_Institution

Univ. of Pernambuco, Pernambuco

Volume

1

fYear

2007

fDate

29-31 Oct. 2007

Firstpage

480

Lastpage

487

Abstract

This paper presents a new algorithm for binarization of historical document images. It is adjusted to deal with the particular case of documents which are written in both sides of the paper. The digitization of these documents in general brings to the digital image this back-to-front interference. In order to deal with it, a thresholding algorithm is proposed based on color quantization by genetic algorithms and image fidelity analysis. The method achieved better results than other well-known algorithms.

Keywords

document image processing; genetic algorithms; image colour analysis; back-to-front interference; color quantization; digital image; genetic algorithm; historical document images; image binarization; thresholding images; Artificial intelligence; Data mining; Image analysis; Image segmentation; Indexing; Interference; Labeling; Machine vision; Testing; Video sharing;

fLanguage

English

Publisher

ieee

Conference_Titel

Tools with Artificial Intelligence, 2007. ICTAI 2007. 19th IEEE International Conference on

Conference_Location

Patras

ISSN

1082-3409

Print_ISBN

978-0-7695-3015-4

Type

conf

DOI

10.1109/ICTAI.2007.81

Filename

4410323