Thresholding images of historical documents with back-to-front interference based on color quantization by genetic algorithms

被引：4

作者：

Bastos Filho, C. J. A. ^{[1
]}

Mello, C. A. B. ^{[1
]}

Andrade, J. D. ^{[1
]}

Falcao, D. M. A. ^{[1
]}

Lima, M. P. ^{[1
]}

Santos, W. P. ^{[1
]}

Oliveira, A. L. I. ^{[1
]}

机构：

[1] Univ Pernambuco, Polytech Sch Pernambuco, Comp Syst Dept, Recife, PE, Brazil

来源：

19TH IEEE INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE, VOL I, PROCEEDINGS | 2007年

关键词：

D O I：

10.1109/ICTAI.2007.58

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents a new algorithm for binarization of historical document images.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.

引用

页码：488 / 491

页数：4