Adaptive binarization method for document image analysis

被引：26

作者：

Feng, ML ^{[1
]}

Tan, YP ^{[1
]}

机构：

[1] Nanyang Technol Univ, Sch Elect & Elect Engn, Singapore 2263, Singapore

来源：

2004 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXP (ICME), VOLS 1-3 | 2004年

关键词：

D O I：

10.1109/ICME.2004.1394198

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 proposed an adaptive binarization method, based on a criterion of maximizing local contrast, for document image analysis. The proposed method has overcome, to a large extent, the general problems of poor quality document images, such as non-uniform illumination, undesirable shadows and random noise. It was tested against a variety of challenging images, and the experimental results are presented to show the effectiveness and superiority of the proposed method.

引用

页码：339 / 342

页数：4