基于多分类器集成的图像文字识别技术及其应用研究  

Image Character Recognition Technology And Its Application Research based on the Integration of Multiple Classifiers

作　　者：罗笑玲[1] 黄绍锋[1] 欧阳天优 凌一宏 潘家辉[1] 

机构地区：[1]华南师范大学软件学院,广东南海528225

出　　处：《软件》2015年第3期98-102,共5页Software

摘　　要：本文本主要对图片文字提取展开研究,首先读取图片进行预处理;然后针对网格特征和方向特征对图片文字进行特征提取;为了提高识别系统的可靠性,采用多分类器集成方法,即通过多个互补的分类器来改善单个分类器的性能。On this paper,the research on the main of text extraction,first reads the image preprocessing; Then in view of the grid features and direction of image text feature extraction; In order to improve the reliability of the recognition system,using the integration method of multiple classifiers by multiple complementary classifier to improve the performance of a single classifier.

关 键 词：图像文字识别 特征提取 多分类器集成 印刷体汉字 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]