基于连通域的汉字切分技术研究  

Chinese Character Segmentation Technique Based on Interconnected Domain

作　　者：陈艳[1] 孙羽菲[1] 张玉志[1] 

机构地区：[1]中国科学院计算技术研究所

出　　处：《计算机应用研究》2005年第6期246-248,共3页Application Research of Computers

摘　　要：字符切分技术已经成为汉字识别系统设计中的关键问题,对于质量较差的文本图像,用灰度图像取代传统的二值化黑白图像能够取得更好的切分效果,基于连通域的切分算法能够对灰度图像进行较好的切分,基于连通域的汉字切分算法能有效地对文本图像中汉字字符部件进行合并及对粘连字符进行分割。Segmentation technique has become the bottleneck for the development of character recognition system. For low-quality document image, grayscale image is a better segmentation source than monochrome image. This paper presents a novel segmentation method, which is based on the concept of interconnected domain.Experiment results showed that this method can achieve better results than traditional methods.

关 键 词：灰度图像 连通域 粘连字符切分 合并 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]