一种基于字符边界的细化算法

字符图像细化能极大地消除图像中的冗余信息量,大大简化字符识别特征的提取过程,提高字符识别的准确性和快速性.对字符进行细化,是字符识别的前提.提出了一种利用字符边界细化字符的算法,每一步都针对单个像素点作处理,并提取笔划单侧边缘点序列作为字符图像骨架.实验结果表明：该算法能较好地保留字符图像的基本信息,快速地去除字符图像中冗余的像素点,有效地解决了交叉点分离,笔段变短等问题,并为连笔笔划的切分提供了有效的方法,具有较好的细化结果.

An Efficient Thinning Algorithm based on Borderline

Thinning character images can greatly eliminate redundancy within image information, so that simplifying character recognition extraction process, and enhancing the accuracy and speed of character recognition by a long way. How to make thinning is the prerequisite of character recognize. Upon that a novel thinning algorithm based on borderline is proposed which treats with individual pixel point in each step and picks up unilateral edge points sequence as the framework of character image. Also, simulation results prove it can hold the basic information of character images better and can wipe off the redundancy pixel points of character images which solve the problem of intersection separates and the problem of shortened stroke segments. Furthermore it provides an efficient method to compartmentalize connective stroked. To sum up, the algorithm achieves good thinning results.