基于孤立点的手写数字识别算法研究

Research of Handwritten Numeral Recognition Algorithm Based on the Outlier

在信息化飞速发展的时代，字符识别是信息录入和转化的一个重要内容。其中，手写体数字的识别有着非常广泛的应用，如邮政编码、手机手写等。该文使用一种基于“孤立点”、交叉数和中间数的手写数字识别方法，利用孤立点对数字（0—9）进行首次分类，再利用交叉数和中间数对分类后的数字进行进一步分类和识别。实验结果表明，该算法有效提高了数字识别的效率。

In the age of information development, character recognition is an important content of information input and conversion.Hand- written numeral recognition has a very wide range of applications, such as postal code, mobile phone handwriting recognition. This paper presents a handwritten digital recognition method based on the＂ outlier＂, crossing number and middle number, which uses isolated point to digital （0-9） for classification, then uses crossing number and middle number for further classification and recognition. The test results show that, the algorithm can improve the efficiency of digital recognition.