在手写体字符识别研究中,由于书写风格的不同造成了字体变化大,导致识别难度很大,采用面积滤波对数字图像预处理消除离散点,使用Fisher分类器对样本进行分类识别,进行了手写体数字识别研究与实现,分类器识别正确率为96%.
In the field of Handwritten Digital Recognition,the recognition is difficult due to the digital varied style.This paper uses the area filter to filter the isolated pixels,and uses the Fisher classifier to classify the samples.The experiment shows that the method is effective and the correct recognization approaches 96%.