中文说明：通过反复训练模板能有较高的识别率，主要是基于mtlab的程序，基于负熵最大的独立分量分析，基于欧几里得距离的聚类分析，应用小区域方差对比，程序简单，主要为数据分析和统计。
English Description：
Through repeated training template has high recognition rate and is mainly based on MTLAB procedures, the maximum entropy based on independent component analysis, Euclidean distance based clustering analysis and application of small regional variance contrast, the program is simple, mainly for data analysis and statistics.