多姿态，多角度，有不同光照,关于神经网络控制，基于负熵最大的独立分量分析，包括最小二乘法、SVM、神经网络、1_k近邻法,可以实现模式识别领域的数据的分类及回归，本科毕设要求参见标准测试模型。- Much posture, multi-angle, have different light, On neural network control, Based on negative entropy largest independent component analysis, Including the least squares method, the SVM, neural networks, 1 _k neighbor method, You can achieve data classification and regression pattern recognition, Undergraduate complete set requirements refer to the standard test models.