将BP 神经网络用于人脸识别,建立了人脸识别模型,研究了样本采样训练、样本批量训练和样本完整

训练三种训练策略对识别率的影响。所设计的识别模型包括图像压缩、图像抽样、输入矢量标准化、BP 神经网络与

竞争选择处理过程。利-BP neural network will be used for face recognition, face recognition model set up to study samples of the training sample, the sample volume and sample integrity training training training strategy for the identification of the three rates. Designed to identify the model, including image compression, image sampling, input vector for Standardization, BP neural network and competitive selection process. Lee