基于局部二值模式与深度置信网络的人脸识别

Face Recognition Based on Local Two Value Model and Deep Belief Network

针对现在的大多算法在提取人脸特征时直接提取整个人脸,而忽略局部的细节特征,提出一种将人脸图像进行分块局部运用LBP算子然后与深度置信网络结合的人脸识别算法(BPBN)。首先,将人脸图像进行分块,对分块后的图像提取LBP进行统计,将生成的LBP直方图按照一定秩序组合连接成新的特征向量。其次,将得到的LBP特征作为深度置信网络(DBN)的输入,采用贪婪算法逐层进行训练,然后用反向传播(BP)算法对训练得到的深度置信网络进行优化。最后,用训练好的深度置信网络对人脸进行识别。在ORL人脸数据库上进行实验,识别率达到96.0%,然后与传统的主成分分析(PCA)算法集成支持向量机(SVM)的方法进行相比,识别率有较为显著的提升,说明该方法具有更好的人脸识别效果。

In view of the fact that most current algorithms directly extract the entire face when extracting face features, and ignore local detailed features, this paper proposes BPBN, a face recognition algorithm that uses the LBP operator to divide the face image into blocks and then combines it with deep belief networks algorithm. First, the face image is divided into blocks, and the LBP is extracted from the divided images for statistics, and the generated LBP histograms are combined in a certain order to form a new feature vector. Secondly, the obtained LBP features are used as the input of Deep Belief Network(DBN), and the greedy algorithm is used to train layer by layer, and then the back propagation(BP) algorithm is used to optimize the trained deep confidence network. Finally, the trained deep belief network is used to recognize faces. Experiments on the ORL face database show that the recognition rate reaches 96.0%, significantly improved compared with the traditional principal component analysis(PCA) algorithm integrated support vector machine(SVM) method, which indicates that the method has better face recognition results.