Face Recognition Based on Histogram Equalization and Convolution Neural Network

Abstract

In order to improve the recognition rate of face recognition, a face recognition method based on histogram equalization and convolution neural network is proposed, which is used for face recognition. First, the histogram equalization method is used to preprocess the face image. Then, we use Google deep learning framework TensorFlow1.3.0 to build convolution neural network. Its structure is referenced to LeNet-5 model, and trained neural network is trained by pre processed face images. Finally, the test samples are input into the completed convolution neural network, and the recognition rate is obtained. By using the method of histogram equalization and convolution neural network to simulate the face images of ORL face database, it is concluded that the algorithm has a high recognition rate.