Facial Recogition for CASIA-Face V5 in Virtue of Convolutional Neural Networks

Since it takes too long time for computer to train to recognize individual under SVM and other traditional algorithms. in this study, this paper used a better model called Convolutional Neural Network (CNN) as the main technology to reduce the training time for computer. This paper showed every step of my proposed model openly and transparently. Eleven of my own pictures are mixed with CASIA-FaceV5 dataset since Asian people are similar to each other, so it would help with exercising the accuracy of the CNN model. This paper used the file called haarcascade_frontalface_default.xml to extract people’s face for further training. Sequential mode in Keras was used for better operating. More specifically, this paper also used ReLu function as the activation function for better result. Stochastic gradient descent (SGD) was employed with momentum to minimize the loss function. Finally, computer camera was used for taking the picture and visualize the final result. Experimental results indicate that my CNN model achieves a satisfactory performance that it can provide accurate feedback for recognition.