Prediction of Changed Faces with HSCNN

Abstract

Convolutional Neural Networks (CNN) have been successfully employed in the field of image classification. However, CNN trained using images from several years ago may be unable to identify how such images have changed over time. Cross-age face recognition is, therefore, a substantial challenge. Several efforts have been made to resolve facial changes over time utilizing recurrent neural networks (RNN) with CNN. The structure of RNN contains hidden contextual information in a hidden state to transfer a state in the previous step to the next step. This paper proposes a novel model called Hidden State-CNN (HSCNN). This adds to CNN a convolution layer of the hidden state saved as a parameter in the previous step and requires no more computing resources than CNN. The previous CNN-RNN models perform CNN and RNN, separately and then merge the results. Therefore, their systems consume twice the memory resources and CPU time, compared with the HSCNN system, which works the same as CNN only. HSCNN consists of 3 types of models. All models load hidden state ht−1 from parameters of the previous step and save ht as a parameter for the next step. In addition, model-B adds ht−1 to x, which is the previous output. The summation of ht−1 and x is multiplied by weight W. In model-C the convolution layer has two weights: W1 and W2. Training HSCNN with faces of the previous step is for testing faces of the next step in the experiment. That is, HSCNN trained with past facial data is then used to verify future data. It has been found to exhibit 10 percent greater accuracy than traditional CNN with a celeb face database.