Face Shape Classification Based on Bilinear Network with Attention Mechanism

Abstract

Face shape is an important information in face recognition, personalized recommendation and other applications. For example, rough face shape filtering before face recognition can effectively improve the recognition accuracy and speed. At the same time, an effective face shape classification can be used to construct a recommendation system for hairstyles and glasses. Therefore, this paper proposes a new face shape classification algorithm. Firstly, the M-RetinaFace network is proposed to align face image. Secondly, by combing the attention mechanism with the EfficientNet bilinear network, the AB-CNN network is proposed to extract feature. Finally, a bilinear pooling layer is used to classify face shape. Experiments on public data sets show that, compared with existing algorithms, the algorithm proposed in this paper is get state-of-the-art results and significantly improves the accuracy of face shape classification.