A deep learning approach for face recognition based on angularly discriminative features

Face recognition in digital images or video frames has several real-world applications in the modern zone of computer vision. Loss function plays a vital role in deep face recognition. Recently, several loss functions have been proposed in classification techniques to reduce the number of model errors. Among several loss functions, softmax loss implemented either multiplicative angular or additive cosine margin. These individual margins have less capacity to reduce the model's errors. To fill this gap; we proposed a hybrid angularly discriminative features by combining multiplicative angular and additive cosine margin to improve the efficiency of angular softmax loss and large margin cosine. We trained proposed model using CASIA-WebFace dataset and testing has been performed on Labeled Face in the Wild (LFW), YouTube Faces (YTF), VGGFacel and VGGFace2. The experimental result shows 99.77% accuracy on LFW dataset whereas 96.40% accuracy achieved on YTF dataset which is higher than the existing similar state-of-theart techniques. (C) 2019 Elsevier B.V. All rights reserved.