Improved performance of face recognition using CNN with constrained triplet loss layer

Recognizing human faces is one of the most popular problems in the field of pattern recognition. Many approaches and methods have been tested and applied on the topic, especially neural networks. This paper proposed a new loss layer that can be replaced at the bottom of a neural network architecture in terms of face recognition, called constrained triplet loss layer (CTLL). In order to make more confident predictions and classifications, this loss layer helps the deep learning model to specify further distinguishable clusters between different people (classes) by placing extra constraints on images of the same person (intra-person) while putting margins on images of a different person (inter-person). This proposed constrained triplet loss layer improved the recognition accuracy on faces by 2%.