Face verification with multi-task and multi-scale feature fusion

Citations of this article
Mendeley users who have this article in their library.


Face verification for unrestricted faces in the wild is a challenging task. This paper proposes a method based on two deep convolutional neural networks (CNN) for face verification. In this work, we explore using identification signals to supervise one CNN and the combination of semi-verification and identification to train the other one. In order to estimate semi-verification loss at a low computation cost, a circle, which is composed of all faces, is used for selecting face pairs from pairwise samples. In the process of face normalization, we propose using different landmarks of faces to solve the problems caused by poses. In addition, the final face representation is formed by the concatenating feature of each deep CNN after principal component analysis (PCA) reduction. Furthermore, each feature is a combination of multi-scale representations through making use of auxiliary classifiers. For the final verification, we only adopt the face representation of one region and one resolution of a face jointing Joint Bayesian classifier. Experiments show that our method can extract effective face representation with a small training dataset and our algorithm achieves 99.71% verification accuracy on Labeled Faces in the Wild (LFW) dataset.




Lu, X., Yang, Y., Zhang, W., Wang, Q., & Wang, Y. (2017). Face verification with multi-task and multi-scale feature fusion. Entropy, 19(5). https://doi.org/10.3390/e19050228

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free