Preprint Article Version 1 This version not peer reviewed

Face Verification with Multi-Task and Multi-Scale Features Fusion

Version 1 : Received: 18 March 2017 / Approved: 20 March 2017 / Online: 20 March 2017 (09:06:18 CET)

How to cite: Lu, X.; Yang, Y.; Zhang, W.; Wang, Q.; Wang, Y. Face Verification with Multi-Task and Multi-Scale Features Fusion. Preprints 2017, 2017030152 (doi: 10.20944/preprints201703.0152.v1). Lu, X.; Yang, Y.; Zhang, W.; Wang, Q.; Wang, Y. Face Verification with Multi-Task and Multi-Scale Features Fusion. Preprints 2017, 2017030152 (doi: 10.20944/preprints201703.0152.v1).

Abstract

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 to use identification signal 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 to use different landmarks of faces to solve the problems caused by poses. And the final face representation is formed by the concatenating feature of each deep CNN after PCA reduction. What's more, 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 LFW dataset.

Subject Areas

deep convolutional neural networks; identification; semi-verification; multi-scale features; face verification

Readers' Comments and Ratings (0)

Leave a public comment
Send a private comment to the author(s)
Rate this article
Views 0
Downloads 0
Comments 0
Metrics 0
Leave a public comment

×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.