An End-to-End System for Unconstrained Face Verification with Deep Convolutional Neural Networks

In this paper, we present an end-to-end system for the unconstrained face verification problem based on deep convolutional neural networks (DCNN). The end-to-end system consists of three modules for face detection, alignment and verification and is evaluated using the newly released IARPA Janus Benchmark A (IJB-A) dataset and its extended version Janus Challenging set 2 (JANUS CS2) dataset. The IJB-A and CS2 datasets include real-world unconstrained faces of 500 subjects with significant pose and illumination variations which are much harder than the Labeled Faces in the Wild (LFW) and Youtube Face (YTF) datasets. Results of experimental evaluations for the proposed system on the IJB-A dataset are provided.

1. Introduction

Face verification is one of the core problems in computer vision and has been actively researched for over two decades [44]. In face verification, given two videos or images, the objective is to determine whether they belong to the same person. Many algorithms have been shown to work well on images that are collected in controlled settings. However, the performance of these algorithms often degrades significantly on images that have large variations in pose, illumination, expression, aging, and occlusion. Most face verification systems assume that the faces have already been detected and focus on designing matching algorithms. However, for an automatic face verification system to be effective, it needs to handle errors that are introduced by algorithms for automatic face detection, face association, and facial landmark detection algorithms.