Log In Sign Up

Searching for Alignment in Face Recognition

by   Xiaqing Xu, et al.

A standard pipeline of current face recognition frameworks consists of four individual steps: locating a face with a rough bounding box and several fiducial landmarks, aligning the face image using a pre-defined template, extracting representations and comparing. Among them, face detection, landmark detection and representation learning have long been studied and a lot of works have been proposed. As an essential step with a significant impact on recognition performance, the alignment step has attracted little attention. In this paper, we first explore and highlight the effects of different alignment templates on face recognition. Then, for the first time, we try to search for the optimal template automatically. We construct a well-defined searching space by decomposing the template searching into the crop size and vertical shift, and propose an efficient method Face Alignment Policy Search (FAPS). Besides, a well-designed benchmark is proposed to evaluate the searched policy. Experiments on our proposed benchmark validate the effectiveness of our method to improve face recognition performance.


page 1

page 3

page 4

page 6


Activation Template Matching Loss for Explainable Face Recognition

Can we construct an explainable face recognition network able to learn a...

An Efficient Method for Face Quality Assessment on the Edge

Face recognition applications in practice are composed of two main steps...

Sub-pixel face landmarks using heatmaps and a bag of tricks

Accurate face landmark localization is an essential part of face recogni...

Template Adaptation for Face Verification and Identification

Face recognition performance evaluation has traditionally focused on one...

Balanced Alignment for Face Recognition: A Joint Learning Approach

Face alignment is crucial for face recognition and has been widely adopt...

Occlusion-guided compact template learning for ensemble deep network-based pose-invariant face recognition

Concatenation of the deep network representations extracted from differe...