QMagFace: Simple and Accurate Quality-Aware Face Recognition

Overview

Quality-Aware Face Recognition

26.11.2021 start readme

QMagFace: Simple and Accurate Quality-Aware Face Recognition

Table of Contents

Abstract

Face recognition systems have to deal with large variabilities (such as different poses, illuminations, and expressions) that might lead to incorrect matching decisions. These variabilities can be measured in terms of face image quality which is defined over the utility of a sample for recognition. Previous works on face recognition either do not employ this valuable information or make use of noninherently fit quality estimates. In this work, we propose a simple and effective face recognition solution (QMag- Face) that combines a quality-aware comparison score with a recognition model based on a magnitude-aware angular margin loss. The proposed approach includes modelspecific face image qualities in the comparison process to enhance the recognition performance under unconstrained circumstances. Exploiting the linearity between the qualities and their comparison scores induced by the utilized loss, our quality-aware comparison function is simple and highly generalizable. The experiments conducted on several face recognition databases and benchmarks demonstrate that the introduced quality-awareness leads to consistent improvements in the recognition performance. Moreover, the proposed QMagFace approach performs especially well under challenging circumstances, such as crosspose, cross-age, or cross-quality. Consequently, it leads to state-of-the-art performances on several face recognition benchmarks, such as 98.50% on AgeDB, 83.97% on XQLFQ, and 98.74% on CFP-FP.

Results

The proposed approach is analysed in three steps. First, we report the performance of QMagFace on six face recognition benchmarks against ten recent state-of-the-art methods in image- and video-based recognition tasks to provide a comprehensive comparison with state-of-the-art. Second, we investigate the face recognition performance of QMagFace over a wide FMR range to show its suitability for a wide variety of applications and to demonstrate that the quality-aware comparison score constantly enhances the recognition performance. Third, we analyse the optimal quality weight over a wide threshold range to demonstrate the robustness of the training process and the generalizability of the proposed approach.

In the following, we will only show some results. For more details and dicussions, please take a look at the paper.

Performance on face recognition benchmarks - The face recognition performance on the four benchmarks is reported in terms of benchmark accuracy (%). The highest performance is marked bold. The proposed approach, QMagFace-100, achieves state-of-the-art face recognition performance, especially in cross-age (AgeDB), cross-pose (CFP-FP), and cross-quality (XQLFW) scenarios. Since the FIQ captures these challenging conditions and the quality values represent the utility of the images for our specific network, the proposed quality-aware comparison score can specifically address the circumstance and their effect on the network. Consequently, it performs highly accurate in the cross-age, cross-pose, and cross-quality scenarios and achieves state-of-the-art performances.

Face recognition performance over a wide range of FMRs - The face recognition performance is reported in terms of FNMR [%] over a wide range of FMRs. The MagFace and the proposed QMagFace approach are compared for three backbone architectures on three databases. The better values between both approaches are highlighted in bold. In general, the proposed quality-aware solutions constantly improve the performance, often by a large margin. This is especially true for QMagFace based on the iResNet-100 backbone.

Robustness analysis - The optimal quality weight for different decision thresholds is reported on four databases. Training on different databases lead to similar linear solutions for the quality-weighting function. The results demonstrate that (a) the choice of a linear function is justified and (b) that the learned models have a high generalizability since the quality-weighting function trained on one database is very similar to the optimal functions of the others.

Installation

To be done soon

Citing

If you use this code, please cite the following paper.

@article{QMagFace,
  author    = {Philipp Terh{\"{o}}rst and
               Malte Ihlefeld and
               Marco Huber and
               Naser Damer and
               Florian Kirchbuchner and
               Kiran Raja and
               Arjan Kuijper},
  title     = {{QMagFace}: Simple and Accurate Quality-Aware Face Recognition},
  journal   = {CoRR},
  volume    = {abs/2111.13475},
  year      = {2021},
  url       = {https://arxiv.org/abs/2111.13475},
  eprinttype = {arXiv},
  eprint    = {2111.13475},
}

If you make use of our implementation based on MagFace, please additionally cite the original MagFace module.

Acknowledgement

This research work has been funded by the German Federal Ministry of Education and Research and the Hessen State Ministry for Higher Education, Research and the Arts within their joint support of the National Research Center for Applied Cybersecurity ATHENE. Portions of the research in this paper use the FERET database of facial images collected under the FERET program, sponsored by the DOD Counterdrug Technology Development Program Office. This work was carried out during the tenure of an ERCIM ’Alain Bensoussan‘ Fellowship Programme.

License

This project is licensed under the terms of the Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) license. Copyright (c) 2021 Fraunhofer Institute for Computer Graphics Research IGD Darmstadt

You might also like...
Face and Pose detector that emits MQTT events when a face or human body is detected and not detected.
Face and Pose detector that emits MQTT events when a face or human body is detected and not detected.

Face Detect MQTT Face or Pose detector that emits MQTT events when a face or human body is detected and not detected. I built this as an alternative t

img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation
img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation

img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation Figure 1: We estimate the 6DoF rigid transformation of a 3D face (rendered in si

[TIP 2021] SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction
[TIP 2021] SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction

SADRNet Paper link: SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction Requirements python

Realtime Face Anti Spoofing with Face Detector based on Deep Learning using Tensorflow/Keras and OpenCV
Realtime Face Anti Spoofing with Face Detector based on Deep Learning using Tensorflow/Keras and OpenCV

Realtime Face Anti-Spoofing Detection 🤖 Realtime Face Anti Spoofing Detection with Face Detector to detect real and fake faces Please star this repo

The implementation of the CVPR2021 paper "Structure-Aware Face Clustering on a Large-Scale Graph with 10^7 Nodes"

STAR-FC This code is the implementation for the CVPR 2021 paper "Structure-Aware Face Clustering on a Large-Scale Graph with 10^7 Nodes" 🌟 🌟 . 🎓 Re

Disentangled Face Attribute Editing via Instance-Aware Latent Space Search, accepted by IJCAI 2021.

Instance-Aware Latent-Space Search This is a PyTorch implementation of the following paper: Disentangled Face Attribute Editing via Instance-Aware Lat

(CVPR 2021) Lifting 2D StyleGAN for 3D-Aware Face Generation

Lifting 2D StyleGAN for 3D-Aware Face Generation Official implementation of paper "Lifting 2D StyleGAN for 3D-Aware Face Generation". Requirements You

Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistency[ECCV 2020]
Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistency[ECCV 2020]

Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistency(ECCV 2020) This is an official python implementati

Official Pytorch Implementation of 3DV2021 paper: SAFA: Structure Aware Face Animation.
Official Pytorch Implementation of 3DV2021 paper: SAFA: Structure Aware Face Animation.

SAFA: Structure Aware Face Animation (3DV2021) Official Pytorch Implementation of 3DV2021 paper: SAFA: Structure Aware Face Animation. Getting Started

Owner
Philipp Terhörst
Philipp Terhörst
MagFace: A Universal Representation for Face Recognition and Quality Assessment

MagFace MagFace: A Universal Representation for Face Recognition and Quality Assessment in IEEE Conference on Computer Vision and Pattern Recognition

Qiang Meng 523 Jan 5, 2023
Cross Quality LFW: A database for Analyzing Cross-Resolution Image Face Recognition in Unconstrained Environments

Cross-Quality Labeled Faces in the Wild (XQLFW) Here, we release the database, evaluation protocol and code for the following paper: Cross Quality LFW

Martin Knoche 10 Dec 12, 2022
A large-scale face dataset for face parsing, recognition, generation and editing.

CelebAMask-HQ [Paper] [Demo] CelebAMask-HQ is a large-scale face image dataset that has 30,000 high-resolution face images selected from the CelebA da

switchnorm 1.7k Dec 26, 2022
DVG-Face: Dual Variational Generation for Heterogeneous Face Recognition, TPAMI 2021

DVG-Face: Dual Variational Generation for HFR This repo is a PyTorch implementation of DVG-Face: Dual Variational Generation for Heterogeneous Face Re

null 52 Dec 30, 2022
Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set (CVPRW 2019). A PyTorch implementation.

Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set —— PyTorch implementation This is an unofficial offici

Sicheng Xu 833 Dec 28, 2022
AI Face Mesh: This is a simple face mesh detection program based on Artificial intelligence.

AI Face Mesh: This is a simple face mesh detection program based on Artificial Intelligence which made with Python. It's able to detect 468 different

Md. Rakibul Islam 1 Jan 13, 2022
This is the offical website for paper ''Category-consistent deep network learning for accurate vehicle logo recognition''

The Pytorch Implementation of Category-consistent deep network learning for accurate vehicle logo recognition This is the offical website for paper ''

Wanglong Lu 28 Oct 29, 2022
[ICCV 2021] Group-aware Contrastive Regression for Action Quality Assessment

CoRe Created by Xumin Yu*, Yongming Rao*, Wenliang Zhao, Jiwen Lu, Jie Zhou This is the PyTorch implementation for ICCV paper Group-aware Contrastive

Xumin Yu 31 Dec 24, 2022
Lightweight Face Image Quality Assessment

LightQNet This is a demo code of training and testing [LightQNet] using Tensorflow. Uncertainty Losses: IDQ loss PCNet loss Uncertainty Networks: Mobi

Kaen 5 Nov 18, 2022