Strengths and Weaknesses of Deep Learning Models for Face Recognition Against Image Degradations

10/04/2017
by   Klemen Grm, et al.
0

Deep convolutional neural networks (CNNs) based approaches are the state-of-the-art in various computer vision tasks, including face recognition. Considerable research effort is currently being directed towards further improving deep CNNs by focusing on more powerful model architectures and better learning techniques. However, studies systematically exploring the strengths and weaknesses of existing deep models for face recognition are still relatively scarce in the literature. In this paper, we try to fill this gap and study the effects of different covariates on the verification performance of four recent deep CNN models using the Labeled Faces in the Wild (LFW) dataset. Specifically, we investigate the influence of covariates related to: image quality -- blur, JPEG compression, occlusion, noise, image brightness, contrast, missing pixels; and model characteristics -- CNN architecture, color information, descriptor computation; and analyze their impact on the face verification performance of AlexNet, VGG-Face, GoogLeNet, and SqueezeNet. Based on comprehensive and rigorous experimentation, we identify the strengths and weaknesses of the deep learning models, and present key areas for potential future research. Our results indicate that high levels of noise, blur, missing pixels, and brightness have a detrimental effect on the verification performance of all models, whereas the impact of contrast changes and compression artifacts is limited. It has been found that the descriptor computation strategy and color information does not have a significant influence on performance.

READ FULL TEXT

page 5

page 6

page 7

page 8

research
08/18/2016

How Image Degradations Affect Deep CNN-based Face Recognition?

Face recognition approaches that are based on deep convolutional neural ...
research
08/23/2021

Cross-Quality LFW: A Database for Analyzing Cross-Resolution Image Face Recognition in Unconstrained Environments

Real-world face recognition applications often deal with suboptimal imag...
research
04/09/2015

When Face Recognition Meets with Deep Learning: an Evaluation of Convolutional Neural Networks for Face Recognition

Deep learning, in particular Convolutional Neural Network (CNN), has ach...
research
09/19/2023

Exploring the Influence of Information Entropy Change in Learning Systems

In this work, we explore the influence of entropy change in deep learnin...
research
08/16/2018

An Experimental Evaluation of Covariates Effects on Unconstrained Face Verification

Covariates are factors that have a debilitating influence on face verifi...
research
09/22/2018

Understanding Fake Faces

Face recognition research is one of the most active topics in computer v...
research
02/10/2019

Deep learning and face recognition: the state of the art

Deep Neural Networks (DNNs) have established themselves as a dominant te...

Please sign up or login with your details

Forgot password? Click here to reset