Strengths and weaknesses of deep learning models for face recognition against image degradations

Klemen Grm*, Vitomir Struc, Anais Artiges, Matthieu Caron, Hazım K. Ekenel

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

175 Citations (Scopus)

Abstract

Convolutional neural network (CNN) based approaches are the state of the art in various computer vision tasks including face recognition. Considerable research effort is currently being directed toward further improving CNNs by focusing on model architectures and training techniques. However, studies systematically exploring the strengths and weaknesses of existing deep models for face recognition are still relatively scarce. In this paper, we try to fill this gap and study the effects of different covariates on the verification performance of four recent CNN models using the Labelled Faces in the Wild dataset. Specifically, we investigate the influence of covariates related to image quality and model characteristics, and analyse their impact on the face verification performance of different deep CNN models. 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 artefacts is limited. We find that the descriptor-computation strategy and colour information does not have a significant influence on performance.

Original languageEnglish
Pages (from-to)81-89
Number of pages9
JournalIET Biometrics
Volume7
Issue number1
DOIs
Publication statusPublished - 1 Jan 2018

Bibliographical note

Publisher Copyright:
© The Institution of Engineering and Technology 2017

Funding

This research was supported in parts by the ARRS (Slovenian Research Agency) Research Programme P2-0250 (B) Metrology and Biometric Systems, by ARRS through the junior researcher programme and by a Marie Curie FP7 Integration Grant within the 7th EU Framework Programme.

FundersFunder number
7th EU Framework Programme
Metrology and Biometric Systems
Javna Agencija za Raziskovalno Dejavnost RSP2-0250
Université Pierre et Marie Curie

    Fingerprint

    Dive into the research topics of 'Strengths and weaknesses of deep learning models for face recognition against image degradations'. Together they form a unique fingerprint.

    Cite this