Disguise Face Classification Using EfficientNet Deep Learning

G. Padmashree, Shruti G. Wagle, A. K. Karunakar

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

With the rise in popularity of social media and intelligent gadgets, one essential biometrics for identifying people is their face. The efficiency of existing automatic face recognition systems has decreased due to factors such as face ageing, conceals, and pose variations. Face recognition algorithms must be more accurate for recognizing faces hidden behind masks and makeup, as security and surveillance requirements become more stringent. Disguise face classification acts as a standalone early warning system in such scenarios. The major goal of this research was to see how the EfficientNet family of models compares to the current state-of-the-art architecture in terms of disguise face classification. For disguise face classification, the EfficientNet deep learning architecture was proposed in this paper. The models were trained and tested using the Disguise Faces in Wild (DFW) 2018 data set. The transfer learning method was used to train EfficientNet and other deep learning models. Results obtained proved that EfficientNet-B3 has outperformed other EfficientNet architectures with 92.2% precision and 93.9% accuracy.

Original languageEnglish
Title of host publicationHuman-Centric Smart Computing - Proceedings of ICHCSC 2022
EditorsSiddhartha Bhattacharyya, Jyoti Sekhar Banerjee, Mario Köppen
PublisherSpringer Science and Business Media Deutschland GmbH
Pages305-314
Number of pages10
ISBN (Print)9789811954023
DOIs
Publication statusPublished - 2023
Event1st International Conference on Human-Centric Smart Computing, ICHCSC 2022 - Virtual, Online
Duration: 27-04-202229-04-2022

Publication series

NameSmart Innovation, Systems and Technologies
Volume316
ISSN (Print)2190-3018
ISSN (Electronic)2190-3026

Conference

Conference1st International Conference on Human-Centric Smart Computing, ICHCSC 2022
CityVirtual, Online
Period27-04-2229-04-22

All Science Journal Classification (ASJC) codes

  • Decision Sciences(all)
  • Computer Science(all)

Fingerprint

Dive into the research topics of 'Disguise Face Classification Using EfficientNet Deep Learning'. Together they form a unique fingerprint.

Cite this