Skip to search boxSkip to navigationSkip to main content

Deep learning for biometric face recognition: experimental study on benchmark data sets

  • University of Bedfordshire
Research Output: Chapter in Book/Report/Conference proceeding Chapter Peer-review

Abstract

There are still problems in applications of Machine Learning for face recognition. Such factors as lighting conditions, head rotations, emotions, and view angles affect the recognition accuracy. A large number of recognition subjects requires complex class boundaries. Deep Neural Networks have provided efficient solutions, although their implementations require massive computations for evaluation and minimisation of error functions. Gradient algorithms provide iterative minimisation of the error function. A maximal performance is achieved if parameters of gradient algorithms and neural network structures are properly set. The use of pairwise neural network structures often improves the performance because such structures require a small set of optimisation parameters. The experiments have been conducted on some face biometric benchmark data sets, and the main findings are presented in the form of a tutorial.

Publication Information

Output type

Research Output: Chapter in Book/Report/Conference proceeding Chapter Peer-review

Original language

English

Pages from-to (Number of pages)

Pages 71-97

Publication milestones

  • Published - 29/01/2020

Publication status

Published - 29/01/2020

Place of publication

London

Edition

1

Volume

1

Publisher

Springer, Japan, India, Australia, Germany, United States, United Arab Emirates, Austria, Switzerland, Italy, China, United Kingdom, Netherlands, Brazil, France, Singapore

Publication series

  • Publication series name: Unsupervised and Semi-Supervised Learning
    Number: 1

ISBN (Print)

9783030325824

ISBN (Electronic)

9783030325831

External Publication IDs

  • handle.net: 10547/624023

Host publication title

Deep Biometrics

Host publication editors

  • Richard Jiang
  • Chang-Tsun Li
  • Danny Crookes
  • Weizhi Meng
  • Christophe Rosenberger

Access to documents

Publication metrics