Periocular recognition in the wild with learned label smoothing regularization

Yoon Gyo Jung, Jaewoo Park, Leslie Ching Ow Tiong, Andrew Beng Jin Teoh

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

Abstract

Periocular recognition has been gaining attention as one of the promising biometrics as it contains rich information of the ocular, skin and eyes color as well as eyebrow. Present researches of periocular recognition in the wild mainly are based on the convolutional neural networks that are equipped with standard cross-entropy loss. Label smoothing regularization (LSR) has been recognized as an effective regularization technique for generalization improvement. LSR optimizes the network based on a weighted combination of cross-entropy loss and KL divergence of uniform and network prediction distributions. In this paper, we extend LSR to Learned LSR (L2SR) by considering learned smoothen prediction distribution instead of predefined uniform distribution. L2SR outperforms LSR at reducing intra-class variation and, thus, improve the generalization. Extensive experiments on three periocular in the wild benchmarking datasets demonstrate the effectiveness and superiority of our method.

Original languageEnglish
Title of host publicationTwelfth International Conference on Digital Image Processing, ICDIP 2020
EditorsXudong Jiang, Hiroshi Fujita
PublisherSPIE
ISBN (Electronic)9781510638457
DOIs
Publication statusPublished - 2020
Event12th International Conference on Digital Image Processing, ICDIP 2020 - Osaka, Japan
Duration: 2020 May 192020 May 22

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume11519
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

Conference12th International Conference on Digital Image Processing, ICDIP 2020
CountryJapan
CityOsaka
Period20/5/1920/5/22

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Periocular recognition in the wild with learned label smoothing regularization'. Together they form a unique fingerprint.

  • Cite this

    Jung, Y. G., Park, J., Tiong, L. C. O., & Teoh, A. B. J. (2020). Periocular recognition in the wild with learned label smoothing regularization. In X. Jiang, & H. Fujita (Eds.), Twelfth International Conference on Digital Image Processing, ICDIP 2020 [115190T] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 11519). SPIE. https://doi.org/10.1117/12.2573072