Periocular recognition in the wild with learned label smoothing regularization

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

doi:10.1117/12.2573072

12 June 2020 Periocular recognition in the wild with learned label smoothing regularization

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

Proceedings Volume 11519, Twelfth International Conference on Digital Image Processing (ICDIP 2020); 115190T (2020) https://doi.org/10.1117/12.2573072
Event: Twelfth International Conference on Digital Image Processing, 2020, Osaka, Japan

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.

Citation Download Citation

Yoon Gyo Jung, Jaewoo Park, Leslie Ching Ow Tiong, and Andrew Beng Jin Teoh "Periocular recognition in the wild with learned label smoothing regularization", Proc. SPIE 11519, Twelfth International Conference on Digital Image Processing (ICDIP 2020), 115190T (12 June 2020); https://doi.org/10.1117/12.2573072

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available