Skip to Main content Skip to Navigation
Conference papers

Local binary patterns and its variants: application to face analysis

Abstract : Local Binary Pattern is a descriptor whose purpose is to summarize the local structure of the images. The goal is to be able to discriminate those different images between them. This method has gone through a large number of changes and adjustments to improve in different types of applications. This paper reviews various LBP methods for facial expression analysis and proposes a new set of LBP descriptors. Firstly, the principle of LBP method will be presented and the main variants for face recognition and facial expression analysis will be described. Then, new LBP methods will be proposed. Finally, a comparison of these different methods will be made and analyzed through experiments conducted on facial recognition database YaleB+ and on facial expressions database JAFFE.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-02488720
Contributor : Kidiyo Kpalma <>
Submitted on : Sunday, February 23, 2020 - 4:30:25 PM
Last modification on : Thursday, March 12, 2020 - 4:27:13 PM

File

KK_SmartICT2019.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02488720, version 1

Citation

Jade Lizé, Vincent Débordès, Hua Lu, Kidiyo Kpalma, Joseph Ronsin. Local binary patterns and its variants: application to face analysis. First international Conference on Smart Information & Communication Technologies (SmartICT’19), Sep 2019, Saidia, Morocco. ⟨hal-02488720⟩

Share

Metrics

Record views

12

Files downloads

7