Multi-scale logarithmic difference face recognition based on local binary pattern
Year: 2017
Journal of Information and Computing Science, Vol. 12 (2017), Iss. 1 : pp. 41–51
Abstract
In order to solve the problem that face recognition is sensitive to illumination variation and local binary pattern has small spatial support region. A novel face recognition approach which is multi-scale logarithmic difference face recognition based on local binary pattern is proposed. Firstly, LBP operator is used to extract the texture feature of the face. Secondly, the LBP feature is used to extract the light invariant based on the Lambertian reflection model. Then, the light invariant is used to obtain the multi-scale features according to the different distances, and the refined feature-map is obtained by the linear combination of multi-scale features. Finally, face recognition is performed using refined feature-map. Extension experiments on four data sets (Yale, FERET, ORL and MUI PIE) show that the proposed method which compares to LBP, MSLDE and Gradientface in different illumination conditions can improve the recognition performance.
Journal Article Details
Publisher Name: Global Science Press
Language: English
DOI: https://doi.org/2024-JICS-22497
Journal of Information and Computing Science, Vol. 12 (2017), Iss. 1 : pp. 41–51
Published online: 2017-01
AMS Subject Headings:
Copyright: COPYRIGHT: © Global Science Press
Pages: 11