Total variation models based algorithm of illumination normalization for face recognition

2010 ◽  
Author(s):  
Kai Yan ◽  
Huorong Ren ◽  
Hailong Yu
Keyword(s):  
Face Recognition ◽  
Total Variation ◽  
Illumination Normalization

Illumination Invariant Face Recognition Using Nonlocal Total Variation in Logarithmic Domain

2012 ◽  
Vol 241-244 ◽  
pp. 1652-1658 ◽  
Author(s):  
Cheng Zhe Xu
Keyword(s):  
Face Recognition ◽  
Total Variation ◽  
Facial Features ◽  
Face Database ◽  
Illumination Normalization ◽  
Illumination Invariant ◽  
Lighting Conditions ◽  
Total Variation Model ◽  
Nonlocal Total Variation ◽  
Robust Face Recognition

This paper presents a new illumination normalization method for robust face recognition under varying lighting conditions. In the proposed method, the illumination component is estimated by applying nonlocal total variation model in the logarithmic domain, and then the reflectance component is obtained based on reflectance model. The proposed method restrains the halo effect effectively while preserves the adequate texture information on the reflectance images. As an illumination invariant facial features, the reflectance images are directly utilized for face recognition. Experimental results on Yale face database B and CMU PIE database show that the performance of proposed method is robust and reliable in illumination invariant face recognition.

scholarly journals Total variation models for variable lighting face recognition

2006 ◽  
Vol 28 (9) ◽  
pp. 1519-1524 ◽  
Author(s):  
T. Chen ◽  
Wotao Yin ◽  
Xiang Sean Zhou ◽  
D. Comaniciu ◽  
T.S. Huang
Keyword(s):  
Face Recognition ◽  
Total Variation

scholarly journals Illumination Normalization Algorithm Combination Analysis in Face Recognition

2017 ◽  
Vol 9 (3) ◽  
pp. 334-339
Author(s):  
Rokas Semėnas
Keyword(s):  
Face Recognition ◽  
Large Scale ◽  
Real Life ◽  
Direct Approach ◽  
Small Scale ◽  
Test Results ◽  
Illumination Normalization ◽  
Recognition Algorithms ◽  
Life Problems

Face recognition programs have many practical usages in various fields, such as security or entertainment. Existing recognition algorithms must deal with various real life problems – mainly with illumination. In practice, illumination normalization models are often used only for Small-scale futures extraction, ignoring Large-scale features. In this article, new and more direct approach to this problem is offered, used algorithms and test results are given.

Sign in / Sign up

Export Citation Format

Share Document