The server is under maintenance between 08:00 to 12:00 (GMT+08:00), and please visit later.
We apologize for any inconvenience caused
Login  | Sign Up  |  Oriprobe Inc. Feed
China/Asia On Demand
Journal Articles
Laws/Policies/Regulations
Companies/Products
Bookmark and Share
Face Recognition under Illumination Variations
Author(s): 
Pages: 22-25
Year: Issue:  12
Journal: Office Automation

Keyword:  Face recognitionTop-hat transformationBot-hat transformationHomomorphic filteringSingular entropy;
Abstract: In order to improve the face recognition rate under illumination variations,This paper proposes a face recog-nition method based on top-hat transformation and bot-hat transformation,homomorphic filtering and singular entropy. Firstly,the face images are proceed with top-hat transformation,bottom-hat transformation and homomorphic filtering. Then the whole singular entropy and the block singular entropy of the image are extracted to form the final classification features. Finally,the classification of the image is classified by the support vector machine. Experiments on Yale face database show that the proposed method not only has high recognition rate but also has certain robustness to illumination.
Related Articles
No related articles found