HOME INDEXING CALL FOR PAPERS JOURNAL POLICY MANUSCRIPT CURRENT ARCHIVES EDITORIAL BOARD
   
TITLE : APPEARANCE BASED MULTIMODAL RECOGNITION SYSTEM WITHOUT SUBJECT'S COOPERATION USING A NEW METHOD NAMED MAG  
AUTHORS : Raja .A.S      JosephRaj .V            
DOI : http://dx.doi.org/10.18000/ijisac.50060  
ABSTRACT :

In this manuscript we present a new multimodal biometric system named MAG for the detection and recognition of face, ear and hand geometry. We propose a new feature extraction metric (Arity) and a modified classifier (Grep) as a part of MAG method. We use Multi-objective genetic algorithm for the combinatorial search space optimization of ear, face and hand geometry. We show that our proposed MAG method improves the performance and robustness of recognition when compared to methods proposed in literature. We apply the proposed method to a variety of datasets and show the results.

Keywords:Multimodal Biometrics, Multi Objective Genetic Algorithm, Arity feature extractor, Grep classifier (MAG)

 
  Download Full Paper
 
Copyrights ©Sathyabama Institute of Science and Technology (Deemed to be University).
Powered By: Infospace Technologies