Title :
A Highly Robust Method for Face Authentication
Author :
Fooprateepsiri, Rerkchai ; Duangphasuk, Surakran
Author_Institution :
Fac. of Inf. Sci. & Technol., Mahanakorn Univ. of Technol., Bangkok, Thailand
Abstract :
This paper proposes a highly robust method for face authentication. Techniques introduced in this work are composed of two stages. Firstly, the feature of face is to be detected by the principle of Trace Transform. Then, in the second stage, the Hausdorff-Shape Context is employed to measure and determine of similarity between models and test images. From the experimental result of 2,520 images form ORL and Yale database, the accuracy rate is very high.s
Keywords :
face recognition; transforms; Hausdorff-shape context; ORL; Yale database; face authentication; trace transform; Authentication; Face detection; Face recognition; Feature extraction; Linear discriminant analysis; Object recognition; Principal component analysis; Robustness; Scattering; Shape measurement; Face Authentication; Hausdorff distance; Shape context; Trace Transform;
Conference_Titel :
Intelligent Information and Database Systems, 2009. ACIIDS 2009. First Asian Conference on
Conference_Location :
Dong Hoi
Print_ISBN :
978-0-7695-3580-7
DOI :
10.1109/ACIIDS.2009.78
