Title :
A hybrid method for facial recognition systems
Author :
Fooprateepsiri, Rerkchai ; Kurutach, Werasak ; Duangphasuk, Surakarn
Author_Institution :
Inf. Technol. Dept., Mahanakorn Univ. of Technol.
fDate :
March 30 2009-April 2 2009
Abstract :
This paper proposes a highly robust method for face recognition. Techniques introduced in this work are composed of two stages. Firstly, the feature of face is to be detected by the combined of trace transform and fast active contour. Then, in the second stage, the Hausdorff distance and modified shape context are employed to measure and determine of similarity between models and test images. Our system is evaluated with experiments on the AR, ORL and Yale face database face images. From experimental result, it is show that the high accuracy rate.
Keywords :
face recognition; matrix algebra; Hausdorff distance; face database face images; facial recognition systems; fast active contour; image test; modified shape context; trace transform; Active contours; Face detection; Face recognition; Information technology; Object recognition; Pattern recognition; Principal component analysis; Scattering; Shape measurement; Space technology;
Conference_Titel :
Computational Intelligence for Multimedia Signal and Vision Processing, 2009. CIMSVP '09. IEEE Symposium on
Conference_Location :
Nashville, TN
Print_ISBN :
978-1-4244-2771-0
DOI :
10.1109/CIMSVP.2009.4925648