|
Title:
|
PERSON IDENTIFICATION BY FACE AUTHENTICATION USING HYBRID APPROACH |
|
Author(s):
|
Rerkchai Fooprateepsiri , Werasak Kurutach |
|
ISBN:
|
978-972-8924-93-5 |
|
Editors:
|
Pedro Isaías, Bebo White and Miguel Baptista Nunes |
|
Year:
|
2009 |
|
Edition:
|
2 |
|
Keywords:
|
Face Recognition and Authentication, Trace Transform |
|
Type:
|
Short Paper |
|
First Page:
|
344 |
|
Last Page:
|
348 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
Face authentication, also called face verification, is used to confirm the identity of a person by classifying them as either
the person they claim to be or not. For face authentication, the user generally provides a user name (and in some cases a
password as well) to an authentication system that allows access to an area or system. Stored models associated with the
provided username are used to verify the persons identity and then allow or deny access. In this paper proposes a robust
method for face authentication with variant illumination, scaling, rotation, compression, flip and difference emotions
(smiling, angry and screaming). Techniques introduced in this work are composed of two stages. First, 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 is employed to measure and determine of similarity between models and test images. Finally, our method is
evaluated with experiments on the AR, ORL, Yale face database using 5,362 face images and compared with other
related works (e.g. Eigen face). The extensive experimental results show that the average of accuracy rate of face
recognition with variant illumination, scaling, rotation, compression, flip and difference emotions is higher than 84%. |
|
|
|
|
|
|
