A Robust Image Preprocessing Algorithm for Face Recognition
2014 ◽
Vol 989-994
◽
pp. 4205-4208
Keyword(s):
In order to obtain more robust face recognition results, the paper proposes an image preprocessing method based on average gradient angle (AGA). It is based on the fact that the central pixel and its neighbors are similar in the local window of an image. AGA firstly calculates the ratio between the relative intensity differences of a current pixel against its neighbors and the number of its neighbors, then employs the arctangent function on the ratio. The dimensionality of the AGA image is reduced by linear discriminant analysis to yield a low-dimensional feature vector. Experimental results show that the proposed method achieves more robust results in comparison with state-of-the-art methods in AR face database.
2014 ◽
Vol 989-994
◽
pp. 4209-4212
2014 ◽
Vol 945-949
◽
pp. 1801-1804
2006 ◽
Vol 03
(01)
◽
pp. 45-51
Keyword(s):
Keyword(s):