Feature Representation Method Based on Kirsch Masks Filter for Face Recognition
2014 ◽
Vol 989-994
◽
pp. 4209-4212
Keyword(s):
In this paper, a feature representation method based on Kirsch masks filter for face recognition is proposed. We firstly obtain eight direction images by performing Kirsch masks filter. For each direction image, the low-dimensional feature vector is computed by Linear Discriminant Analysisis. Then, a fusion strategy is used to combine different direction image according to their respective salience. Experimental results show that our methods significantly outperform popular methods such as Gabor features, Local Binary Patterns, Regularized Robust Coding (RRC), and achieve state-of-the-art performance for difficult problems such as illumination and occlusion-robust face recognition.
2014 ◽
Vol 945-949
◽
pp. 1801-1804
2014 ◽
Vol 989-994
◽
pp. 4205-4208
2014 ◽
Vol 989-994
◽
pp. 4119-4122
2006 ◽
Vol 03
(01)
◽
pp. 45-51
2017 ◽
Vol 82
◽
pp. 1-9
◽
Keyword(s):
2017 ◽
Vol 31
(12)
◽
pp. 1756018
◽
Keyword(s):