Single-Sample Face Recognition Using SIFT Features
Yang Wang · Journal of Information Engineering University · 2008
This paper uses the pattern-specific SIFT feature and a simple non-statistical matching strategy combined with feature clustering to solve single training sample face recognition problems.Large scale experiments on FERET,ORL face databases using only one training sample per person have been carried out to compare it with existing features such as Gabor wavelet feature,Local Binary Pattern feature,and the results demonstrate the effectiveness of our methods to different face variations with only one training sample.