Collaborative representation-based classification method using weighted multi-scale LBP for image recognition

In this paper, we propose a novel collaborative representation-based classification method using weighted multi-scale LBP for face recognition. First, to capture more useful local information from the dictionary, we constructed a weighted hierarchical multi-scale LBP as a dictionary optimization tool to dig out the multi-scale information of the original samples. Second, a query sample is represented as a linear combination of the most informative weighted multi-scale LBP features, in which the representation capability of each weighted multi-scale LBP feature is measured to determine the "nearest neighbors" for representing the test sample. The final goal of the proposed method is to find an optimal representation of these weighted multi-scale LBP features from the classes with major contributions. Experimental results conducted on the ORL, FERET, AR and GT face databases demonstrate the effectiveness of the proposed method