Fusion linear representation-based classification

Abstract

Representation-based classification methods have brought into sharp focus in recent years and achieved better classification performance. Both collaborative representation-based classification (CRC) algorithm and linear regression classification (LRC) algorithm are two typical representation-based classification methods. However, patterns from a single object are requested to lie on a linear subspace in representation-based classification methods. There are not enough samples in reality for face recognition, and it is difficult for the limited data to meet the requirement. The mirror images and the inverse images of the original images are still an effective description of the face. The problem of insufficient sample can be solved well by means of mirror image and inverse image. Based on this idea, a novel fusion linear representation-based classification method is proposed in the paper. The mirror image of each training sample is firstly generated, and the original training samples and the new obtained mirror images corresponding to the original training sample images are used for acting as training set for LRC. Then, the inverse image of each image is generated and the inverse training images are used to perform CRC. Lastly, the score-level fusion scheme is taken to complete classification task. The extensive experiment results on four public image databases clearly indicate that our method has very competitive classification results.