Feature coding method based on shared weights support vector data description for face recognition

In this paper, we propose a feature coding method based on shared weights support vector data description (FCM-SWSVDD). The proposed process of FCM-SWSVDD is as follows. By considering the density information clusters and introducing weighting learning, an improved (SVDD), named (SWSVDD). SWSVDD can obtain cluster center radius more accurately. Incorporating triangle into same learning process, proposed. After features those images are extracted by using FCM-SWSVDD, sparse representation classifier used to classify features. Experimental results show that performance exceeds many methods.