Non-negative Sparse and Collaborative Representation for Pattern Classification
This work addresses pattern classification tasks, such as face recognition, with an incremental improvement over existing sparse and collaborative representation methods.
The authors tackled the problem of pattern classification by proposing a Non-negative Sparse and Collaborative Representation (NSCR), which enhances discriminative power through non-negativity constraints. The NSCR-based classifier outperformed previous sparse and collaborative representation methods and state-of-the-art deep approaches on benchmark datasets.
Sparse representation (SR) and collaborative representation (CR) have been successfully applied in many pattern classification tasks such as face recognition. In this paper, we propose a novel Non-negative Sparse and Collaborative Representation (NSCR) for pattern classification. The NSCR representation of each test sample is obtained by seeking a non-negative sparse and collaborative representation vector that represents the test sample as a linear combination of training samples. We observe that the non-negativity can make the SR and CR more discriminative and effective for pattern classification. Based on the proposed NSCR, we propose a NSCR based classifier for pattern classification. Extensive experiments on benchmark datasets demonstrate that the proposed NSCR based classifier outperforms the previous SR or CR based approach, as well as state-of-the-art deep approaches, on diverse challenging pattern classification tasks.