We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Random-filtering based sparse representation parallel face recognition.
- Authors
Tang, Deyan; Zhou, Siwang; Yang, Wenjuan
- Abstract
Collaborative representation classification (CRC) has attracted increasing attention in face recognition (FR) tasks. The two-phase sparse representation (TPSR) methods are the improved schemes. However, most existing TPSR methods decrease training samples in the first step, resulting in less similarities or discrimination for representation, even unstable classification. In this paper, we propose a novel two-phase representation based FR approach, called random-filtering based sparse representation (RFSR) scheme. In the first phase, to increase the similarity in the same class and the discrimination between different classes, RFSR uses original training samples and their corresponding random-filtering virtual samples to construct a new training set. In the second phase, it exploits the new training set to perform CRC. Furthermore, the time cost of RFSR becomes much more expensive, with the increasement of the scale of training set. To further save the computational time, the parallel measure of RFSR is proposed. The experiment results indicate that our RFSR method can improve the FR accuracy just using a simple way to obtain more training samples, along with a higher time efficiency.
- Subjects
FACE perception; MULTIPLE correspondence analysis (Statistics); DIGITAL image processing; BIOMETRIC identification; VISUAL cryptography
- Publication
Multimedia Tools & Applications, 2019, Vol 78, Issue 2, p1419
- ISSN
1380-7501
- Publication type
Article
- DOI
10.1007/s11042-018-6166-3