dc.contributor.author | Asif, M Daud Abdullah | |
dc.contributor.author | Gao, Yongsheng | |
dc.contributor.author | Zhou, Jun | |
dc.contributor.editor | Murshed, M | |
dc.contributor.editor | Paul, M | |
dc.contributor.editor | Asikuzzaman, M | |
dc.contributor.editor | Pickering, M | |
dc.contributor.editor | Natu, A | |
dc.contributor.editor | RoblesKelly, A | |
dc.contributor.editor | You, S | |
dc.contributor.editor | Zheng, L | |
dc.contributor.editor | Rahman, A | |
dc.date.accessioned | 2019-07-04T12:37:43Z | |
dc.date.available | 2019-07-04T12:37:43Z | |
dc.date.issued | 2018 | |
dc.identifier.isbn | 978-1-5386-6602-9 | |
dc.identifier.doi | 10.1109/dicta.2018.8615831 | |
dc.identifier.uri | http://hdl.handle.net/10072/384217 | |
dc.description.abstract | In this paper, we propose a novel Local Mesh High-order Pattern Descriptor (LMHPD) for face recognition. This description is constructed in a high-order derivative space and is integrated with a Convolutional Neural Network (CNN) architecture. Based on the information collected at a local neighborhood of reference pixel with diverse radiuses and mesh angles, a vectorized feature representation of the reference pixel is generated to provide micro-patterns. They are then converted to multi-channels to use in conjunction with the CNN. The CNN adopted in the proposed architecture is generic and very compact with a small number of convolutional layers. However, LMHPD is derived in such a way that it can work with most of the available CNN architectures. For keeping the computational cost and time complexity at the minimum, we propose a lighter approach of high-order texture descriptor with CNN architecture that can effectively extract discriminative face features. Extensive experiments on Extended Yale B and CMU-PIE datasets show that our method consistently outperforms several alternative descriptors for face recognition under various circumstances. | |
dc.description.peerreviewed | Yes | |
dc.language | English | |
dc.publisher | IEEE | |
dc.relation.ispartofconferencename | 2018 Digital Image Computing: Techniques and Applications (DICTA) | |
dc.relation.ispartofconferencetitle | 2018 Digital Image Computing: Techniques and Applications (DICTA) | |
dc.relation.ispartofdatefrom | 2018-12-10 | |
dc.relation.ispartofdateto | 2018-12-13 | |
dc.relation.ispartoflocation | Canberra, Australia | |
dc.relation.ispartofpagefrom | 1 | |
dc.relation.ispartofpagefrom | 7 pages | |
dc.relation.ispartofpageto | 7 | |
dc.relation.ispartofpageto | 7 pages | |
dc.subject.fieldofresearch | Artificial intelligence | |
dc.subject.fieldofresearchcode | 4602 | |
dc.title | Face Recognition with Multi-channel Local Mesh High-order Pattern Descriptor and Convolutional Neural Network | |
dc.type | Conference output | |
dc.type.description | E1 - Conferences | |
dc.type.code | E - Conference Publications | |
gro.hasfulltext | No Full Text | |
gro.griffith.author | Zhou, Jun | |
gro.griffith.author | Gao, Yongsheng | |