Improving face recognition from a single image per person via virtual images produced by imagination using neural networks

abdolali, fatemeh; dadashi, neda; SeyyedSalehi, SeyyedAli

Volume 8, Issue 1 (9-2011) JSDP 2011, 8(1): 33-44 | Back to browse issues page

Mendeley

Zotero

RefWorks

abdolali F, dadashi N, SeyyedSalehi S. Improving face recognition from a single image per person via virtual images produced by imagination using neural networks. JSDP 2011; 8 (1) :33-44
URL: http://jsdp.rcisp.ac.ir/article-1-709-en.html

Improving face recognition from a single image per person via virtual images produced by imagination using neural networks

Fatemeh Abdolali ^*

, Neda Dadashi

, SeyyedAli SeyyedSalehi

Abstract: (4021 Views)

This paper deals with the problem of face recognition from a single image per person by producing virtual images using neural networks. To this aim, the person and variation information are separated and the associated manifolds are estimated using a nonlinear neural information processing model. For increasing the number of training samples in neural classifier, virtual images are produced for the neutral pose samples in a gallery dataset. By designing various structures of neural networks, the quality of virtually produced images, and consequently the recognition accuracy rate are improved. To obtain person information manifold codes giving better performance in describing the other persons and in generalizing, a learning method based on unsupervised clustering is presented. Applying this learning method and training classifier with virtual images, gives an accuracy rate of 83.63% on test dataset, which shows 12.73% improvement in comparison with training classifier using neutral pose samples.

Keywords: Face recognition, single image per person, virtual images, manifold learning, neural network, expression variant faces

Full-Text [PDF 3960 kb] (882 Downloads)

Type of Study: Research | Subject: Paper
Received: 2011/09/22 | Accepted: 2018/02/19 | Published: 2018/02/19 | ePublished: 2018/02/19

Send email to the article author

Rights and permissions
	This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Signal and Data Processing

Vote