Visible and Infrared Face Identification via Sparse Representation. (2nd June 2013)

• Record Type: Journal Article
• Authors: Buyssens, Pierre; Revenu, Marinette
• Other Names: Ghita O. Academic Editor.; Hernandez D. Academic Editor.; Hou Z. Academic Editor.; La Cascia M. Academic Editor.; Tavares J. M. Academic Editor.
• Is Part Of: ISRN machine vision. Volume 2013(2013)
• Publication Date: 2013-06-02
• Subjects: Computer vision -- Periodicals; Computer vision; Periodicals; Electronic journals; 006.37
• DOI: 10.1155/2013/579126
• Languages: English
• ISSNs: 2090-7796

Abstract

Abstract : We present a facial recognition technique based on facial sparse representation. A dictionary is learned from data, and patches extracted from a face are decomposed in a sparse manner onto this dictionary. We particularly focus on the design of dictionaries that play a crucial role in the final identification rates. Applied to various databases and modalities, we show that this approach gives interesting performances. We propose also a score fusion framework that allows quantifying the saliency classifiers outputs and merging them according to these saliencies.