Psychologically inspired dimensionality reduction for 2D and 3D Face Recognition

Hansen, Mark F; Atkinson, Gary; Smith, Melvyn; Smith, Lyndon

Abstract

We present a number of related novel methods for reducing the dimensionality of data for the purposes of 2D and 3D face recognition. Results from psychology show that humans are capable of very good recognition of low resolution images and caricatures. These findings have inspired our experiments into methods of effective dimension reduction. For experimentation we use a subset of the benchmark FRGCv2.0 database as well as our own photometric stereo ``Photoface'' database. Our approaches look at the effects of image resizing, and inclusion of pixels based on percentiles and variance. Via the best combination of these techniques we represent a 3D image using only 61 variables and achieve 95.75% recognition performance (only a 2.25% decrease from using all pixels). These variables are extracted using computationally efficient techniques instead of more intensive methods employed by Eigenface and Fisherface techniques and can additionally reduce processing time tenfold.

• Presentation Conference Type: Conference Paper (unpublished)
• Conference Name: British Machine Vision Conference 2011
• Start Date: Sep 1, 2011
• End Date: Sep 1, 2011
• Publication Date: Dec 1, 2011
• Deposit Date: Nov 8, 2012
• Publicly Available Date: Feb 24, 2016
• Peer Reviewed: Peer Reviewed
• Pages: 15-26
• Keywords: 2D face recognition, 3d face recognition, dimensionality reduction, bio-inspiration, caricaturing
• Public URL: https://uwe-repository.worktribe.com/output/957178
• Publisher URL: http://www.bmva.org/bmvc/2011/proceedings/paperi4/WorkshopProceedings.pdf
• Additional Information: Title of Conference or Conference Proceedings : British Machine Vision Conference 2011
• Contract Date: Feb 24, 2016