3 October 2014 Expression-invariant face recognition in hyperspectral images
Author Affiliations +
Optical Engineering, 53(10), 103102 (2014). doi:10.1117/1.OE.53.10.103102
The performance of a face recognition system degrades when the expression in the probe set is different from the expression in the gallery set. Previous studies use either spatial or spectral information to address this problem. We propose an algorithm that uses spatial and spectral information for expression-invariant face recognition. The algorithm uses a set of three-dimensional Gabor filters to exploit spatial and spectral correlations, while principal-component analysis is used to model expression variation. We demonstrate the effectiveness of the algorithm on a database of 200 subjects with neutral and smiling expressions and explore the dependence of the performance on image spatial resolution and training set size.
© 2014 Society of Photo-Optical Instrumentation Engineers (SPIE)
Han Wang, Tien C. Bau, Glenn E. Healey, "Expression-invariant face recognition in hyperspectral images," Optical Engineering 53(10), 103102 (3 October 2014). http://dx.doi.org/10.1117/1.OE.53.10.103102

Facial recognition systems

Principal component analysis

Hyperspectral imaging

3D modeling

Detection and tracking algorithms


Image filtering

Back to Top