Towards a Hybrid NMF-based Neural Approach for Face Recognition on GPUs



We present a hybrid face recognition approach that
relies on a high-performance Graphics Processing Unit (GPU) implementation of the Non-Negative Matrix Factorization (NMF) and Multiple Back-Propagation (MBP) algorithms. NMF is a non-linear unsupervised algorithm which reduces the data dimensionality, while preserving the information of the most relevant features allowing for the reconstruction of the original data. The projection of the data on lower dimensional spaces accounts for noise reduction and enables to remove worthless information. By combining the strengths of both algorithms, we are able to take advantage of the high generalization potential of MBP, while upholding the parts-based representation capabilities provided by the NMF algorithm. The proposed approach is tested on the Yale and AT&T (ORL) facial images databases, evidencing robustness with dierent lighting conditions, thus demonstrating its potential and usefulness. Moreover, the speedups obtained with the GPU greatly enhance real-time
implementation face recognition systems and may be crucial for many real-world applications.


Non-negative matrix factorization, Multiple back- propagation; Dimensionality reduction, Pattern recognition, Face recognition


International Journal of Data Mining, Modelling and Management (IJDMMM), Vol. 4, #2, pp. 138-155, John Wang, May 2012


Cited by

No citations found