NMF Face Recognition Method Based on Alpha Divergence
This paper proposed NMF decomposition method based on Alpha divergence for face recognition, which uses Alpha divergence as a distance measure standard to obtain the corresponding NMF decomposition expression. Through the parameter values derived from the expression, a variety of decomposition iteration expression can be obtained. In each iteration process, the differences are calculated to determine the optimal parameters of the next step. Such decomposition can converge to the global optimum to improve the accuracy of face recognition.
KeywordsNMF Alpha divergence Face recognition
- 2.Lu j, Plataniotis KN, Venetsanopoulos AN (2003) Face recognition using kernel direct discriminant analysis algorithms. IEEE Trans Neural Networks 14(1):117–126Google Scholar
- 4.Dhillon S, Sra S (2005) Generalized nonnegative matrix approximations with Bregman divergences. Adv Neural Inf Process Syst 05:19–24Google Scholar
- 6.Amari S, Cichocki A (2010) Information geometry of divergence functions. Bull Pol Acad Sci 58:183–195Google Scholar
- 7.Cichocki A, Zdunek R, Phan AH, Amari S (2009) Nonnegative matrix and tensor factorizations, vol 47. Wiley, Chichester, pp 24–27Google Scholar