Fusion Face and Palmprint for Human Recognition via Spectral Eigenvector


The Biometrics recognition systems act as an efficient method with broadapplications in the area of: security access control, personal identification to humancomputercommunication. From other hand, some biometrics have only little variationover the population, have large intra-variability over time, or/and are not present in allthe population. To fill these gaps, a use of multimodal biometrics is a first choicesolution [1].This paper describes a multibiometrics method for human recognition based onnew teacher vector identified as spectrum eigenface, and spectrum eigenpalm. Theproposed combination scheme exploits parallel mode capabilities of the fusion featurevectors in matching level and invokes certain normalization techniques that increase itsrobustness to variations in geometry and illumination for face and palmprint. Thecorrelation distance is used as a similarity measure. A threshold value is used toprevent the imposter for being recognized. Experimental results demonstrate theeffectiveness of the new method compared to the unimodal biometrics for spectrumeigenface/eigenpalm.