Correlative feature applications in identity recognition based on palmprint and face
Shixiong Zhang · Journal of Circuits and Systems · 2010
Firstly, palmprint and face are preprocessed. Secondly, palmprint and face feature are enhanced by wavelet. Then combined with diagonal discrete cosine transform and two-dimensional principal component analysis (Dia-DCT+2DPCA), a novel concept for subspace analysis is presented to extract features. Finally, identity recognition can be realized according to the nearest neighbor rule. Experimental results show that identity recognition is realized. Higher correct recognition rate demonstrates the validity of this method.