Ear recognition based on improved ISOMAP algorithm
Liu Jia-mi · Jisuanji yingyong yanjiu · 2014
Aiming at the poor generalization of the ISOMAP algorithm when applied on new samples,this paper proposed MRC-ISOMAP( manifold reconstruction-ISOMAP) algorithm to reduce sample characteristics' dimension on the basis of having an in-depth understanding of LLE algorithm's local reconstruction idea. For training samples,MRC-ISOMAP adopted ISOMAP algorithm's global nonlinear structure theory to calculate training samples' low-dimensional representations,and for added samples,the algorithm adopted the theory of local linear to maintain local linear relationships which could conduct the new samples' low-dimensional representation reconstructed by low-dimensional training samples more quickly and accurately. Comparing with the original ISOMAP algorithm,experiments on USTB3 ear image library show that MRC-ISOMAP algorithm can get a higher recognition rate,and achieve a higher efficiency when dealing with added samples.