Aiming at the problem of low recognition rate and poor security in the process of palmprint identity authentication,a cancelable palmprint template generating algorithm is proposed,which is based on local Gabor directional pattern with adaptive threshold by mean(m LGDP),difference local Gabor directional pattern with adaptive threshold by mean(m DLGDP)and feature fusion of them.In this method,the feature code of the image is segmented and the feature vectors are extracted and binarized.Then the Bloom filter is used to achieve many-toone mapping and the location scrambling of palmprint image.Finally,the scrambling result matrix and the user key are irreversibly transformed by the convolution operation to obtain a revocable template of the palmprint image.Both theoretical and experimental results analysis show that,in the case of key loss,the method of feature fusion can enhance the diversity of the original palmprint template effectively,improve the recognition rate efficiently,and have better security.
展开▼
