Palmprint recognition based on kernel principal component analysis and fisher linear discriminant
Weiqi Yuan · Journal of Optoelectronics·laser · 2008
A novel method for palmprint recognition based on kernel principal component analysis(KPCA) and fisher linear discriminant(FLD) is presented.After the utilization of KPCA as a pre-processing step to reduce the dimensionality of a palmprint image,the 2D image matrices are then transformed into 1D image vectors.FLD has been used to extract feature vectors for all palmprint image vectors of PolyU palmprint database.Then the cosine distances between feature vectors are calculated to match palmprints.The experiment results show that the new method has lower equal error rate(EER),shorter time for the feature extraction and faster running speed than the traditional method when the principal component numbers are different.The recognition performance of radial basis function is the best among the three different types of kernels,because the equal error rate are zero.