According to the fact that the basic features of a palmprint, includingprincipal lines, wrinkles and ridges, have different resolutions, in this paper we analyzepalmprints using a multi-resolution method and define a ...According to the fact that the basic features of a palmprint, includingprincipal lines, wrinkles and ridges, have different resolutions, in this paper we analyzepalmprints using a multi-resolution method and define a novel palmprint feature, which calledwavelet energy feature (WEF), based on the wavelet transform. WEF can reflect the wavelet energydistribution of the principal lines, wrinkles and ridges in different directions at differentresolutions (scales), thus it can efficiently characterize palmprints. This paper also analyses thediscriminabilities of each level WEF and, according to these discriminabilities, chooses a suitableweight for each level to compute the weighted city block distance for recognition. The experimentalresults show that the order of the discriminabilities of each level WEF, from strong to weak, is the4th, 3rd, 5th, 2nd and 1st level. It also shows that WEF is robust to some extent in rotation andtranslation of the images. Accuracies of 99.24% and 99.45% have been obtained in palmprintverification and palmprint identification, respectively. These results demonstrate the power of theproposed approach.展开更多
文摘According to the fact that the basic features of a palmprint, includingprincipal lines, wrinkles and ridges, have different resolutions, in this paper we analyzepalmprints using a multi-resolution method and define a novel palmprint feature, which calledwavelet energy feature (WEF), based on the wavelet transform. WEF can reflect the wavelet energydistribution of the principal lines, wrinkles and ridges in different directions at differentresolutions (scales), thus it can efficiently characterize palmprints. This paper also analyses thediscriminabilities of each level WEF and, according to these discriminabilities, chooses a suitableweight for each level to compute the weighted city block distance for recognition. The experimentalresults show that the order of the discriminabilities of each level WEF, from strong to weak, is the4th, 3rd, 5th, 2nd and 1st level. It also shows that WEF is robust to some extent in rotation andtranslation of the images. Accuracies of 99.24% and 99.45% have been obtained in palmprintverification and palmprint identification, respectively. These results demonstrate the power of theproposed approach.
