Compared with traditional contact collection method, contactless acquisition is the mainstream and trend of palmprint recognition. However, this method may lead to affine deformation caused by non-parallelity between palm plane and sensor plane. In order to improve the limitation of scale invariant feature transform (SIFT) about this problem, a better palmprint recognition method based on affine scale invariant feature transform (ASIFT) is proposed. Firstly, an affine model of the deformed palmprint is established, then the latitude and longitude angles of the camera axis are simulated, and the image features in the affine space are extracted. Based on the practical application environment, the SUT pamlprint database is established for the performance tests. Compared with the SIFT and other typical palmprint recognition methods, the experimental results show that ASIFT has good performance in resisting the affine deformation of palmprint, the equal error rate (EER) is 0.6%. In conclusion, the proposed algorithm can successfully solve the deformation problem of palmprint, and has superiority, and strong robustness and stability.
Figures - uploaded by
Sen LinAuthor contentAll figure content in this area was uploaded by Sen Lin
Content may be subject to copyright.