Palmprint recognition (PR) is an effective technology for personal recognition. A main problem, which deteriorates the performance of PR, is the deformations of palmprint images. This problem becomes more severe on contactless occasions, in which images are acquired without any guiding mechanisms, and hence critically limits the applications of PR. To solve the deformation problems, in this paper, a model for non-linearly deformed palmprint matching is derived by approximating non-linear deformed palmprint images with piecewise-linear deformed stable regions. Based on this model, a novel approach for deformed palmprint matching, named key point-based block growing (KPBG), is proposed. In KPBG, an iterative M-estimator sample consensus algorithm based on scale invariant feature transform features is devised to compute piecewise-linear transformations to approximate the non-linear deformations of palmprints, and then, the stable regions complying with the linear transformations are decided using a block growing algorithm. Palmprint feature extraction and matching are performed over these stable regions to compute matching scores for decision. Experiments on several public palmprint databases show that the proposed models and the KPBG approach can effectively solve the deformation problem in palmprint verification and outperform the state-of-the-art methods.

Contactless palmprint recognition is an effective technology for improving the user friendliness of palmprint recognition. The main challenge of contactless palmprint recognition is the intra-class variations due to the hand deformation caused by contactless image acquisition. Traditional palmprint feature extraction and matching algorithms usually require that the query image is well aligned with the gallery image, which cannot be always assured in contactless occasions. In this work, the scale invariant feature transform (SIFT) is applied for contactless palmprint feature extraction and matching. SIFT features are invariant to image rotation, translation, and scale variations, and hence are promising to solve the deformation problem. Moreover, an iterative RANSAC algorithm is proposed to refine the matched SIFT points. The iterative RANSAC retains more matched SIFT points than the traditional RANSAC algorithm despite the points comply with different transformation models. Experiments show a great improvement of verification accuracy on a public contactless palmprint database.