No abstract

No abstract

Interest on palmprint biometrics has experimented a strong growth in the last decades due to its useful characteristics as uniqueness, permanence, reliability, user-friendliness, acceptability, non-intrusiveness, and low cost of the acquisition devices, which make it attractive for civil and commercial applications. Accordingly, a wide research has been developed in this field. Nevertheless, there is a lack of evaluation of the results under a common framework which permits to obtain a fair comparison between different methods. In this work an evaluation methodology based on the definitions suggested by the ISO/IDE 19795 norm is provided and applied to evaluate different palmprint feature extraction methods and matching approaches in terms of accuracy and computation time, offering a basis against which to compare future research. Given the growing trend towards touch-less biometrics promoted by the increase in the use of mobile devices, the evaluation has been carried out using two different contact-less hand databases. First database was recorded under totally controlled environmental conditions and providing the user some feedback about the recorded images during the acquisition process, while second database introduces lighting variations as well as no-pose restrictions during the capture.

In this work, the Curvelet transform is proposed as a fairly new feature extraction method for palmprint recognition. Particularly, a multiscale analysis has been performed at four levels, assessing and combining the features extracted at each level in order to find those which better represent the palmprint. Feature matching has been conducted by means of Euclidean distance and Support Vector Machines (SVMs), and comparative results are provided. In addition, a multimodal approach involving the extracted palmprint features and hand geometry features has also been evaluated, obtaining an improvement of the results in relation to monomodal biometrics. Evaluations have been carried out following an evaluation protocol based on the definitions suggested by the ISO/IDE 19795 norm that allows for a fair comparison between the different methods. To this end, images coming from two different contact-less databases, which cover different capturing conditions, have been employed.