Hand recognition

In this chapter, an overview of hand recognition is given first. We then describe the BioSecure Benchmarking Framework for hand modality, which is composed of open-source software, publicly available databases, and experimental protocols. For hand image-based person recognition, two methodologies are presented, namely geometry-based and appearance-based methods. The geometry-based method, with its C based open-source software, is part of the BioSecure Benchmarking framework for hand modality. Both methods use publicly available databases and follow the benchmarking protocols. For both systems the vital preprocessing operations involving the registration of deformable shapes are described and details of feature extraction schemes are discussed. The identification and verification results are given under a set of factors, such as population, enrollment, image resolution, time lapse and hand type. It is shown that hand modality is a user-friendly, robust and very effective biometric method, at least for populations of several hundred.