With the development of information technology and computer networks, interpersonal communications is not limited to face-to-face talk or exchange of letters. Different individuals can access information resources or exchange information with others remotely via internet or wireless devices at their own disposal. Therefore, it is important to verify personal identities before accessing private information, which aims at protecting information security. Biometrics emerges to provide a novel and effective solution to this demand. It captures and recognizes characteristics of human bodies or behaviors in order to achieve personal identification. Palmprint image recognition is a novel member in biometrics. It evaluates similarity of line-like textures inside central regions of palms between different individuals to recognize identities. In recent ten years, based on much research progress, the performance of palmprint recognition systems has been enhanced to a large degree. Palmprint image capturing becomes more and more convenient. As a result, palmprint recognition technology begins to be put into practical use. Most palmprint recognition systems require users to put their hands on platforms of image capturing devices. They make use of pegs to constraint hand postures. This contact way to capture palmprint images reduces usability and friendliness of human-machine interaction in the palmprint recognition systems. Therefore, contactless palmprint image acquisition and recognition have become a hot topic in palmprint recognition. Through contactless image capturing, use of such systems becomes more convenient. However, in another light, variations of hand postures are much larger in contactless image capturing than the contact solutions, including rotation, translation and scale variations of hands, which proposes a challenge to robustness of palmprint image preprocessing and feature representation. In most of applications, such variations of hand postures lead to degradation of recognition performances. In this thesis, we focus on the challenge of contactless palmprint recognition and investigate the problem of image acquisition, preprocessing, palmprint image representation and recognition. The main contributions of this thesis include: 1) We propose an overall framework of contactless palmprint recognition. Following this framework, we firstly investigate the problem of palmprint acquisition in a contactless way under simple backgrounds. We design and im...
修改评论