Citation Context

...and geometry system that was used in our experiments. The system computes 14 feature values comprising of the lengths of the fingers, widths of the fingers and widths of the palm at various locations =-=[26]-=-. 4.4 Combining the three modalities The database for our experiments consisted of matching scores obtained from three different modalities - face, fingerprint and hand geometry. However, data 9s(a) G...

Citation Context

...sically present at the point of identification. The physical characteristics of an individual that can be used in biometric identification/verification systems are fingerprint [3], [4], hand geometry =-=[5]-=-, [6], palm print [7], [8], [9], face [4], [10], iris [11], [12], retina [13], and ear [14]; the behavioral characteristics are signature [2], lip movement [15], speech [16], keystroke dynamics, gestu...

Citation Context

...fingerprint images and the elastic string matching technique [17] was used for computing the similarity between two minutia point patterns. Fourteen features describing the geometry of the hand shape =-=[18]-=- were extracted from the hand images and Euclidean distance was computed for each template-query pair.sTable 1. Summary of Multimodal Databases Used Database Modalities K No. of Users MSU-Multimodal F...

Citation Context

...d variety of physical characteristics are now being tested to determine the potential accuracy and ultimate consumer acceptance of their biometric measurement as personal identification standards. Up to now, biometric properties like fingerprint, face, voice, handwriting and iris were the subjects of many research efforts and used in different types of identification and verification systems. But the main reason of increased interest in this research area is that as the technology develops, these kinds of systems are more likely to run on the personal devices such as mobile phones and laptops [3]. In many access control systems like border control, personnel follow-up, important point is verification rather than identification. Hand recognition systems are very appropriate for these purposes, because they do not cause anxiety for the user like fingerprint and iris systems. People’s ease of acceptance due to their convenience, and their easy and cheap setup are the major superiorities of hand geometry based recognition systems to other systems. There are some commercial hand recognition systems available, and new algorithms were proposed recently giving better performance. Most of thes...

Citation Context

...nd geometry-based verification systems have been commercialized for almost three decades. Still, their technical descriptions are scarce and the available informations is based mostly on patents (see =-=[1, 2]-=- and the references therein). However, the problem of matching hand shapes is not only important for biometric systems, but it is part of a more general, shape-based object learning and recognition to...

Citation Context

...middle, and (e) index finger. 8[18]. We considered two computationally simpler normalization schemes to obtain the normalized feature vector x� ik . � Min-Max Normalization: xik � min( xik ) x� ik � =-=(3)-=- max( x ) � min( x ) ik ik where xik � { xi1, xi2 ,..., xiN } is the feature vector with N values and x� ik is the corresponding normalized feature vector. � Z-Score Normalization: x x �� � ik � ik � ...

Citation Context

...erprint images and the elastic string matching tech200nique [86] was used for computing the similarity between two minutia point patterns. Fourteen features describing the geometry of the hand shape =-=[98]-=- were extracted from the hand images and Euclidean distance was computed for each template-query pair. A.2 Fingerprint Databases The performance of the fingerprint-based fuzzy vault implementation has...