Research On Biometrics Characteristic Recognition With Hand Shape

With the development of information and network technology, the information security becomes a key part of development of economy and society, personal authentication has been an important method of ensuring the security of information and network. Traditional verification methods can not meet the need because of the disadvantages of their own, such as ID card be faked and password can be stolen easily. The biometrics of humans has been the main verification method because of its uniqueness and invariability.Because of the simple collection instrument (compared with fingerprint and iris) and the high verification speed, hand shape verification becomes another method of biometrics characteristic recognition following the fingerprint verification. In the foreign biometrics characteristic recognition commodity market, the hand shape verification systems have shared the half with fingerprint systems. But techniques of the hand shape recognition and verification in our country are still in the primary development phase.Based on the PC and camera, adopted the image process and pattern recognition techniques and method, the whole procedures have been realized, including hand shape image collecting, preprocessing, characteristic extracting, matching and verifying. Algorithms of hand shape verification are studied, the traditional algorithm, sequential similarity detection algorithm (SSDA) is improved. Oriental point statistic is adopted in calculating similar, so calculation procedure is simplified and calculation speed is increased; a concept of finger direction angle is introduced, so the error from hand rotating is decreased; a method of finger block dividing is adopted, so the error from finger nonlinear movement is decreased; a concept of flexibility factor is introduced, so the problem of recognition rate decreasing, because of slight misshaping from hand pressure in data collection, is resolved. After the algorithm improvement on pattern matching mentioned above, the restriction on hand gesture is decreased, the false reject rate (FRR) and false accept rate (FAR) is decreased and reorganization speed is increased.