Hand Shape Recognition Method Research

As the development of information and network,the information security and social safety has becomes to a key problem to the development of economy and society which results in drawing more and more attention of identity recognition since it is a crucial aspect of information security and social safety.Identity recognition has grown to an importation means to ensure the security of information and network since traditional security technology can not satisfy it due to its intrinsic defects such as card can be easily fabricated or password can be stolen.Compared with these, recognition of a person's physical features has become the main methods since they are unique and invariant.As one the main biometric recognition technology,hand-shape recognition is another main method of biometric recognition beyond the fingerprint recognition due to its simple sampling device(compared with fingerprint,iris etc.) and fast recognition speed.Currently,in the biometric product markets aboard,products of hand-shape recognition gets the same rate with that of fingerprint recognition and it has becomes another large category recognition products.This dissertation adapts grey scale hand-shape images in BMP formation,takes advantage of the image processing and pattern recognition technology to automatically realize the a series of procedures such as the pre-processing,feature extraction,pattern matching and so on, successfully designs and achieves a hand-shape recognition system and get a good experimental results.In the natural open state of hand,this paper does research in the hand-shape image sampled in a non-fixed bolt and no touch method and proposes three kinds method to recognize.First,the finger relative length based method is used and it gets a 78.52%recognition result;then it analyzes corresponding relation of chosen to finger relative width and recognition rate,it proves through the experiments that the 90%above recognition results can be acquired when the chosen width is not less than 3 of every finger;the discriminating feature of a single person and stable recognition rate can be got when the chosen width is 6;at last,it combines the finger length and width with the weighted coefficients to effectively enhance the recognition results on the basis of not adding time consumption.