The Preprocessing Technology Research Of Hand Vein Recognition Image

Vein patterns,as one of the personal biological characters,is unique and stable.Vein pattern verification has recently been intensively researched because of its importance in biometrics. The key of identify recognition on the use of hand vein characteristic,is how to effectively extract the structure of the hand vein image.Hand vein image was enhanced by using standardization and gray level stretching. After processed, vein image background was removed in order to extract segmentation of vein image skeletion; a new threshold segmention method was improved,and compared of usedly common segmentation method, very good skeletion segmentation result was obtained; based on existing algorithms and analyses of experimention, in order to reduce noise,median filter was adopted to smooth vein image edges, then use thinning algorithm and use a improved methord to remove outer layer edge of simple vein image structure; for different noises of vein image, different methods were adopted, a new solution method was adopted in order to use judgment of feature extraction, such as extract crossing points and so on. The experiments show that using gray level stretching and removeing noises of the hand vein image, is effectively remove interieience factor; and using thinning and restoration ,is effecively remove useless branch to preserve the major structure in the image,the new algorithms could make the skeleton express geometric structure of the hand vein image.