The Research Of Contactless Palmprint And Palm Vein Fusion Algorithm

In recent years,with the continuous improvement of people's requirements for identity authentication technology,people have a lot of needs for high convenience and security.Compared to traditional recognition techniques,The biometric recognition technology is better to meet the people's present needs people,Therefore,the recognition technology based on biological characteristics has been widely concerned and developed rapidly.Traditional identification techniques include authentication methods based on knowledge or property.Compared with Traditional identification techniques,Biomedical recognition technology has outstanding convenience and security characteristics,and palmprint and vein biometric recognition technology is developing rapidly.On the one hand,the traditional contact palm acquisition system has some problems of low convenience and poor user acceptance and adaptation in terms of acquisition.These problems can be effectively solved by non-contact acquisition.On the other hand,The performance of single mode recognition technology has gradually reached the bottleneck.In view of the above problems,this paper will research the contactless palmprint and palm vein fusion recognition algorithm.In this paper,two cameras are used to collect images of palmprint and palm vein,Aiming at the problem that the non-contact acquisition method may lead to the inaccurate location of the region of interest,a multi-modal joint roi location algorithm is proposed.The algorithm is robust to rotation and displacement,and the effectiveness of the algorithm is proved by experiments on images collected in different ways.Moreover,according to the characteristics of palmprint and palm vein,multi-scale and multi-orientation loggabor wavelet and multi-scale multi-orientation Gaussian low-pass filter are used to extract palmprint and palm vein features,and directional competitive coding algorithm is used to extract coding features.The PolyU Palmprint Database is carried out to do simulation,and the results show that both feature extraction algorithms can achieve better performance than the traditional feature extraction algorithm.Finally,the palmprint and palm vein fusion algorithms are studied.The comparative competitive fusion coding(C2code)algorithm is used to fuse palmprint and palmar vein direction coding features.the fusion algorithm have batter recognition performance than single mode recognition.