A New Finger Vein Verification Method Focused On The Protection Of The Template

Abstract

Abstract This paper examines a collection of finger vein enhancement stages that have not only low computational complexity but also high distinguishing capacity. This proposed series of enhancement stages is based on the equalization of fuzzy histograms. A mixture of Hierarchical Centroid and Gradient Histograms was used to extract features. Both the enhancement stages were evaluated using 6 fold stratified cross validation with K Nearest Neighbor and Support Vector Machine (SVM). Experimental results show that the (KNN) algorithm is a simple, easy-to-implement supervised machine learning algorithm which can be used to solve problems of classification and regression. Calculations of KNN in the test data are highly accurate. Using stratified 6-fold analyzes on all fingers of all hands in the collected database, when selecting the right and middle fingers based on the analysis of the 106 people in the data set. Compared with SVM and related works, the algorithm proposed has optimum performance.