OPTIMIZED FRAMEWORK FOR HAND VEIN RECOGNITION

Abstract

This project explores the domain of palm vein recognition-the authentication of individuals based on their unique vein patterns in palm. Biometrics is the field of using an individual’s biological characteristics for the process of authentication and identification. The aim of this project is to design a biometric authentication system based on hand veins. A vein map with vein bifurcation points and end points from the palm region is used as a feature. This feature is used in boosted tree classifier which classifies the hand vein image of being authentic or not. Comparison with other classifiers is also done in the report. The advantages and disadvantages of using machine learning in the field of biometrics is also explored.