Extraction and authentication of biometric finger vein using gradient boosted feature algorithm

摘要

Emerging technology for secured services is “BIOMETRIC”, term associated to identify an individual based on their physiological characteristics. Biometrics utilizes biological characteristics to recognize an individual. Authentication based on fingerprint has a lot of disadvantages such as it can be made foolproof by any unknown person. Finger vein is a non-forgeable pattern and it provides high end security as vein images are taken from live body. The pattern recognition technique which is used here is based on vein patterns present inside the finger under the surface of skin. The finger vein patterns are preprocessed, features are extracted by applying Gradient boosted feature algorithm technique and labeled using SVM classifier and they are used for authentication purpose.