Description

Deep learning based face liveness detection in videos using openCV

Abstract

       Biometric system is widely used to recognize the authorized person based on either behavioural characteristics or physical. But this can be spoofed using various traits. Spoofing attack is nothing but attacking or harming biometric recognition system using security features to use system without permission of authorized user. Images or video of person can be easily available from social media or can be easily captured from some distance   .

Proposed system

     Method of liveness detection detect physiological signs of life from face ensuring that only live face samples are stored for enrolment or authentication. For the PROJECT, we’ll be treating liveness detection as a binary classification problem .Given an input image, we’ll train a Convolutional Neural Network capable of distinguishing real faces from fake/spoofed faces.