Low cost enhanced security face recognition with stereo cameras

TL;DR

This paper presents a low-cost stereo camera-based face recognition system that enhances security by incorporating depth map analysis through deep neural networks, making it resistant to printed photo attacks.

Contribution

It introduces a novel face recognition approach using stereo cameras and deep learning to improve security over existing low-cost solutions.

Findings

Depth map analysis increases security against photo spoofing.

Real-time face authentication achieved with low-cost hardware.

Deep neural networks effectively analyze facial features and depth.

Abstract

This article explores a face recognition alternative which seeks to contribute to resolve current security vulnerabilities in most recognition architectures. Current low cost facial authentication software in the market can be fooled by a printed picture of a face due to the lack of depth information. The presented software creates a depth map of the face with the help of a stereo setup, offering a higher level of security than traditional recognition programs. Analysis of the person's identity and facial depth map are processed through deep convolutional neural networks, providing a secure low cost real-time face authentication method.