# Deep Pixel-wise Binary Supervision for Face Presentation Attack Detection

## TL;DR

This paper introduces a CNN-based face presentation attack detection method with deep pixel-wise supervision, achieving state-of-the-art results using only frame-level data suitable for deployment on smart devices.

## Contribution

The work presents a novel CNN framework with deep pixel-wise supervision for face PAD that requires only frame-level information, enabling efficient deployment.

## Key findings

- Achieves 0% HTER on Replay Mobile dataset.
- Attains 0.42% ACER on OULU Protocol-1.
- Outperforms existing state-of-the-art methods.

## Abstract

Face recognition has evolved as a prominent biometric authentication modality. However, vulnerability to presentation attacks curtails its reliable deployment. Automatic detection of presentation attacks is essential for secure use of face recognition technology in unattended scenarios. In this work, we introduce a Convolutional Neural Network (CNN) based framework for presentation attack detection, with deep pixel-wise supervision. The framework uses only frame level information making it suitable for deployment in smart devices with minimal computational and time overhead. We demonstrate the effectiveness of the proposed approach in public datasets for both intra as well as cross-dataset experiments. The proposed approach achieves an HTER of 0% in Replay Mobile dataset and an ACER of 0.42% in Protocol-1 of OULU dataset outperforming state of the art methods.