Face Anti-Spoofing Data

Summary

Introduction

This dataset is curated for the task of Face Anti-Spoofing, aiming to distinguish between real and spoofed (fake) facial inputs. It includes diverse attack types such as printed photos, screen replays, and 3D masks under various lighting and pose conditions. The dataset supports the development and evaluation of robust liveness detection models for secure face authentication systems.

Dataset Structure

In each phase, the dataset is provided as a .zip file containing face anti-spoofing data. Each .zip includes:

70 Real samples: Genuine face images or videos.
100 Spoof samples: Fake inputs such as printed photos, screen replays, or other spoofing techniques.

The data is organized into folders, where each folder name represents the label:

real/ — contains all real samples
spoof/ — contains all spoof samples This structure allows for easy loading and labeling during training or evaluation of anti-spoofing models.

Reference

For more dataset information, please go through the following link, dataset.

License

This repository is licensed under the MIT License.