Biometric recognition is increasingly used in society for commercial applications and high-level security. However, recent works are not generalizable between the biometric modalities. We collect the GOSet dataset to study content-independent anti-spoofing.

Dataset Description

The GOSet dataset is divided into a training partition and a testing partition, which contain overlap in sensors and spoof mediums, but are disjoint in terms of object and background. Live videos are collected by viewing an object placed in front of background from a distance that maximizes the object size while maintaining high quality and focus. The viewing angle and distance are varied while collecting live videos. Spoof videos are collected by viewing a live video played through a spoof medium from appropriate distance to maximize image quality. More details are in Section 4 of our paper.

Overview Example

Figure 1: The objects and backgrounds used in the GOSet dataset.

How To Download

1. GOSet dataset is available for research purposes.

2. Submit the request at Online Application.

3. If you are unable to access Google Server in Step 2, please send an email to guoxia11@msu.edu with the following information:

    • Title: GOSet Application
    • CC: Your advisor's email
    • Content Line 1: Your name, email, affiliation
    • Content Line 2: Your advisor's name, email
    • Content Line 3: Research Lab Webpage
    • (Wrong formats may require longer time to process!)

4. You will receive the download password and instructions upon approval of your usage of the dataset, and you can download the GOSet dataset.

Acknowledgements

  • Noise Modeling, Synthesis and Classification for Generic Object Anti-Spoofing
    Joel Stehouwer, Amin Jourabloo, Yaojie Liu, Xiaoming Liu
    In Proceeding of IEEE Computer Vision and Pattern Recognition (CVPR 2020), Seattle, WA, Jun. 2020
    Bibtex | PDF | arXiv | Project Webpage
  • @inproceedings{ noise-modeling-classification-and-synthesis-for-goas,
      author = { Joel Stehouwer and Amin Jourabloo and Yaojie Liu and Xiaoming Liu },
      title = { Noise Modeling, Synthesis and Classification for Generic Object Anti-Spoofing },
      booktitle = { In Proceeding of IEEE Computer Vision and Pattern Recognition },
      address = { Seattle, WA },
      month = { June },
      year = { 2020 },
    }