Generating Automatically Print/Scan Textures for Morphing Attack Detection Applications

TL;DR

This paper introduces transfer-based methods to automatically generate realistic print/scan face images to enhance morphing attack detection, achieving low error rates on standard datasets.

Contribution

It presents novel transfer-transfer techniques for creating synthetic print/scan images to improve MAD training datasets.

Findings

Achieved EER of 3.84% on FRGC database.

Achieved EER of 1.92% with texture-transfer images.

Demonstrated effectiveness of synthetic data in MAD.

Abstract

Morphing Attack Detection (MAD) is a relevant topic that aims to detect attempts by unauthorised individuals to access a "valid" identity. One of the main scenarios is printing morphed images and submitting the respective print in a passport application process. Today, small datasets are available to train the MAD algorithm because of privacy concerns and the limitations resulting from the effort associated with the printing and scanning of images at large numbers. In order to improve the detection capabilities and spot such morphing attacks, it will be necessary to have a larger and more realistic dataset representing the passport application scenario with the diversity of devices and the resulting printed scanned or compressed images. Creating training data representing the diversity of attacks is a very demanding task because the training material is developed manually. This paper proposes two different methods based on transfer-transfer for automatically creating digital print/scan face images and using such images in the training of a Morphing Attack Detection algorithm. Our proposed method can reach an Equal Error Rate (EER) of 3.84% and 1.92% on the FRGC/FERET database when including our synthetic and texture-transfer print/scan with 600 dpi to handcrafted images, respectively.