Predicting performance of a face recognition system based on image quality

Dutta, Abhishek

doi:10.3990/1.9789036538725

Cited by 2 publications

(1 citation statement)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This has been addressed in [21] through image de-warping models. The dependency of recognition performance on image quality in a broader sense has been the subject of research in several works [1,8]. The threat of a morphing attack in a eMRTD scenario using commercial face recognition software was first identified in [3].…”

Section: Related Workmentioning

confidence: 99%

CNNs Under Attack: On the Vulnerability of Deep Neural Networks Based Face Recognition to Image Morphing

Wandzik

Garcia

Kaeding

et al. 2017

Digital Forensics and Watermarking

View full text Add to dashboard Cite

Facial recognition has become a critical constituent of common automatic border control gates. Despite many advances in recent years, face recognition systems remain susceptible to an ever evolving diversity of spoofing attacks. It has recently been shown that high-quality face morphing or splicing can be employed to deceive facial recognition systems in a border control scenario. Moreover, facial morphs can easily be produced by means of open source software and with minimal technical knowledge. The purpose of this work is to quantify the severeness of the problem using a large dataset of morphed face images. We employ a state-of-the-art face recognition algorithm based on deep convolutional neural networks and measure its performance on a dataset of 7260 high-quality facial morphs with varying blending factor. Using the Inception-ResNet-v1 architecture we train a deep neural model on 4 million images to obtain a validation rate of 99.96% at 0.04% false acceptance rate (FAR) on the original, unmodified images. The same model fails to repel 1.13% of all morphing attacks, accepting both the impostor and the document owner. Based on these results, we discuss the observed weaknesses and possible remedies.

show abstract