Image Quality Assessment of Identity Cards Using Measures from Open Face Image Quality
For remote identity verification systems, this work provides a method to assess ID card image quality to enhance security against presentation attacks.
The paper applies Open Face Image Quality (OFIQ) measures to ID card images, showing that quality assessment based on some OFIQ measures can significantly improve presentation attack detection (PAD) performance across four datasets.
This paper addresses the challenge of assessing image quality in ID cards in remote verification systems by applying capture-related quality measures from the Open Face Image Quality (OFIQ) standard to ID card images. Our preprocessing pipeline includes corner detection, perspective normalization, and comprehensive foreground masking to ensure accurate and unbiased quality measure computation. We evaluate the effectiveness of these measures by analyzing their correlation with the performance of three presentation attack detection (PAD) algorithms across four diverse ID card datasets, where two datasets contain bona fide, i.e. pristine, images and two contain printed mock ID cards. Our results suggest that quality assessment based on some OFIQ measures can significantly improve PAD performance.