Domain Fingerprints for No-Reference Image Quality Assessment

Human fingerprints are detailed and nearly unique markers of human identity. Such a stable fingerprint is also left on each acquired image. It can reveal how an image was degraded during the acquisition procedure thus closely related to quality In this work, we propose new no-reference assessment (NR-IQA) approach called domain-aware IQA (DA-IQA), which for first time introduces concept domain NR-IQA field. The learned from collections different degradations then used as characteristics identify degradation sources assess To end, design architecture, enables simultaneous determination both distortion With in better characterized, be more accurately assessed, verified by extensive experiments, show that proposed DA-IQA performs than almost all compared state-of-the-art methods.