Deep Networks for Perceptual Image Quality Assessment for IRYStec Perceptual Display Platform

As most imagery is ultimately displayed to humans via physical display panels under a variety of viewing conditions, it is important to evaluate the quality of perceived imagery in addition to the quality of digital imagery alone. Conventional Image Quality Assessment (IQA) methods typically do not consider the variety of viewing conditions and make generalized assumptions about the viewer. The currently proposed research thus intends to define a method to evaluate the quality of displayed imagery, while considering various viewing conditions and the characteristics of the viewer. IRYStecs Perceptual Display Platform (PDP) software adapts the viewing experience of displayed imagery via image processing performed in accordance with the characteristics of the surrounding environment, the image content, and the viewer. IRYStec plans to use the developed solution to evaluate the quality of imagery produced by their image processing algorithms.

Faculty Supervisor:

James Clark

Student:

Andrei Chubarau

Partner:

Irystec Software Inc

Discipline:

Engineering - computer / electrical

Sector:

Information and communications technologies

University:

Program: