Neural networks for the no-reference assessment of perceived quality

Abstract

Imaging algorithms often require reliable methods to evaluate the quality effects of the visual artifacts that digital processing brings about. We adopt a no-reference objective method for predicting the perceived quality of images in a deterministic fashion. JPEG coding provides a significant and interesting case study. To enhance the coherence of the quality estimates with respect to the empirical evidence of the perceptual phenomenon, the system parameters are adjusted using subjective scores obtained from human assessors. Principal component analysis is first used to assemble a set of objective features that best characterize the information in image data. Then a neural network, based on the circular backpropagation (CBP) model, associates the selected features with the corresponding predictions of quality ratings and reproduces the scores process of human assessors. The neural model enables one to decouple the process of feature selection from the task of mapping features into a quality score. Results on a public database for an image-quality experiment involving JPEG-compressed images and comparisons with existing objective methods confirm the approach effectiveness.