Attended Visual Content Degradation Based Reduced Reference Image Quality Assessment

Reduced-reference (RR) image quality assessment (IQA), which aims to use a small amount of the reference information but achieve high accuracy, is greatly demanded in quality-orientated systems. In order to design a better RR IQA model which performs consistently with the subjective perception, the inner mechanism of the human visual system (HVS) is usually investigated and imitated. In this paper, the attention mechanism is thoroughly analyzed and used for RR IQA modeling. Generally, the HVS is more sensitive to the distortion on the attended region than that on the unattended region. Thus, the saliency of each region is calculated to highlight its importance, and a saliency weighted local structure (SWLS)-based histogram is created for visual structure degradation measurement. Meanwhile, the distortion may cause attention shift (changing the attended region). In other words, the difference of attention between the reference and distorted images can efficiently represent the quality degradation. Therefore, the attention distribution is analyzed with the salient map, and an orientation located global saliency (OLGS)-based histogram is built for attention shift measurement. Finally, combining the quality degradations from both SWLS and OLGS, a novel attended visual content degradation-based RR IQA method is introduced.¹ Experimental results demonstrate that the proposed method uses only several values (18 values) and performs consistently with the subjective perception. Moreover, the proposed attention procedure can be easily extended to the existing RR IQA models and improve their performances.

Abstract licence: CC BY-NC-ND

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.