立体图像质量评价是评价立体视频系统性能的有效途径, 而如何对立体图像质量进行有效的客观评价是目前的研究难点。本文提出了一种基于感知重要性的立体图像质量评价方法。该评价方法通过分析视觉显著和失真对感知质量的影响, 建立立体图像视觉感知重要性模型, 将立体图像分为四类区域: 显著失真区域、显著非失真区域、非显著失真区域和非显著非失真区域, 然后对各个区域分别进行评价, 最后通过对各个区域赋予不同的权值从而预测得到最终的客观评价值。实验结果表明, 该方法与主观评价结果有较好的相关性, 符合人眼视觉系统。

Stereoscopic image quality assessment is an effective way to evaluate the performance of stereoscopic video system. However, how to utilize human visual characteristics in quality assessment is still an unsolved issue. In this paper, an objective stereoscopic image quality assessment method is proposed based on perceptual significance. Firstly, by analyzing the effects of visual saliency and distortion on perceptual quality, we construct perceptual significance model of stereoscopic images. Then, we separate the stereoscopic image into four types of regions: salient distortion region, salient non-distortion region, non-salient distortion region and non-salient non-distortion region, and evaluate them independently. Finally, all evaluation results are integrated into an overall score. Experimental results show that the proposed method can achieve higher consistency with the subjective assessment of stereoscopic images and effectively reflect human visual system.