CAJ | 학술논문

基于人眼视觉系统对图像边缘结构信息和局部亮度刺激敏感的假设，该文提出了一种基于全变分模型的视觉感知图像质量评价PIQA方法。该方法由边缘结构信息评价和局部亮度信息评价两部分组成。本文首先采用全变分模型描述失真图像与原始参考图像之间的图像结构信息变化；为测量亮度失真，又采用失真图像与参考图像之间的差值图像中封闭区域的能量函数来衡量人眼敏感的图像亮度信息。最后，采用3种标准图像数据库验证该评价方法的性能。实验结果表明，所提出的图像质量评价方法优于现有的图像评价标准。
기우인안시각계통대도상변연결구신식화국부량도자격민감적가설，해문제출료일충기우전변분모형적시각감지도상질량평개PIQA방법。해방법유변연결구신식평개화국부량도신식평개량부분조성。본문수선채용전변분모형묘술실진도상여원시삼고도상지간적도상결구신식변화；위측량량도실진，우채용실진도상여삼고도상지간적차치도상중봉폐구역적능량함수래형량인안민감적도상량도신식。최후，채용3충표준도상수거고험증해평개방법적성능。실험결과표명，소제출적도상질량평개방법우우현유적도상평개표준。
In this paper, based on the assumption that human visual system(HVS) is sensitive for image structures (edges) and local luminance (light stimulation), we propose a new perceptual image quality assessment (PIQA) metric based on total variation(TV) model in spatial domain. In the proposed metric, the TV’s comparison between a distorted image and its reference image is applied to measure the extent of the loss of the image structural information. As a complementary part to measure the distortion, the energy of enclosed regions in a difference image is used to measure the missing luminance information which is sensitive to human visual system. The performance of the proposed metric is validated with an extensive subjective database. The results show that the proposed metric outperforms the state-of-the-art of image quality assessment metrics.