CAJ | 학술논문

图像质量的客观评价是图像处理领域中的一个重要分支，其评价指标可以作为一种测度或者准则用来校准图像处理系统，抑或用于图像处理算法的优化及参数的优选。鉴于人眼是图像的最终受体，而视觉注意机制在人眼观看图像过程中起到非常重要的作用。因此本文针对图像质量评价的基本问题，提出了一种新的基于视觉注意机制的仿生学图像质量评价算法。结合视觉注意机制形成的原理，利用高斯塔式分解将图像分解为不同的空域尺度，从而模拟人类视觉系统的多通道特性。采用对比敏感度函数对不同的空域尺度进行视觉感知滤波，然后利用人类视觉系统的中央-周边感受野特性与侧抑制机制对图像特征进行提取，进而利用该特征来捕捉由图像降质引起的视觉感知的差异。实验结果表明，本方法能较准确地反映人眼对图像质量的主观感受，且计算复杂度较低，性能优于同类评价算法。
도상질량적객관평개시도상처리영역중적일개중요분지，기평개지표가이작위일충측도혹자준칙용래교준도상처리계통，억혹용우도상처리산법적우화급삼수적우선。감우인안시도상적최종수체，이시각주의궤제재인안관간도상과정중기도비상중요적작용。인차본문침대도상질량평개적기본문제，제출료일충신적기우시각주의궤제적방생학도상질량평개산법。결합시각주의궤제형성적원리，이용고사탑식분해장도상분해위불동적공역척도，종이모의인류시각계통적다통도특성。채용대비민감도함수대불동적공역척도진행시각감지려파，연후이용인류시각계통적중앙-주변감수야특성여측억제궤제대도상특정진행제취，진이이용해특정래포착유도상강질인기적시각감지적차이。실험결과표명，본방법능교준학지반영인안대도상질량적주관감수，차계산복잡도교저，성능우우동류평개산법。
Image quality evaluation is to use some computational models to predict the quality of the specified image automatically and accurately. Since human eyes are ultimate receptor of images, it is better to mimic human visual system (HVS) to perceive the image quality. Based on the properties of the HVS, a novel bionic image quality metric (IQA) is proposed, which adopts several bionic characteristics, e.g. multi-channel decomposition, contrast sensitivity function, center-surround operation and lateral inhibition mechanism. Experimental results demonstrate that the performance of the proposed IQA method outperforms those of the existing methods.