CAJ | 학술논문

基于结构相似度(SSIM)的图像质量评价方法简单高效,准确性较高,评价性能优于峰值信噪比(PNSR)和均方误差( MSE),但SSIM模型不能较好地评价严重失真和交叉失真类型的图像。文中提出了一种改进的基于结构相似度的图像质量评价方法( HSSIM),该方法将直方图信息作为图像的主要结构信息,根据人眼视觉特性,利用直方图集中度来表示图像模糊度,最终计算得到图像的结构相似度值。实验结果表明,HSSIM比SSIM模型更符合人眼视觉系统特性,能更好地评价失真图像的质量。
기우결구상사도(SSIM)적도상질량평개방법간단고효,준학성교고,평개성능우우봉치신조비(PNSR)화균방오차( MSE),단SSIM모형불능교호지평개엄중실진화교차실진류형적도상。문중제출료일충개진적기우결구상사도적도상질량평개방법( HSSIM),해방법장직방도신식작위도상적주요결구신식,근거인안시각특성,이용직방도집중도래표시도상모호도,최종계산득도도상적결구상사도치。실험결과표명,HSSIM비SSIM모형경부합인안시각계통특성,능경호지평개실진도상적질량。
SSIM is an image quality assessment algorithm with the advantage of simplicity,high efficiency and better consistence. Its eval-uation of performance is better than PNSR and MSE,however,it often fails when assessing badly distorted or cross distorted images. In this paper,an improved image quality assessment algorithm based on structural similarity ( HSSIM) is proposed,which takes the histo-gram concentration as the main structural information of an image,according to the human visual characteristics,using histogram concen-tration to calculate the fuzzy degree of the image,obtaining the structure similarity value of the image finally. Experimental results show that,compared with the SSIM model,the proposed HSSIM model is more consistent with human visual system and can assess the quality of fault images more precisely.