液晶与显示Issue(6)：992-999,8.DOI:10.3788/YJYXS20153006.0992
基于 Riesz 变换的结构相似度图像质量评价方法
Image quality assessment method via Riesz-transform based structural similarity
摘要
Abstract
Various distortions will be introduced to images during different image processing proce-dures,and the assessment of image quality has become a hot topic.According to the fact that the tra-ditional pixel-difference statistics-based PSNR method and structural similarity method cannot corre-late well with human subjective evaluation,a novel image quality assessment method via Riesz-Trans-form based structural similarity is proposed.The method firstly applies 1st-order Riesz-Transform and 2nd-order Riesz Transform to the reference image and distorted image,and 5 groups of corre-sponding features maps are obtained to produce 5 similarity maps and 5 weighting maps.Then the average-method fusion is performed to get the final similarity map and weighting map.Lastly,the lu-minance comparison of the original reference image and distorted image is considered to get the final image quality index.The experiments on the LIVE database indicate that the proposed method has high prediction accuracy and consistency on all 5 distortion types.It also outperforms the SSIM method under cross-distortion conditions and the PLCC value and SROCC value reach 0.948 2 and 0.953 2 respectively.Compared with other state-of-the-art methods,the proposed method owns good predictive performance,which indicates better consistency with human subjective perception.关键词
图像质量/结构相似度/Riesz 变换/特征图Key words
image quality/structural similarity/Riesz-Transform/feature map分类
信息技术与安全科学引用本文复制引用
卢彦飞,张涛..基于 Riesz 变换的结构相似度图像质量评价方法[J].液晶与显示,2015,(6):992-999,8.基金项目
国家自然科学基金项目(No.61201117,No.61301042) （No.61201117,No.61301042）
国家重大科学仪器设备开发专项(No.2011YQ040082) （No.2011YQ040082）
国家科技支撑计划(No.2012BA113B04) （No.2012BA113B04）
江苏省自然基金项目(No.BK2012189) Supported by National Natural Science Foundation of China(No.61201117,No.61301042) （No.BK2012189）
National Key Scien-tific Instrument and Equipment Development Project(No.2011YQ040082) （No.2011YQ040082）
National Key Technology Support Program(No.2012BA113B04) （No.2012BA113B04）
Natural Science Foundation of Jiangsu Province(No.BK2012189) （No.BK2012189）
