计算机科学 ›› 2014, Vol. 41 ›› Issue (6): 287-290.doi: 10.11896/j.issn.1002-137X.2014.06.057
桑庆兵,梁狄林,吴小俊,李朝锋
SANG Qing-bing,LIANG Di-lin,WU Xiao-jun and LI Chao-feng
摘要： 传统的梯度结构相似度算法(GSSIM)简单地将各子块GSSIM的平均值作为整幅图像的质量评估值,忽略了人眼对图像不同失真区域的视觉灵敏度不同的特点。针对此问题,提出了一种基于膨胀和图像块分类的加权梯度结构相似度图像质量评价方法(WGSSIM)。该方法首先将失真图像划分为两个区域:边缘膨胀区域和平滑区域；然后将失真图像划分成8×8的图像块,根据失真区域将图像块区分为边缘膨胀块与平滑块两类；最后对不同类型图像块之间的GSSIM值赋予不同的权值,计算得到整幅图像的WGSSIM。实验表明,该方法在3个数据库上的评价结果稳定、合理,更加符合人眼视觉系统特性,评价结果与主观评价有很好的一致性。
| [1] Wang Z,Wu G,Sheikh H R,et al．Quality-aware images [J]．IEEE Transactions on Image Processing,2006,15(6):1680-1689 [2] Wang Z,Bovik A C,Li G．Why is image quality assessment so difficult?[C]∥IEEE International Conference on Acoustics,Speech,and Signal Processing．Orlando,Florida,USA,2002,4:3313-3316 [3] 孔繁锵.结合HVS和相似性度量的图像质量评价测度[J]．中国图形图象学报,2011,16(7):1184-1191 [4] Nill N B,Bouzas B H．Objective image quality measure derived digital image power spectra[J]．IEEE signal processing letters,2002,0(9):388-392 [5] Wang Z,Bovik A C,Sheikh H R,et al．Image quality assessment:From error visibility tostructural similarity [J].IEEE Transactions on Image Processing,2004,3(4):600-612 [6] 杨春玲,何流,魏毅,等.基于图像块分类的加权结构相似度[J].华南理工大学学报:自然科学版,2009,37(1):42-47 [7] 杨春玲,陈冠豪,谢胜利．基于梯度信息的图像质量评判方法的研究[J].电子学报,2007,35(7):1313-1317 [8] 楼斌,严晓浪．基于NSS和HVS的图像质量评价方法研究[D].杭州:浙江大学电气学院,2009 [9] Li C,Bovik A C．Three-component weighted structural similarity index[C]∥SPIE Electronic Imaging,International Society for Optics and Photonics．2009:72420Q-1-9 [10] Thung K H,Paramesran R,Lim C L．Content-based image qua-lity metric using similarity measure of moment vectors[J]．Pattern Recognition,2012,45(6):2193-2204 [11] Gao X,Lu W,Tao D,et al．Image quality assessment based on multiscale geometric analysis[J]．IEEE Transactions on Image Processing,2009,18(7):1409-1423 [12] 孙玉宝,费选,等．基于Contourlet的图像感知质量评价[J].电子学报,2011,9(3):649-655 [13] Sheikh H R,Wang Z,Cormack L,et al．LIVE Image QualityAssessment Database Release2[EB/OL]．http://live.ece.utexas.edu/research/quality [14] Image Coding and Analysis Laboratory,Oklahoma State University:Categorical Subjective Image Quality[EB/OL]．http://vision.okstate.edu/csiq/ [15] Ninassi A,Le Callet P,Autrusseau F．Pseudo no reference image quality metric using perceptual data hiding[C]∥Electronic Imaging,International Society for Optics and Photonics．2006:60570G-1-12 [16] Sheikh H R,Sabir M F,Bovik A C．A statistical evaluation of recent full reference image quality assessment algorithms[J]．IEEE Transactions on Image Processing,2006,15(11):3440-3451 |
| No related articles found! |
|
||
首页