[1]崔力,浩明.基于视觉注意机制的图像质量评价[J].东南大学学报(自然科学版),2012,42(5):854-858.[doi:10.3969/j.issn.1001-0505.2012.05.011]
 Cui Li,Hao Ming.Image quality assessment based on visual attention mechanism[J].Journal of Southeast University (Natural Science Edition),2012,42(5):854-858.[doi:10.3969/j.issn.1001-0505.2012.05.011]
点击复制

基于视觉注意机制的图像质量评价()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
42
期数:
2012年第5期
页码:
854-858
栏目:
信息与通信工程
出版日期:
2012-09-20

文章信息/Info

Title:
Image quality assessment based on visual attention mechanism
作者:
崔力1 浩明2
1 西北工业大学电子信息学院,西安 710072; 2 西安邮电大学通信与信息工程学院,西安 710121
Author(s):
Cui Li1 Hao Ming2
1 School of Electronic and Information, Northwestern Polytechnic University, Xi’an 710072, China
2 School of Telecommunication and Information Engineering, Xi’an University of Posts and Telecommunications, Xi’an 710121, China
关键词:
图像质量 视觉感知 视觉注意 边缘检测
Keywords:
image quality visual perception visual attention edge detection
分类号:
TN911.73
DOI:
10.3969/j.issn.1001-0505.2012.05.011
摘要:
提出了一种基于人眼视觉注意机制的图像质量评价算法(VAIQM).首先,对输入图像进行预处理,以便分别在细节和轮廓2个层次上测量局部视觉畸变.然后,在视觉显著、中等显著和不显著区域分别计算区域相似度,并将其合并为图像整体的细节和轮廓相似度.最后,将细节和轮廓相似度合并为图像整体质量指标. 实验结果表明,在A57,IVC,TID2008,Tomaya-MICT,LIVE,CSIQ和WIQ 七种数据库上,VAIQM算法的整体性能均优于结构相似性(SSIM)算法及其扩展版本MS-SSIM算法, 能更好地体现主客观评价的一致性.MS-SSIM算法需要利用多分辨率分析工具将待测图像分解为若干子带,其计算复杂度远高于VAIQM算法.此外,VAIQM算法在这7种数据库上的性能波动均较小,显示出较高的鲁棒性.
Abstract:
An image quality assessment algorithm based on visual attention mechanism(VAIQM)is proposed. Firstly, input images are preprocessed to measure local visual distortion at both the detail and the coarse scales. Then, region similarities are computed in the high, middle and low visual saliency regions, and are merged into the detail and the coarse similarities of images. Finally, a whole image quality index is derived by combining the detail similarity and the coarse similarity. The experimental results show that on the public available image databases of A57,IVC,TID2008, Tomaya-MICT, LIVE,CSIQ and WIQ, the overall performance of the VAIQM is better than those of the structural similarity metric(SSIM)and its multi-scale extension(MS-SSIM). The consistency between subjective ratings and objective evaluation can be embodied better by the VAIQM. Considering that the MS-SSIM need decompose images into a set of subbands by using multi-resolution analysis tools, its computational complexity is much higher than that of the VAIQM. In addition, the performance fluctuation of the VAIQM on these 7 databases is small, exhibiting high robustness.

参考文献/References:

[1] Wang Z,Bovik A C.Modern image quality assessment[M].San Rafael,CA,USA:Morgan & Claypool,2006.
[2] Vankata N D,Kite T D,Geisler W S,et al.Image quality assessment based on a degradation model[J].IEEE Trans on Image Processing,2000,9(4):636-650.
[3] Chandler D M,Hemami S S.VSNR:a wavelet-based visual signal-to-noise ratio for natural images [J].IEEE Trans on Image Processing,2007,16(9):2284-2298.
[4] Wang Z,Bovik A C,Sheikh H R,et al.Image quality assessment:from error visibility to structural similarity[J].IEEE Trans on Image Processing,2004,13(4):600-612.
[5] Wang Z,Bovik A C.A universal image quality index[J].IEEE Signal Processing Letters,2002,9(3):81-84.
[6] Wang Z,Simoncelli E P,Bovik A C.Multi-scale structural similarity for image quality assessment[C] //Proceedings of the 37th Asilomar Conference on Signals,Systems and Computers.New York,USA,2003:1398-1402.
[7] Itti L,Koch C,Niebur E.A model of saliency-based visual attention of rapid scene analysis [J].IEEE Trans on Pattern Analysis and Machine Intelligence,1998,20(11):1254-1259.
[8] Chandler D M,Hemami S S.A57 image quality assessment database [EB/OL].(2007)[2012-01-02].http://foulard.ece.cornell.edu/dmc27/vsnr/vsnr.html.
[9] Ninassi A,Callet P L,Autrusseau F.IVC image quality assessment database[EB/OL].(2005)[2012-01-02].http://www2.irccyn.ec-nantes.fr/ivcdb/.
[10] Ponomarenko N,Lukin V,Zelensky A,et al.TID2008—a database for evaluation of full reference visual quality assessment metrics[J].Advances of Modern Radioelectronics,2009,10:30-45.
[11] Horita H,Shibata K,Kawayoke Y,et al.Tomaya-MICT image quality evaluation database[EB/OL].(2008)[2012-01-02].http://mict.eng.u-toyama.ac.jp/mictdb.html.
[12] Sheikh H R,Wang Z,Cormack L,et al.LIVE image quality assessment database release 2 [EB/OL].(2006)[2012-01-02].http://live.ece.utexas.edu/research/Quality/.
[13] Larson E C,Chandler D M.Categorical image quality(CSIQ)database [EB/OL].(2010)[2012-01-02].http://vision.okstate.edu/?loc=csiq.
[14] Engelke U,Kusuma T M,Zepernick H J.Wireless imaging quality(WIQ)database [EB/OL].(2009)[2011-10-02].http://www.bth.se/tek/rcg.nsf/pages/wiq-db.

备注/Memo

备注/Memo:
作者简介: 崔力(1980—),男,博士,讲师,l.cui@nwpu.edu.cn.
基金项目: 留学人员科技活动项目择优资助经费资助项目、陕西省自然科学基金资助项目(2011JQ8038)、西北工业大学基础研究基金资助项目(JC201014)、西北工业大学E之星青年基金资助项目.
引文格式: 崔力,浩明.基于视觉注意机制的图像质量评价[J].东南大学学报:自然科学版,2012,42(5):854-858. [doi:10.3969/j.issn.1001-0505.2012.05.011]
更新日期/Last Update: 2012-09-20