Please wait a minute...
浙江大学学报(工学版)
浙江大学学报(工学版)
自动化技术、电信技术     
基于CSF和仿射重建模型的噪声图像质量评价
崔光茫,冯华君,徐之海,李奇,陈跃庭
浙江大学 现代光学仪器重点实验室,浙江 杭州 310027
Image quality assessment method for noisy images based on CSF and affine reconstruction model
CUI Guang mang, FENG Hua jun, XU Zhi hai, LI Qi, CHEN Yue ting
State Key Laboratory of Optical Instrumentation, Zhejiang University, Hangzhou 310027, China
 全文: PDF(1692 KB)   HTML
摘要：

针对无参考噪声图像质量评价问题,提出基于视觉对比度敏感函数(CSF)和仿射重建模型的噪声图像质量评价方法.引入CSF对待评价噪声图像进行滤波,利用图像分块技术,建立基于最优化问题求解的仿射重建模型,得到图像信号成分,估计出残差信号图像.计算各分块的噪声强度点分布,选取噪声强度点数量分布最多的区间,最终的噪声图像质量评价算子由该强度区间内的所有强度点的均值计算得到.在LIVE、TID2008及CSIQ数据库上开展评价算法主客观一致性评估实验,与其他几种评价算法进行对比,比较算法客观评价性能的表现.实验结果表明,提出的算法具有很好的准确性和主客观评价一致性.
Abstract:

An image quality assessment method based on contrast sensitive function (CSF) and affine reconstruction model was proposed for no reference noisy image quality assessment. The visual contrast sensitivity function was introduced to apply the filtering process for noisy image. The image segmentation algorithm was utilized and the affine reconstruction model was applied to solve the optimal problem. Then image signal was obtained and the residual signal image was estimated from the input image and the signal image. The noise intensity sample of each block was calculated to select the interval with the most noise samples falling in. The final noise image assessment metric was obtained by the mean value of all the noise intensity samples belonging to the selected interval. Experiments were conducted on LIVE, TID2008 and CSIQ image data base in order to evaluate the subjective and objective consistency of the proposed method. The objective performances were assessed compared with other image quality assessment methods. Experimental results illustrate that the presented algorithm has a good performance on accuracy and subjective and objective consistency．
出版日期: 2016-03-31
:  TP 391  
基金资助:

国家自然科学基金资助项目(61178064).
通讯作者: 冯华君，男，教授，博导.ORCID：0000 0002 5606 6637.     E-mail: fenghj@zju.edu.cn
作者简介: 崔光茫(1989-)，男，博士生，从事光学成像、图像质量评价等的研究.ORCID：0000 0002 1997 6084. E-mail：nycgm@163.com
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　

引用本文:

崔光茫,冯华君,徐之海,李奇,陈跃庭. 基于CSF和仿射重建模型的噪声图像质量评价[J]. 浙江大学学报(工学版), 10.3785/j.issn.1008-973X.2016.01.021.

CUI Guang mang, FENG Hua jun, XU Zhi hai, LI Qi, CHEN Yue ting. Image quality assessment method for noisy images based on CSF and affine reconstruction model. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 10.3785/j.issn.1008-973X.2016.01.021.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2016.01.021    或    http://www.zjujournals.com/eng/CN/Y2016/V50/I1/144

［1］ BOVIK A C, WANG Zhou. Modern image quality assessment ［M］. New York: Morgan and Claypool, 2006．
［2］ SUTHAHARAN S. No reference visually signifcant blocking artifact metric for natural scene images ［J］. Signal Processing, 2009, 89(8): 1647-1652．
［3］ MARZILIANO P, DUFAUX F, WINKLER S, et al. Perceptual blur and ringing metrics: application to JPEG2000 ［J］. Signal Processing: Image Communication, 2004, 19(2): 163-172．
［4］ NARVEKAR N D, KARAM L J. A no reference image blur metric based on the cumulative probability of blur detection (CPBD) ［J］. IEEE Transactions on Image Processing, 2011, 20(9): 2678-2683．
［5］ CHEN Ming Jun, BOVIK A C. No reference image blur assessment using multi scale gradient ［J］. EURASIP Journal on Image and Video Processing, 2011, 2011(1): 111．
［6］ SAAD M A, BOVIK A C, CHARRIER C. A DCT statistics based blind image quality index ［J］. IEEE Signal Processing Letters, 2010, 17(6): 583-586．
［7］ GABARDA S, CRISTBAL G. Blind image quality assessment through anisotropy ［J］. Journal of the Optical Society of America A, 2007, 24(12): 42-51．
［8］ MOORTHY A K, BOVIK A C. Blind image quality assessment: from natural scene statistics to perceptual quality ［J］. IEEE Transactions on Image Processing, 2011, 20(12): 3350-3364．
［9］ BARLAND R, SAADANE A. Reference free quality metric for JPEG 2000 compressed images ［C］∥ International Symposium on Signal Processing and its Applications. Australia: IEEE, 2005, 1:351-354.
［10］ TONG Hang hang, LI Ming jing, ZHANG Hong jiang, et al. No reference quality assessment for JPEG2000 compressed images ［C］∥Proceeding of IEEE International Conference on Image Processing. Singapore: IEEE, 2004, 5: 3539-3542．
［11］ 张天煜,冯华君,徐之海,等. 基于强边缘宽度直方图的图像清晰度指标［J］. 浙江大学学报：工学版,2014, 48(2): 312-320．
ZHANG Tian yu, FENG Hua jun, XU Zhi hai, et al. Sharpness metric based on histogram of strong edge width ［J］. Journal of Zhejiang University: Engineering Science,2014, 48(2): 312-320．
［12］ PASTOR D. A theoretical result for processing signals that have unknown distributions and priors in white Gaussian noise ［J］. Computational Statistics and Data Analysis, 2008, 52(6): 3167-3186．
［13］ JIANG Ping, ZHANG Jian zhou. Fast and reliable noise estimation algorithm based on statistical hypothesis tests ［C］∥Visual Communications and Image Processing.San Diego : IEEE, 2012:1-5．
［14］ LIU Xin hao, TANAKA M, OKUTOMI M. Noise level estimation using weak textured patches of a single noisy image ［C］∥19th IEEE International Conference on Image Processing. Orlando: IEEE , 2012: 665-668．
［15］ KARUNASEKA S A, KINGSBURG N G. A distortion measure for blocking artifacts in image based on human visual sensitivity ［J］. IEEE Transactions on Image Processing, 1995, 4(6): 713-724．
［16］张量,王怡影,明军,等. 基于掩盖效应图像质量评价方法的研究［J］. 合肥工业大学学报：自然科学版,2013, 36(6): 696-699．
ZHANG Liang, WANG Yi ying, MING Jun, et al. Research on image quality evaluation method based on masking effect ［J］. Journal of Hefei University of Technology: Natural Science, 2013, 36(6): 696-699．
［17］ MIYAHARA M, KOTANI K, ALGAZI V. Objective picture quality scale (PQS) for image coding ［J］. IEEE Transactions on Communications, 1998, 46(9): 12151226．
［18］ VINCENT L, SOILLE P. Watersheds in digital spaces: an efficient algorithm based on immersion simulations ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1991, 13(6): 583-598．
［19］ SHEIKH H R, ZHOU Wang, CORMACK L, et al. LIVE image quality assessment database release 2 ［EB/OL］. ［2006 03 15］. http:∥ live.eoe.utexas.edu/research/quality/．
［20］ 王宇庆,朱明. 评价彩色图像质量的四元数矩阵最大奇异值方法［J］. 光学精密工程,2013, 21(2): 469-478．
WANG Yu qing, ZHU Ming. Maximum singular value method of quaternion matrix for evaluating color image quality ［J］. Optics and Precision Engineering, 2013, 21(2): 469478．
［21］ 王勇,王宇庆,赵晓晖.图像质量客观评价的复数矩阵结构相似度方法［J］.仪器仪表学报, 2014, 35(5): 1118-1129．
WANG Yong, WANG Yu qing, ZHAO Xiao hui. Objective image quality assessment based on complex matrix structure similarity ［J］. Chinese Journal of Scientific Instrument, 2014, 35(5): 1118-1129．
［22］ FERZIL R, KARAM L J. A no reference objective image sharpness metric based on the notion of just noticeable blur (JNB) ［J］. IEEE Transactions on Image Processing, 2009, 18(4): 717-728．
［23］ WANG Zhou, BOVIK A C, SHEIKH H R, et al. Image quality assessment: from error visibility to structural similarity ［J］. IEEE Transactions on Image Processing, 2004, 13(4): 600-612．
［24］ MOORTHY A K, BOVIK A C. A two step framework for constructing blind image quality indices ［J］. IEEE Signal Processing Letters, 2010, 17(5): 513-516．
［25］ 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．
［26］ ERIC C L, DAMON M C. Most apparent distortion: full reference image quality assessment and the role of strategy ［J］. Journal of Electron Imaging, 2010, 19(1): 143-153．
[1] 何雪军, 王进, 陆国栋, 刘振宇, 陈立, 金晶. 基于三角网切片及碰撞检测的工业机器人三维头像雕刻[J]. 浙江大学学报(工学版), 2017, 51(6): 1104-1110.
[2] 王桦, 韩同阳, 周可. 公安情报中基于关键图谱的群体发现算法[J]. 浙江大学学报(工学版), 2017, 51(6): 1173-1180.
[3] 尤海辉, 马增益, 唐义军, 王月兰, 郑林, 俞钟, 吉澄军. 循环流化床入炉垃圾热值软测量[J]. 浙江大学学报(工学版), 2017, 51(6): 1163-1172.
[4] 毕晓君, 王佳荟. 基于混合学习策略的教与学优化算法[J]. 浙江大学学报(工学版), 2017, 51(5): 1024-1031.
[5] 黄正宇, 蒋鑫龙, 刘军发, 陈益强, 谷洋. 基于融合特征的半监督流形约束定位方法[J]. 浙江大学学报(工学版), 2017, 51(4): 655-662.
[6] 蒋鑫龙, 陈益强, 刘军发, 忽丽莎, 沈建飞. 面向自闭症患者社交距离认知的可穿戴系统[J]. 浙江大学学报(工学版), 2017, 51(4): 637-647.
[7] 王亮, 於志文, 郭斌. 基于双层多粒度知识发现的移动轨迹预测模型[J]. 浙江大学学报(工学版), 2017, 51(4): 669-674.
[8] 廖苗, 赵于前, 曾业战, 黄忠朝, 张丙奎, 邹北骥. 基于支持向量机和椭圆拟合的细胞图像自动分割[J]. 浙江大学学报(工学版), 2017, 51(4): 722-728.
[9] 穆晶晶, 赵昕玥, 何再兴, 张树有. 基于凹凸变换与圆周拟合的重叠气泡轮廓重构[J]. 浙江大学学报(工学版), 2017, 51(4): 714-721.
[10] 戴彩艳, 陈崚, 李斌, 陈伯伦. 复杂网络中的抽样链接预测[J]. 浙江大学学报(工学版), 2017, 51(3): 554-561.
[11] 刘磊, 杨鹏, 刘作军. 采用多核相关向量机的人体步态识别[J]. 浙江大学学报(工学版), 2017, 51(3): 562-571.
[12] 郭梦丽, 达飞鹏, 邓星, 盖绍彦. 基于关键点和局部特征的三维人脸识别[J]. 浙江大学学报(工学版), 2017, 51(3): 584-589.
[13] 王海军, 葛红娟, 张圣燕. 基于核协同表示的快速目标跟踪算法[J]. 浙江大学学报(工学版), 2017, 51(2): 399-407.
[14] 张亚楠, 陈德运, 王莹洁, 刘宇鹏. 基于增量图形模式匹配的动态冷启动推荐方法[J]. 浙江大学学报(工学版), 2017, 51(2): 408-415.
[15] 刘宇鹏, 乔秀明, 赵石磊, 马春光. 统计机器翻译中大规模特征的深度融合[J]. 浙江大学学报(工学版), 2017, 51(1): 46-56.