光学技术, 2017, 43 (1): 25, 网络出版: 2017-02-23  

一种基于图像融合的无参考立体图像质量评价方法

A objective quality assessment method for no reference stereo image based on image fusion
作者单位
江南大学 物联网工程与技术学院, 江苏 无锡 214000
摘要
提出了一种基于图像融合的立体图像质量评价方法。通过对立体图像的左右视图进行图像融合生成一幅彩色图像, 融合算法采用主成分分析(PCA), 使用归一化互相关(NCC)视差图算法, 生成了对应的视差图; 对融合图像和视差图分别进行归一化亮度系数和谱能量参数的提取, 作为支持向量回归(SVR)的输入数据, 在经过充分的训练后对立体图像的质量评分进行预测。在LIVE 3D立体图像数据库上的实验结果表明, 提出的算法优于最新的无参考立体图像质量评价方法, 与人类的主观评价具有较好的一致性。
Abstract
A method based on image fusion is proposed. Through the left and right view images of a stereo pair, a pair of color image is generated based on principal component analysis (PCA) image fusion. A normalized cross correlation (NCC) algorithm is used to generate the parallax image. The normalized intensity coefficient and spectral energy feature extraction of the fusion image and the parallax image are extracted as features. The stereo image quality score is obtained by support vector regression (SVR) training. In live 3D image database of experimental results show that the algorithm outperforms the latest no reference stereo image quality assessment methods, and has good consistency with human subjective evaluation.
参考文献

[1] HUR N, LEE H, LEE G S, et al. 3dDTV broadcasting and distribution system[J]. IEEE Transaction on Broadcasting, 2011,57(2): 395-407.

[2] KIM B, HAHM S J, KANG J, et al. World’s first hybrid 3DTV broadcasting experiment[C].IEEE lnternational Symposium on Broadband Multimedia Systems and Broadcasting, 2012: 1-5.

[3] MOORTHY A K, SU C-C, MITTAL A, et al. Subjective evaluation of stereoscopic image quality[J].Signal Processing : Image Communication, 2013,28(8): 870-883.

[4] 刘玄玄, 王晓红, 章婷.一种基于视觉底层特征的图像质量评价方法[J].光学技术, 2015 ,41(3): 280-284.

    LIU Xuanxuan, WANG Xiaohong, et al. A method of image quality assessment based on visual low-level features[J].Optical Technique ,2015,41(3): 280-284.

[5] CHEN M J, CORMACK L K, BOVIK A C, et al. No-reference quality assessment of natural stereopairs[J]. IEEE Trans. Image Process, 2013, 22(9): 3379-3391.

[6] SHAO Feng, LIN Weisi, WANG Shanshan, et al. Blind image quality assessment for stereoscopic images using binocular guided quality lookup and visual codebook[J]. IEEE Transaction On Broadcasting, 2015,61(2): 54-165.

[7] RYU S, KIM D H, SOHN K, Et al. Stereoscopic image quality metric based on binocular perception model[C]. in Proc. IEEE Int. Conf. Image Process, Orlando, 2012 : 609-612.

[8] 刘姗姗, 郁梅, 王颖.基于小波高频的立体图像质量评价[J] .光学技术, 2015 ,41(5): 445-450.

    LIU Shanshan, YU Mei, WANG Ying. Stereo image quality assessment based on wavelet transform[J]. Optical Technique, 2015, 41(5): 445-450.

[9] MITTAL A, MOORTHY A K, BOVIK A C, et al. Making image quality assessment robust[C]. Signals, Systems and Computers (ASILOMAR), Pacific Grove, 2012 : 1718-1722.

[10] LIU Lixiong, LIU Bao, HUANG Hua, et al. No-reference image quality assessment based on spatial and spectral entropies[J].Signal Processing: Image Communication ,2014,29: 856-863.

[11] 桑庆兵, 仉静.彩色立体图像质量评价方法[J]. 计算机应用, 2015, 35( 3) : 816-820.

    SANG Qingbing, ZHANG Jing, et al. Quality assessment method of color stereoscopic images[J]. Journal of Computer Applications,2015,35(3): 816-820.

[12] 黄真宝, 陈阳. 图像匹配中NCC 算法的一种快速实现方法[J]. 信息化研究, 2011, 37( 2) : 48-52.

    HUANG Zhenbao, CHEN Yang, et al. A fast method for NCC algorithm in image matching[J].Informatization Research,2011,37(2): 48-52.

[13] HUANG Zhenbao, CHEN Yang. A fast method for NCC algorithm in image matching [J]. Information Research, 2011, 37(2) : 48-52.

[14] RUDERMAN D L. The statistics of natural images[J]. Network: Computation in Neural Systems, 1994, 5 (4) : 517-548.

[15] MOORTHY A K, BOVIK A C , Statistics of natural image distortions [C]. IEEE 2010 International Conference on Acoustics Speech and Signal Processing ( ICASSP), 2010 : 962-965.

[16] SHARIFI K, LEON-GARCIA A. Estimation of shape parameter for generalized Gaussian distributions in subband decompositions of video[J]. IEEE Transactions on Circuits and Systems for Video Technology, 1995, 5 ( 1) : 52-56.

[17] LASMAR N E, STITOU Y, BERTHOUMIEU Y. Multiscale skewed heavy tailed model for texture analysis[C]. IEEE 2009 the 16th IEEE International Conference on Image Processing(ICIP), 2009: 2281-2284.

[18] HOSKING J R M. L-moments: Analysis and estimation of distributions using linear combinations of order statistics[J]. Jour. Royal Stat. Soc., 1990: 105-124.

[19] GREENWOOD J A, LANDWEHR J M, MATALAS N C, et al. Probability weighted moments: Definition and relation to parameters of several distributions express able in inverse form[J].Water Resources Res., 1979 , 15: 1049-1054.

[20] LONGBOTHAM H G, BOVIK A C. Theory of order statistic filters and their relationship to linear FIR filters[J]. IEEE Trans. Acous., Speech and Sig. Proc, 1989, 37(2) : 275-287.

[21] WANG Z, BOVIK A C, SHEIKH H R, et al. Image quality assessment: from error visibility to structural similarity[J]. IEEE Trans. Image Process, 2004,13(4) : 600-612.

[22] MOORTHY A K, BOVIK A C. Visual importance pooling for image quality assessment[J]. IEEE Select Top Signal Process, 2009, 3(2): 193-201.

[23] SHEIKH H R, BOVIK A C. Image information and visual quality[J]. IEEE Trans. Image Process, 2006,15(2): 430-444.

[24] 桑庆兵, 李朝锋, 吴小俊. 基于灰度共生矩阵的无参考模糊图像质量评价方法[J. 模式识别与人工智能, 2013, 26( 5) : 492-497.

    SANG Qingbing, LI Chaofeng, WU Xiaojun, et al. No-reference blurred image quality assessment based on gray level co-occurrence matrix[J]. Pattern Recognition and Artificial Intelligence | Patt Recog Artif Intell,2013,26(5): 492-497.

[25]

    WANG Z, BOVIK A C, SHEIKH H R, et al. Image quality assessment: From error visibility to structural similarity[J]. IEEE Trans. Image Process, 2004, 13(4): 600-612.

[26] MITTAL A, MOORTHY A K, BOVIK A C. Blind/referenceless image spatial quality evaluator[J]. IEEE Trans. Image Process, 2012 ,19( 2): 75-78.

[27] BENOIT A, LE.CALLET P,CAMPISI P, et al. Quality assessment of stereoscopic images[J]. Image Video Process,2009,2008: 1-13.

李苗苗, 桑庆兵. 一种基于图像融合的无参考立体图像质量评价方法[J]. 光学技术, 2017, 43(1): 25. LI Miaomiao, SANG Qingbing. A objective quality assessment method for no reference stereo image based on image fusion[J]. Optical Technique, 2017, 43(1): 25.

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!