基于小波包分解的无参考立体图像质量评价
|
摘要
立体图像质量评价在立体图像处理领域中应用广泛.基于小波包分解的精细分辨率,提出了一种全新的无参考立体图像质量评价算法.选取合值图和差值图作为融合图来评估立体图像,首先,对立体图像对进行小波包分解,基于双眼竞争和双眼抑制原理,将分解后的左右视图进行融合得到合值图和差值图.然后,分别在融合图上提取自然场景统计(NSS)特征和信息熵;另外,考虑到左右视图之间的内在相关联系,提取结构相似度特征.最后,运用支持向量回归(SVR)来建立感知特征和主观分数模型并预测得到客观评价分数.采用该算法在LIVE 3D立体图像数据库上进行测试,实验结果表明,该算法与人眼主观评价结果一致性较高,优于当前主流的立体图像质量评价算法,符合人眼视觉感知特性.
Stereoscopic image quality evaluation is widely employed in the field of stereo image processing.Based on accurate resolution of wavelet-packet,a novel algorithm for no-reference stereoscopic image quality assessment is proposed.It evaluates stereo image quality via fusion map,which consists of cyclopean map and difference map.First,the stereo image pair is decomposed by wavelet-packet,and afterwards the decomposed left and right views are fused to obtain cyclopean map and difference map based on the principle of binocular rivalry and binocular suppression.Then,Natural Scene Statistics(NSS)features and information entropy are extracted on the fusion map;besides,the structural similarity feature is extracted by taking into account the internal relations between the left and right views.Finally,the Support Vector Regression(SVR)is used to establish model between the perception features and subjective scores,which can predict the objective evaluation score.The experimental results on LIVE 3Dimage databases show that the proposed algorithm has high consistency with the subjective evaluation results,and it outperforms state-of-the-art stereoscopic image quality assessment algorithms and is in accordance with the human visual perception characteristics.
Stereoscopic image quality evaluation is widely employed in the field of stereo image processing.Based on accurate resolution of wavelet-packet,a novel algorithm for no-reference stereoscopic image quality assessment is proposed.It evaluates stereo image quality via fusion map,which consists of cyclopean map and difference map.First,the stereo image pair is decomposed by wavelet-packet,and afterwards the decomposed left and right views are fused to obtain cyclopean map and difference map based on the principle of binocular rivalry and binocular suppression.Then,Natural Scene Statistics(NSS)features and information entropy are extracted on the fusion map;besides,the structural similarity feature is extracted by taking into account the internal relations between the left and right views.Finally,the Support Vector Regression(SVR)is used to establish model between the perception features and subjective scores,which can predict the objective evaluation score.The experimental results on LIVE 3Dimage databases show that the proposed algorithm has high consistency with the subjective evaluation results,and it outperforms state-of-the-art stereoscopic image quality assessment algorithms and is in accordance with the human visual perception characteristics.
引文
[1]周武杰,郁梅,蒋刚毅,等.基于视觉感知和零水印的部分参考立体图像质量评价模型[J].电子与信息学报,2012,34(8):1786-1792.ZHOU W J,YU M,JIANG G Y,et al.Reduced-reference quality assessment model of stereoscopic image based on visual perception zero-watermark[J].Journal of Electronics&Information Technology,2012,34(8):1786-1792.(In Chinese)
[2] WANG Z,SIMONCELLI E P,BOVIK A C.Multiscale structural similarity for image quality assessment[C]//Signals,Systems and Computers,USA:Conference Record of the Thirty-Seventh Asilomar Conference on IEEE,2004:1398-1402.
[3] MITTAL A,MOORTHY A K,BOVIK A C.No-reference image quality assessment in the spatial domain[J].IEEE Transactions on Image Processing,2012,21(12):4695-4708.
[4]侯春萍,刘月,岳广辉,等.沃尔什哈达玛变换域的无参考图像质量评价[J].湖南大学学报(自然科学版),2017,44(8):137-144.HOU C P,LIU Y,YUE G H,et al.No-reference image quality assessment on Walsh Hadamard transform domain[J].Journal of Hunan University(Nature Sciences),2017,44(8):137-144.(In Chinese)
[5] CHEN M J,SU C C,KWON D K,et al.Full-reference quality assessment of stereopairs accounting for rivalry[J].Signal Processing Image Communication,2013,28(9):1143-1155.
[6] CHEN M J,CORMACK L K,BOVIK A C.No-reference quality assessment of natural stereopairs[J].IEEE Transactions on Image Processing,2013,22(9):3379-3391.
[7]王珊珊,邵枫,蒋刚毅,等.基于双目能量响应的无参考立体图像质量评价[J].光电子·激光,2014(4):741-747.WANG S S,SHAO F,JIANG G Y,et al.No-reference image quality assessment based on binocular energy response[J],Journal of Optoelectronics·Laser,2014(4):741-747.(In Chinese)
[8] LIN Y H,WU J L.Quality assessment of stereoscopic 3Dimage compression by binocular integration behaviors[J].IEEE Transactions on Image Processing,2014,23(4):1527-1542.
[9] SHAO F,LIN W,GU S,et al.Perceptual full-reference quality assessment of stereoscopic images by considering binocular visual characteristics[J].IEEE Transactions on Image Processing,2013,22(5):1940-1953.
[10]GU K,ZHAI G,YANG X,et al.No-reference stereoscopic IQA approach:from nonlinear effect to parallax compensation[J].Journal of Electrical and Computer Engineering,2012(5):1-12.
[11]ZHOU W,ZHANG S,PAN T,et al.Blind 3Dimage quality assessment based on self-similarity of binocular features[J].Neurocomputing,2016,224:128-134.
[12]HADIZADEH H,BAJIC I V.No-reference image quality assessment using statistical wavelet-packet features[J].Pattern Recognition Letters,2016,80:144-149.
[13]FLEET D J,WAGNER H,HEEGER D J.Neural encoding of binocular disparity:energy models,position shifts and phase shifts[J].Vision Research,1996,36(12):1839-1857.
[14]王旭红,何怡刚.基于小波包和Elman神经网络的异步电机转子断条故障诊断方法[J].湖南大学学报(自然科学版),2010,37(5):45-48.WANG X H,HE Y G.Method of fault diagnosis for induction machine rotor broken bar based on wavelet package and elman neural network[J].Journal of Hunan University(Nature Sciences),2010,37(5):45-48.(In Chinese)
[15]MA L,WANG X,LIU Q,et al.Reorganized DCT-based image representation for reduced reference stereoscopic image quality assessment[J].Neurocomputing,2016,215(C):21-31.
[16]RUDERMAN D L.The statistics of natural images[J].Network Computation in Neural Systems,2009,5(4):517-548.
[17]LIU L,LIU B,HUANG H,et al.No-reference image quality assessment based on spatial and spectral entropies[J].Signal Processing Image Communication,2014,29(8):856-863.
[18]KOVESI P.Phase congruency detects corners and edges[C]//Pattern Recognition Society Conference.Australia:DICTA,2003:309-318.
[19]ANDREW A M.An introduction to support vector machines and other kernel-based learning methods[J].Kybernetes,2001,32(1):1-28.
[20] 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.
[21]SHAO F,LI K,LIN W,et al.Learning blind quality evaluator for stereoscopic images using joint sparse representation[J].IEEE Transactions on Multimedia,2016,18(10):210-220.
[2] WANG Z,SIMONCELLI E P,BOVIK A C.Multiscale structural similarity for image quality assessment[C]//Signals,Systems and Computers,USA:Conference Record of the Thirty-Seventh Asilomar Conference on IEEE,2004:1398-1402.
[3] MITTAL A,MOORTHY A K,BOVIK A C.No-reference image quality assessment in the spatial domain[J].IEEE Transactions on Image Processing,2012,21(12):4695-4708.
[4]侯春萍,刘月,岳广辉,等.沃尔什哈达玛变换域的无参考图像质量评价[J].湖南大学学报(自然科学版),2017,44(8):137-144.HOU C P,LIU Y,YUE G H,et al.No-reference image quality assessment on Walsh Hadamard transform domain[J].Journal of Hunan University(Nature Sciences),2017,44(8):137-144.(In Chinese)
[5] CHEN M J,SU C C,KWON D K,et al.Full-reference quality assessment of stereopairs accounting for rivalry[J].Signal Processing Image Communication,2013,28(9):1143-1155.
[6] CHEN M J,CORMACK L K,BOVIK A C.No-reference quality assessment of natural stereopairs[J].IEEE Transactions on Image Processing,2013,22(9):3379-3391.
[7]王珊珊,邵枫,蒋刚毅,等.基于双目能量响应的无参考立体图像质量评价[J].光电子·激光,2014(4):741-747.WANG S S,SHAO F,JIANG G Y,et al.No-reference image quality assessment based on binocular energy response[J],Journal of Optoelectronics·Laser,2014(4):741-747.(In Chinese)
[8] LIN Y H,WU J L.Quality assessment of stereoscopic 3Dimage compression by binocular integration behaviors[J].IEEE Transactions on Image Processing,2014,23(4):1527-1542.
[9] SHAO F,LIN W,GU S,et al.Perceptual full-reference quality assessment of stereoscopic images by considering binocular visual characteristics[J].IEEE Transactions on Image Processing,2013,22(5):1940-1953.
[10]GU K,ZHAI G,YANG X,et al.No-reference stereoscopic IQA approach:from nonlinear effect to parallax compensation[J].Journal of Electrical and Computer Engineering,2012(5):1-12.
[11]ZHOU W,ZHANG S,PAN T,et al.Blind 3Dimage quality assessment based on self-similarity of binocular features[J].Neurocomputing,2016,224:128-134.
[12]HADIZADEH H,BAJIC I V.No-reference image quality assessment using statistical wavelet-packet features[J].Pattern Recognition Letters,2016,80:144-149.
[13]FLEET D J,WAGNER H,HEEGER D J.Neural encoding of binocular disparity:energy models,position shifts and phase shifts[J].Vision Research,1996,36(12):1839-1857.
[14]王旭红,何怡刚.基于小波包和Elman神经网络的异步电机转子断条故障诊断方法[J].湖南大学学报(自然科学版),2010,37(5):45-48.WANG X H,HE Y G.Method of fault diagnosis for induction machine rotor broken bar based on wavelet package and elman neural network[J].Journal of Hunan University(Nature Sciences),2010,37(5):45-48.(In Chinese)
[15]MA L,WANG X,LIU Q,et al.Reorganized DCT-based image representation for reduced reference stereoscopic image quality assessment[J].Neurocomputing,2016,215(C):21-31.
[16]RUDERMAN D L.The statistics of natural images[J].Network Computation in Neural Systems,2009,5(4):517-548.
[17]LIU L,LIU B,HUANG H,et al.No-reference image quality assessment based on spatial and spectral entropies[J].Signal Processing Image Communication,2014,29(8):856-863.
[18]KOVESI P.Phase congruency detects corners and edges[C]//Pattern Recognition Society Conference.Australia:DICTA,2003:309-318.
[19]ANDREW A M.An introduction to support vector machines and other kernel-based learning methods[J].Kybernetes,2001,32(1):1-28.
[20] 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.
[21]SHAO F,LI K,LIN W,et al.Learning blind quality evaluator for stereoscopic images using joint sparse representation[J].IEEE Transactions on Multimedia,2016,18(10):210-220.