基于未匹配子带合成系数统计特性的立体图像质量评价算法
|
摘要
针对经典立体图像质量评价算法存在评价准确性低以及特征提取耗时较长的问题,提出一种基于未匹配子带合成系数统计特性的立体图像质量评价算法。首先,利用可控金字塔对左右视点图像进行多尺度、多方向的小波分解,并将左右视点图像在相同尺度、相同方向上未经视差图匹配的小波子带系数合成为子带合成系数。其次,提取小波子带合成系数中的统计分布特征,相同尺度相邻方向小波子带合成系数之间的相关性特征,以及相同方向相邻尺度子带合成系数之间的相关性特征。最后,利用所提取特征训练经典的支持向量回归模型,预测图像质量。在LIVE 3D和Waterloo IVC 3D数据库上的实验结果表明,与主流立体图像质量评价算法相比,本文算法在预测对称和非对称失真立体图像质量时都获得了更高的评价准确性。同时,由于子带合成系数的生成无需根据视差图进行匹配,算法执行效率高。
The classic stereoscopic image quality assessment(SIQA) methods usually have the problem of low prediction accuracy,and their feature extraction process is time consuming.To address these problems,this paper proposes a new no-reference SIQA algorithm based on synthetic coefficients of unmatched subbands(SCUSs).First,we employ the steerable pyramid to perform image decomposition over multi-scale and multi-orientation to generate multiple wavelet subbands for left and right views.Then,the corresponding wavelet subbands,which are at the same scale and the same orientation of the left and right images,are combined into SCUSs without using disparity map.After that,the distribution statistics of SCUSs,the correlation features between SCUSs at the same scale and neighboring orientations,and the correlation features between SCUSs at the same orientation and neighboring scales are extracted.Finally,we utilize the statistics extracted from SCUSs to train a support vector regression model to evaluate the quality of distorted images.Experiment results on LIVE 3 D and Waterloo IVC 3 D databases show that the proposed algorithm achieves higher prediction accuracy on both symmetrically and asymmetrically distorted images than the state-of-the-art SIQA algorithms.Meanwhile,since the SCUSs are combined without matching the left and right views by disparity map,the proposed algorithm can be implemented with high efficiency.
The classic stereoscopic image quality assessment(SIQA) methods usually have the problem of low prediction accuracy,and their feature extraction process is time consuming.To address these problems,this paper proposes a new no-reference SIQA algorithm based on synthetic coefficients of unmatched subbands(SCUSs).First,we employ the steerable pyramid to perform image decomposition over multi-scale and multi-orientation to generate multiple wavelet subbands for left and right views.Then,the corresponding wavelet subbands,which are at the same scale and the same orientation of the left and right images,are combined into SCUSs without using disparity map.After that,the distribution statistics of SCUSs,the correlation features between SCUSs at the same scale and neighboring orientations,and the correlation features between SCUSs at the same orientation and neighboring scales are extracted.Finally,we utilize the statistics extracted from SCUSs to train a support vector regression model to evaluate the quality of distorted images.Experiment results on LIVE 3 D and Waterloo IVC 3 D databases show that the proposed algorithm achieves higher prediction accuracy on both symmetrically and asymmetrically distorted images than the state-of-the-art SIQA algorithms.Meanwhile,since the SCUSs are combined without matching the left and right views by disparity map,the proposed algorithm can be implemented with high efficiency.
引文
[1] Su C C,Moorthy A K,Bovic A C.Visual quality assessment of stereoscopic image and video:challenges,advances,and future trends[M].In Visual Signal Quality Assessment,Springer,Cham,2015,185-212.
[2] XU Shao-ping,LIN Guan-xi,ZENG Xiao-xia,et al.Quality-aware feature extraction in the stereoscopic image quality assessment algorithm[J].Computer Engineering,2018,44(6):239-248.徐少平,林官喜,曾小霞,等.立体图像质量感知特征提取的研究进展[J].计算机工程,2018,44(6):239-248.
[3] Gu K,Jakhetiya V,Qiao J F,et al.Model-based referenceless quality metric of 3D synthesized images using local image description[J].IEEE Transactions on Image Processing.2018,27(1):394-405.
[4] Galkandage C,Calic J,Dogan S,et al.Stereoscopic video quality assessment using binocular energy[J].IEEE Journal of Selected Topics in Signal Processing,2017,11(1):102-112.
[5] Li F C,Shao F,Jiang Q P,et al.Local and global sparse representation for no-reference quality assessment of stereoscopic images[J].Information Sciences,2018,422:110-121.
[6] SHEN Li-bo,SHAO Feng,JIANG Gang-yi,et al.Full-reference image quality assessment for stereoscopic images based on extreme learning machine[J].Journal of Computer-Aided Design & Computer Graphics,2017,26(10):4818-4831.沈力波,邵枫,蒋刚毅,等.基于极限学习机的全参考立体图像质量评价[J].计算机辅助设计与图形学学报,2017,29(5):791-798.
[7] FU Zhen-qi,FEI Yan-jia,YANG Yan,et.al.No-feference stereoscopic image quality assessment based on deep feature learning[J].Joursnal of Optoelectronics·Laser,2018,29(5):545-552.富振奇,费延佳,杨艳.基于深层特征学习的无参考立体图像质量评价[J].光电子·激光,2018,29(5):545-552.
[8] CHEN Wan-ting,LIN Wen-chong,SHAO Feng.Stereosco-pic image quality assessment based on laminar cortical model[J].Journal of Optoelectronics·Laser,2017,28(5):529-537.陈婉婷,林文崇,邵枫.基于大脑层状皮质模型的立体图像质量评价[J].光电子·激光,2017,28(5):529-537.
[9] Yasakethu S L P,Hewage C T E R,Fernando W,et al.Quality analysis for 3D video using 2D video quality models[J].IEEE Transactions on Consumer Electronics,2008,54(4):1969-1976.
[10] Benoit A,Callet P L,Campisi P,et al.Quality assessment of stereoscopic images[C].Eurasip Journal on Image and Video Processing 2009,2008:659024.
[11] Bensalma R,Larabi M C.A perceptual metric for stereoscopic image quality assessment based on the binocular energy[J].Multidimensional Systems and Signal Processing,2013,24(2):281-316.
[12] 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.
[13] 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.
[14] Su C C,Cormack L K,Bovik A C.Oriented correlation models of distorted natural images with application to natural stereopair quality evaluation[J].IEEE Transactions on Image Processing,2015,24(5):1685-1699.
[15] TIAN Wei-jun,SHAO Feng,JIANG Gang-yi,et al.Blind image quality assessment for stereoscopic images via deep learning[J].Journal of Computer-Aided Design & Computer Graphics,2016,28(6):968-975.田维军,邵枫,蒋刚毅,等.基于深度学习的无参考立体图像质量评价[J].计算机辅助设计与图形学学报,2016,28(6):968-975.
[16] Liu L X,Liu B,Su C C.et al.Binocular spatial activity and reverse saliency driven no-reference stereopair quality assessment[J].Signal Processing Image Communication,2017,58(10):287-299.
[17] 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.
[18] Simoncelli E P,Freeman W T.The steerable pyramid:a flexible architecture for multi-scale derivative computation[C].IEEE International Conference on Image Processing,IEEE Computer Society,Washington,DC,USA,1995,3:3444.
[19] Wang J H,Rehman A,Zeng K,et al.Quality prediction of asymmetrically distorted stereoscopic 3D images[J].IEEE Transactions on Image Processing,2015,24(11):3400-3414.
[20] Wang J H,Zeng K,Wang Z.Quality prediction of asymmetrically distorted stereoscopic images from single views[C].IEEE International Conference on Multimedia and Expo,Chengdu,Sichuan,China,2014,14-18.
[21] 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.
[22] Wang Z,Bovik A C,Sheikh H R,et al.Image quality assessment:from error visibility to structural similarity[J].IEEE Transaction Image Processing,2004,13(4):600-612.
[23] Wang Z,Simoncelli E P,Bovik A C.Multiscale structural similarity for image quality assessment[C].IEEE 37th asilomar conference on Signals,Systems and Computers,Pacific Grove,C A,USA,2004,1398-1402.
[24] 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.
[2] XU Shao-ping,LIN Guan-xi,ZENG Xiao-xia,et al.Quality-aware feature extraction in the stereoscopic image quality assessment algorithm[J].Computer Engineering,2018,44(6):239-248.徐少平,林官喜,曾小霞,等.立体图像质量感知特征提取的研究进展[J].计算机工程,2018,44(6):239-248.
[3] Gu K,Jakhetiya V,Qiao J F,et al.Model-based referenceless quality metric of 3D synthesized images using local image description[J].IEEE Transactions on Image Processing.2018,27(1):394-405.
[4] Galkandage C,Calic J,Dogan S,et al.Stereoscopic video quality assessment using binocular energy[J].IEEE Journal of Selected Topics in Signal Processing,2017,11(1):102-112.
[5] Li F C,Shao F,Jiang Q P,et al.Local and global sparse representation for no-reference quality assessment of stereoscopic images[J].Information Sciences,2018,422:110-121.
[6] SHEN Li-bo,SHAO Feng,JIANG Gang-yi,et al.Full-reference image quality assessment for stereoscopic images based on extreme learning machine[J].Journal of Computer-Aided Design & Computer Graphics,2017,26(10):4818-4831.沈力波,邵枫,蒋刚毅,等.基于极限学习机的全参考立体图像质量评价[J].计算机辅助设计与图形学学报,2017,29(5):791-798.
[7] FU Zhen-qi,FEI Yan-jia,YANG Yan,et.al.No-feference stereoscopic image quality assessment based on deep feature learning[J].Joursnal of Optoelectronics·Laser,2018,29(5):545-552.富振奇,费延佳,杨艳.基于深层特征学习的无参考立体图像质量评价[J].光电子·激光,2018,29(5):545-552.
[8] CHEN Wan-ting,LIN Wen-chong,SHAO Feng.Stereosco-pic image quality assessment based on laminar cortical model[J].Journal of Optoelectronics·Laser,2017,28(5):529-537.陈婉婷,林文崇,邵枫.基于大脑层状皮质模型的立体图像质量评价[J].光电子·激光,2017,28(5):529-537.
[9] Yasakethu S L P,Hewage C T E R,Fernando W,et al.Quality analysis for 3D video using 2D video quality models[J].IEEE Transactions on Consumer Electronics,2008,54(4):1969-1976.
[10] Benoit A,Callet P L,Campisi P,et al.Quality assessment of stereoscopic images[C].Eurasip Journal on Image and Video Processing 2009,2008:659024.
[11] Bensalma R,Larabi M C.A perceptual metric for stereoscopic image quality assessment based on the binocular energy[J].Multidimensional Systems and Signal Processing,2013,24(2):281-316.
[12] 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.
[13] 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.
[14] Su C C,Cormack L K,Bovik A C.Oriented correlation models of distorted natural images with application to natural stereopair quality evaluation[J].IEEE Transactions on Image Processing,2015,24(5):1685-1699.
[15] TIAN Wei-jun,SHAO Feng,JIANG Gang-yi,et al.Blind image quality assessment for stereoscopic images via deep learning[J].Journal of Computer-Aided Design & Computer Graphics,2016,28(6):968-975.田维军,邵枫,蒋刚毅,等.基于深度学习的无参考立体图像质量评价[J].计算机辅助设计与图形学学报,2016,28(6):968-975.
[16] Liu L X,Liu B,Su C C.et al.Binocular spatial activity and reverse saliency driven no-reference stereopair quality assessment[J].Signal Processing Image Communication,2017,58(10):287-299.
[17] 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.
[18] Simoncelli E P,Freeman W T.The steerable pyramid:a flexible architecture for multi-scale derivative computation[C].IEEE International Conference on Image Processing,IEEE Computer Society,Washington,DC,USA,1995,3:3444.
[19] Wang J H,Rehman A,Zeng K,et al.Quality prediction of asymmetrically distorted stereoscopic 3D images[J].IEEE Transactions on Image Processing,2015,24(11):3400-3414.
[20] Wang J H,Zeng K,Wang Z.Quality prediction of asymmetrically distorted stereoscopic images from single views[C].IEEE International Conference on Multimedia and Expo,Chengdu,Sichuan,China,2014,14-18.
[21] 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.
[22] Wang Z,Bovik A C,Sheikh H R,et al.Image quality assessment:from error visibility to structural similarity[J].IEEE Transaction Image Processing,2004,13(4):600-612.
[23] Wang Z,Simoncelli E P,Bovik A C.Multiscale structural similarity for image quality assessment[C].IEEE 37th asilomar conference on Signals,Systems and Computers,Pacific Grove,C A,USA,2004,1398-1402.
[24] 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.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |