基于Contourlet变换的无参考立体图像质量评价

李永生; 桑庆兵

光学技术, 2016, 42 (6): 538, 网络出版: 2016-12-23

基于Contourlet变换的无参考立体图像质量评价

No-reference quality assessment for stereoscopic images based on Contourlet transform

论文大纲

李永生 ^*桑庆兵

作者单位

江南大学物联网工程学院, 江苏无锡 214122

摘要

立体图像的景物生动逼真, 给人一种身临其境的全新视觉享受, 但在制作、存储和传输过程中往往会产生失真。为了评价立体图像的质量优劣, 提出了一种基于轮廓波(Contourlet)变换的无参考立体图像质量评价算法。通过对失真的左、右图像分别进行主成分分析(PCA)融合来生成新的融合图像, 并使用基于SSIM(Structural Similarity)立体匹配算法生成视差图和匹配差值图, 然后对上述三张图片进行Contourlet变换, 再然后使用自定义的高频能量指标并结合边缘强度和信息熵, 最后将得到的特征输入支持向量回归(Support Vector Regression,SVR)模型中学习, 得出质量评价分数。该方法在德克萨斯大学公布的立体图像库中进行了验证, 线性相关系数和斯皮尔曼相关系数在Phase I库中可高达0.957和0.947, 在Phase II库中也可高达0.944和0.934, 与主观评价吻合度很高, 优于最新的一些评价方法。

Abstract

Stereo images are vivid and lifelike, which give people a new visual enjoyment, but in the process of production, storage and transmission the distortion is often introduced. In order to evaluate the quality of stereo images, a new algorithm for quality evaluation of no-reference stereo images is presented, which is based on Contourlet transform. First, PCA image fusion is used to deal with the distortion image pairs to generate 2D images, and the Disparity Maps and Matching Difference Maps are generated by stereo matching algorithm based on SSIM(Structural Similarity). Then, the amplitude of Fourier transform, the average gradient, information entropy as features are extracted. Finally, the extracted features are put into the SVR(Support Vector Regression) model to predict image quality score. The method has been verified on the LIVE 3D Image Quality Database which is published by university of Texas respectively. The linear correlation coefficient and spearman rank order correlation coefficient can be as high as 0.957 and 0.947 respectively in Phase I database, and 0.944 and 0.934 in Phase II database. The results have a high degree of agreement with the subjective evaluation and are better than some of the latest evaluation methods.

参考文献

[1] 智研咨询集团.2015-2020年中国电影放映银幕市场深度调查及投资前景预测报告［EB/OL］.(2015-08).http:∥www.chyxx.com/research/201508/337711.html.

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

[3] CHEN M J, et al. Full-reference quality assessment of stereopairs accounting for rivalry［J］. Signal Processing: Image Communication, 2013, 28(9): 1143-1155.

[4] HEWAGE C, et al. Prediction of stereoscopic video quality using objective quality models of 2-D video［J］. Electronics letters, 2008, 44(16): 963-965.

[5] GORLEY P,et al. Stereoscopic image quality metrics and compression［C］∥Transactions on electronic imaging. International Society for Optics and Photonics,2008: 680305-680305-12.

[6] LOWE D G. Object recognition from local scale-invariant features［J］.IEEE 7th International Conference Transactions on Computer Vision,1999,2:1150-1157.

[7] FISCHLER M A,et al. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography［J］. Communications of the ACM, 1981, 24(6): 381-395.

[8] 刘姗姗,等. 基于小波高频的立体图像质量评价［J］. 光学技术, 2015,(5).

LIU S S,et al.Stereo image quality evaluation based on wavelet transform［J］.Optical Technique,2015, (5).

[9] CHEN M J,et al. No-reference quality assessment of natural stereopairs［J］. IEEE Transactions on Image Processing, 2013, 22(9): 3379-3391.

[10] SHAO F, et al. Using binocular feature combination for blind quality assessment of stereoscopic images［J］. IEEE Transactions on Signal Processing Letters, 2015, 22(10): 1548-1551.

[11] SU C C,et al. 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.

[12] DO M N,et al. The contourlet transform: an efficient directional multiresolution image representation［J］. IEEE Transactions on Image Processing, 2005, 14(12): 2091-2106.

[13] LIU M,et al. Image quality assessment using contourlet transform［J］. Optical Engineering, 2009, 48(10): 107201-107201-10.

[14] WANG X, et al. Natural image statistics based 3D reduced reference image quality assessment in contourlet domain［J］. Neuro computing, 2015, 151: 683-691.

[15] KLAUS A,et al. Segment-based stereo matching using belief propagation and a self-adapting dissimilarity measure［J］.IEEE 18th International Conference Transactions on Pattern Recognition, 2006, 3: 15-18.

[16] Laboratory for Image & Video Engineering. Image & video quality assessment at LIVE［EB/OL］.(2012-08).http:∥live.ece.utexas.edu/research/quality/live_3dimage.html.

李永生, 桑庆兵. 基于Contourlet变换的无参考立体图像质量评价[J]. 光学技术, 2016, 42(6): 538. LI Yongsheng, SANG Qingbing. No-reference quality assessment for stereoscopic images based on Contourlet transform[J]. Optical Technique, 2016, 42(6): 538.

基于Contourlet变换的无参考立体图像质量评价

关于本站 Cookie 的使用提示

全站搜索

基于Contourlet变换的无参考立体图像质量评价

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索