可控金字塔分解的立体图像质量评价方法
发布时间：2018-10-04 20:41
【摘要】：基于最小能量误差得到左右视图的视差图,分别对左、右视图和视差图进行4尺度、12个方向的可控金字塔分解,每一幅图像可得到1条高频子带和48条方向子带。对左、右视图分解后相对应的48对方向子带进行二元广义高斯分布拟合,提取其形状参数和尺度参数,并提取所有方向子带的跨尺度相关性、空间相关性等特征信息,将这些特征输入支持向量回归(SVR)训练预测得到立体图像质量评分。结果表明该质量评价模型在LIVE 3D数据库上的性能指标斯皮尔曼等级相关系数(SROCC)、线性皮尔逊相关系数(CC)均在0.93以上,与人类的主观评价具有较好的一致性。
[Abstract]:Based on the minimum energy error, the parallax graphs of left and right views are obtained, and the left, right and parallax images are decomposed with 4 scales and 12 directions respectively. One high frequency subband and 48 directional subbands can be obtained for each image. After decomposing the left and right view, 48 opposite direction sub-bands are fitted with binary generalized Gao Si distribution, and the shape parameters and scale parameters are extracted, and the cross-scale correlation, spatial correlation and other characteristic information of all directional sub-bands are extracted. These features are input into support vector regression (SVR) training to predict stereo image quality. The results show that the Spelman grade correlation coefficient (SROCC), linear Pearson correlation coefficient (CC) of the quality evaluation model in LIVE 3D database is above 0.93, which is in good agreement with human subjective evaluation.
【作者单位】： 江南大学物联网工程学院轻工过程先进控制教育部重点实验室;安徽省明光市第三中学;
【基金】：国家自然科学基金,61170120~~
【分类号】：TP391.41
[Abstract]:Based on the minimum energy error, the parallax graphs of left and right views are obtained, and the left, right and parallax images are decomposed with 4 scales and 12 directions respectively. One high frequency subband and 48 directional subbands can be obtained for each image. After decomposing the left and right view, 48 opposite direction sub-bands are fitted with binary generalized Gao Si distribution, and the shape parameters and scale parameters are extracted, and the cross-scale correlation, spatial correlation and other characteristic information of all directional sub-bands are extracted. These features are input into support vector regression (SVR) training to predict stereo image quality. The results show that the Spelman grade correlation coefficient (SROCC), linear Pearson correlation coefficient (CC) of the quality evaluation model in LIVE 3D database is above 0.93, which is in good agreement with human subjective evaluation.
【作者单位】： 江南大学物联网工程学院轻工过程先进控制教育部重点实验室;安徽省明光市第三中学;
【基金】：国家自然科学基金,61170120~~
【分类号】：TP391.41
【相似文献】
相关期刊论文 前10条
1 韩伟;;日本立体图像技术近十年的回顾与前瞻[J];有线电视技术;2011年07期
2 杨s，
本文编号：2251814
本文链接：https://www.wllwen.com/kejilunwen/ruanjiangongchenglunwen/2251814.html
