Utilizing binocular vision to facilitate completely blind 3D image quality measurement
Utilizing binocular vision to facilitate completely blind 3D image quality measurement
复制标题
DOI：
10.1016/j.sigpro.2016.06.005
复制
发表时间：
2016-12
期刊：
影响因子：
--
通讯作者：
Wujie Zhou;Lu Yu;Weiwei Qiu;Ting Luo;Zhongpeng Wang;Ming-Wei Wu
中科院分区：
文献类型：
--
作者：
Wujie Zhou;Lu Yu;Weiwei Qiu;Ting Luo;Zhongpeng Wang;Ming-Wei Wu
在实际的三维(3D)应用领域，失真3D图像的感知质量的盲测量仍然是一个具有挑战性的研究课题。在本文中，我们提出了一种完全盲的3D图像质量度量(IQM)，它利用双目视觉机制来更好地与人的感知保持一致。本研究以双眼视觉的初级视皮层(V1)和高级视区(V2)的视觉加工为主要研究对象，以促进3D-IQM的盲化。此外，所提出的度量不需要失真样本或人类主观意见得分来进行训练。更具体地说，首先从原始自然3D图像语料库中提取区域V1和V2的双目质量预测特征。随后，从提取的特征中训练原始的多变量高斯(MVG)模型。最后，使用训练好的MVG模型，使用马氏距离来衡量失真的3D图像的质量。在两个公共基准3D数据库上的实验结果表明，与当前最新的IQM度量相比，该度量具有良好的预测性能。
In the field of practical three-dimensional (3D) applications, blind measurement of the perceptual quality of distorted 3D images remains a challenging research topic. In this paper, we propose a completely blind 3D image quality measurement (IQM) metric that utilizes a binocular vision mechanism to better align with human perception. As its primary focus, this study is inspired by the visual processing in the primary visual cortex (V1) and the higher visual areas (V2) of binocular vision to facilitate blind 3D-IQM. Furthermore, the proposed metric does not require distorted samples or human subjective opinion scores for training. More specifically, the binocular quality-predictive features of areas V1 and V2 are first extracted from a corpus of pristine natural 3D images. Subsequently, a pristine multivariate Gaussian (MVG) model is trained from the extracted features. Finally, with the trained MVG model, the quality of distorted 3D images is measured using a Mahalanobis distance. Experimental results using two public benchmark 3D databases show that in comparison with current state-of-the-art IQM metrics, the proposed metric achieves excellent prediction performance.