Opinion-Unaware Blind Quality Assessment of Multiply and Singly Distorted Images via Distortion Parameter Estimation
Opinion-Unaware Blind Quality Assessment of Multiply and Singly Distorted Images via Distortion Parameter Estimation
复制标题
DOI：
10.1109/tip.2018.2857413
复制
发表时间：
2018-07
影响因子：
10.6
通讯作者：
Yi Zhang;D. Chandler
中科院分区：
文献类型：
--
作者：
Yi Zhang;D. Chandler
在过去的几十年里，已经开发了许多图像质量评估（IQA）算法来估计包含单一类型失真的图像的质量。尽管在实践中，图像可能会受到多重失真的污染，但先前对多重失真图像质量评估的研究非常有限。在本文中，我们提出了一种有效的算法，基于使用自然场景统计（NSS）特征预测失真参数来盲目评估多重和单失真图像的质量。我们的方法称为多重和单失真图像质量估计器 (MUSIQUE)，通过三个主要阶段进行操作。在第一阶段，采用两层分类模型来识别图像中可能存在的失真类型（即高斯模糊、JPEG压缩和白噪声）。在第二阶段，通过学习不同失真类型和组合的不同NSS特征，采用特定的回归模型来预测三个失真参数（即，用于高斯模糊的$\sigma _{G}$，用于JPEG压缩的$Q$，以及用于白噪声的$\bar {\sigma }_{N}$）。在最后阶段，根据质量映射曲线和最明显失真策略，将三个估计的失真参数值映射并组合成总体质量估计。在三个多重失真和七个单失真图像质量数据库上测试的实验结果表明，与其他最先进的 FR/NR IQA 算法相比，所提出的 MUSIQUE 算法可以实现更好/有竞争力的性能。
Over the past couple of decades, numerous image quality assessment (IQA) algorithms have been developed to estimate the quality of images that contain a single type of distortion. Although in practice, images can be contaminated by multiple distortions, previous research on the quality assessment of multiply distorted images is very limited. In this paper, we propose an efficient algorithm to blindly assess the quality of both multiply and singly distorted images based on predicting the distortion parameters using a bag of natural scene statistics (NSS) features. Our method, called MUltiply and Singly distorted Image QUality Estimator (MUSIQUE), operates via three main stages. In the first stage, a two-layer classification model is employed to identify the distortion types (i.e., Gaussian blur, JPEG compression, and white noise) that may exist in an image. In the second stage, specific regression models are employed to predict the three distortion parameters (i.e., $\sigma _{G}$ for Gaussian blur, $Q$ for JPEG compression, and $\bar {\sigma }_{N}$ for white noise) by learning the different NSS features for different distortion types and combinations. In the final stage, the three estimated distortion parameter values are mapped and combined into an overall quality estimate based on quality-mapping curves and the most-apparent-distortion strategy. Experimental results tested on three multiply distorted and seven singly distorted image quality databases demonstrate that the proposed MUSIQUE algorithm can achieve better/competitive performance as compared with other state-of-the-art FR/NR IQA algorithms.