Blind Image Quality Measurement via Data-Driven Transform-Based Feature Enhancement
Blind Image Quality Measurement via Data-Driven Transform-Based Feature Enhancement
复制标题
通过数据驱动的基于变换的特征增强进行盲图像质量测量
DOI：
10.1109/tim.2022.3191661
复制
发表时间：
2022
影响因子：
5.6
通讯作者：
Shen Liquan
中科院分区：
文献类型：
--
作者：
Yang Chao;An Ping;Shen Liquan
盲图像质量测量（BIQM）试图在没有参考图像的情况下测量图像的感知质量。根据特征的类型，BIQM方法可以分为两类：手工特征和基于学习的特征。在本文中，我们提出了一种用于BIQM的数据驱动的基于变换的特征增强（DFE）方法，该方法将手工制作的特征的可移植性与基于学习的特征的高性能相结合。具体地说，我们首先从Karhunen-Loéve变换（KLT），相位一致性（PC）和梯度幅度（GM）系数中提取图像的结构特征，然后从局部归一化系数中提取自然场景统计（NSS）特征。然后，我们使用KLT作为特征增强过程，以增强结构和NSS特征，与Weibull分布和广义高斯分布（GGD）建模的变换系数在所有频带的分布作为质量感知特征。最后，采用支持向量回归（SVR）的特征映射到主观评分。所提出的方法已被比较有利的国家的最先进的BIQM方法在七个广泛使用的数据库上的人工和真实的失真类型，并实现了极具竞争力的性能。
Blind image quality measurement (BIQM) attempts to measure image perceptual quality in the absence of reference ones. Based on the types of features, BIQM methods can be divided into two categories: hand-crafted features and learning-based features. In this article, we present a data-driven transform-based feature enhancement (DFE) approach for BIQM that combines the portability of hand-crafted features with the high performance of learning-based features. Specifically, we first extract the image structural features from Karhunen–Loéve transform (KLT), phase congruency (PC), and gradient magnitude (GM) coefficients, and then natural scene statistics (NSS) feature from the local normalized coefficient. Then, we use KLT as feature enhancement process to enhance the structural and NSS features, with Weibull distribution and generalized Gaussian distribution (GGD) modeling the distributions of transform coefficient in all the frequency bands as quality-aware features. Finally, support vector regression (SVR) is adopted to map the features to subjective scores. The proposed method has been compared favorably with the state-of-the-art BIQM methods on seven widely used databases on both artificial and authentic distortion types and achieves highly competitive performance.