Learning No-Reference Quality Assessment of Multiply and Singly Distorted Images with Big Data

Learning No-Reference Quality Assessment of Multiply and Singly Distorted Images with Big Data
复制标题

利用大数据学习多重和单一扭曲图像的无参考质量评估

DOI:
10.1109/tip.2019.2952010
复制
发表时间:
2019-11
影响因子:
10.6
通讯作者:
ler
ler
中科院分区:
计算机科学1区
文献类型:
--
作者:
Yi Zhang;Xuanqin Mou;Damon M. Ch;ler

文献摘要

参考文献

相似文献

以前的研究无参考(NR)质量评估的多重失真图像主要集中在三种失真类型(白色噪声,高斯模糊,JPEG压缩),而在实践中,图像可以被许多其他常见的失真,由于处理的各个阶段。虽然MUSIQUE(多重和单一失真图像质量估计)[Zhang等人,TIP 2018]是一种成功的NR算法,但这种方法仍限于三种失真类型。在本文中,我们将MUSIQUE扩展到MUSIQUE-II,以盲评估五种失真类型(白色噪声,高斯模糊,JPEG压缩,JPEG 2000压缩和对比度变化)及其组合的图像质量。建议MUSIQUE-II算法的基础上,其前身的分类和参数估计框架,使用更先进的模型和更全面的失真敏感功能。具体而言,MUSIQUE-II依赖于三层分类模型来识别19种失真类型。为了预测五个失真参数值,MUSIQUE-II提取额外的14个对比度特征,并采用多层概率加权规则。最后,MUSIQUE-II采用了一种新的最明显失真策略,根据三个分类模型的输出自适应地将五个质量分数联合收割机组合起来。在三个多失真和六个单失真图像质量数据库上的实验结果表明,MUSIQUE-II不仅在质量预测性能上有了很大的提高,而且与其他最先进的FR/NR.IQA算法相比,具有很强的竞争力。
Previous research on no-reference (NR) quality assessment of multiply-distorted images focused mainly on three distortion types (white noise, Gaussian blur, and JPEG compression), while in practice images can be contaminated by many other common distortions due to the various stages of processing. Although MUSIQUE (MUltiply- and Singly-distorted Image QUality Estimator) [Zhang et al., TIP 2018] is a successful NR algorithm, this approach is still limited to the three distortion types. In this paper, we extend MUSIQUE to MUSIQUE-II to blindly assess the quality of images corrupted by five distortion types (white noise, Gaussian blur, JPEG compression, JPEG2000 compression, and contrast change) and their combinations. The proposed MUSIQUE-II algorithm builds upon the classification and parameter-estimation framework of its predecessor by using more advanced models and a more comprehensive set of distortion-sensitive features. Specifically, MUSIQUE-II relies on a three-layer classification model to identify 19 distortion types. To predict the five distortion parameter values, MUSIQUE-II extracts an additional 14 contrast features and employs a multilayer probability-weighting rule. Finally, MUSIQUE-II employs a new most-apparent-distortion strategy to adaptively combine five quality scores based on outputs of three classification models. Experimental results tested on three multiply-distorted and six singly-distorted image quality databases show that MUSIQUE-II yields not only a substantial improvement in quality predictive performance as compared with its predecessor, but also highly competitive performance relative to other state-of-the-art FR/NR.IQA algorithms.
DOI: 10.1109/icassp.2016.7471841
发表时间: 2016-03
期刊: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
影响因子: --
作者:
Jie Fu;Hanli Wang;L. Zuo
通讯作者: Jie Fu;Hanli Wang;L. Zuo
DOI: 10.1109/tip.2005.859378
发表时间: 2006-02-01
影响因子: 10.6
作者:
Sheikh, HR;Bovik, AC
通讯作者: Bovik, AC
DOI: 10.1109/mmsp.1999.794137
发表时间: 1999
期刊: 1999 IEEE Third Workshop on Multimedia Signal Processing (Cat. No.99TH8451)
影响因子: --
作者:
S. Winkler
通讯作者: S. Winkler
DOI: 10.1109/cvpr.2013.133
发表时间: 2013-06
期刊: 2013 IEEE Conference on Computer Vision and Pattern Recognition
影响因子: --
作者:
Wufeng Xue;Lei Zhang;X. Mou
通讯作者: Wufeng Xue;Lei Zhang;X. Mou
具有内部生成机制的感知质量指标
DOI: --
发表时间: --
期刊: IEEE Trans. on Image Processing
影响因子: --
作者:
Jinjian Wu;Weisi Lin;Guangming Shi;Anmin Liu
通讯作者: Anmin Liu