期刊
IEEE TRANSACTIONS ON MULTIMEDIA
卷 23, 期 -, 页码 4259-4271出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMM.2020.3039382
关键词
Feature extraction; Tensors; Dictionaries; Image color analysis; Image quality; Image coding; Mathematical model; Screen content image; image quality assessment; no-reference; macro-micro modeling; dictionary learning
资金
- Natural Science Foundation of China [61671412, 61871247, 61931022]
- Natural Science Foundation of Zhejiang Province [LY19F010002, LY21F010014]
- Commonweal Projects of Zhejiang Province [LGN20F010001]
- Natural Science Foundation of Ningbo, China [2018A610053, 202003N4323]
- General Scientific Research Project of Zhejiang Education Department [Y201941122]
- Ningbo Municipal Projects for Leading and Top Talents [NBLJ201801006]
- Fundamental Research Funds for Zhejiang Provincial Colleges and Universities
- School-level Research and Innovation Team of Zhejiang Wanli University
This article proposes a novel blind quality assessment method for SCIs based on macro-micro modeling of tensor domain dictionary. By utilizing tensor decomposition to preserve color information and establishing a macro-micro model to characterize micro and macro features in the target dictionary space, the method provides a systematic mathematical interpretation for feature extraction, enhancing the effectiveness of feature aggregation.
Screen content images (SCIs) have been rapidly and widely applied in interactive multimedia applications. The problem of quality assessment for SCIs is an interesting research topic. Most of the existing methods use subjective and independent features in gray domain to predict the image quality, which cannot comprehensively characterize the image properties or lack unified mathematical explanation for SCIs. To address these problems, we propose a novel blind quality assessment method based on macro-micro modeling of tensor domain dictionary for SCIs in this article. In the proposed method, the tensor decomposition is explored first to avoid the loss of color information, and then a target dictionary is learned more effectively with the principal components. Furthermore, a macro-micro model is established to characterize the micro and macro features in the target dictionary space, which can provide a systematic mathematical interpretation for feature extraction. For the micro features, a log-normal pooling scheme is designed to enhance the effectiveness of feature aggregation by analyzing the particularity of the statistical distribution of sparse codes. Additionally, the statistical properties are mainly discussed and studied based on the Bernoulli law of large numbers, and then a reliable macro feature is generated to describe the relationship between the statistical distribution and quality degradation of SCIs. Experimental results determined by using three public SCI databases show that the proposed method can perform better than relevant existing methods in the prediction of the visual quality of SCIs, especially in terms of the generalization for distortion type and interpretability for feature generation.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据