Skip to main content
Log in

No-reference noisy image quality assessment incorporating features of entropy, gradient, and kurtosis

结合熵、 梯度、 峰度特征的无参考噪声图像质量评价

  • Research Article
  • Published:
Frontiers of Information Technology & Electronic Engineering Aims and scope Submit manuscript

Abstract

Noise is the most common type of image distortion affecting human visual perception. In this paper, we propose a no-reference image quality assessment (IQA) method for noisy images incorporating the features of entropy, gradient, and kurtosis. Specifically, image noise estimation is conducted in the discrete cosine transform domain based on skewness invariance. In the principal component analysis domain, kurtosis feature is obtained by statistically counting the significant differences between images with and without noise. In addition, both the consistency between the entropy and kurtosis features and the subjective scores are improved by combining them with the gradient coefficient. Support vector regression is applied to map all extracted features into an integrated scoring system. The proposed method is evaluated in three mainstream databases (i.e., LIVE, TID2013, and CSIQ), and the results demonstrate the superiority of the proposed method according to the Pearson linear correlation coefficient which is the most significant indicator in IQA.

摘要

噪声是影响人类视觉感知最常见的图像失真类型. 本文提出一种基于熵、 梯度和峰度特征的无参考图像质量评估方法. 具体来说, 基于偏度不变性在离散余弦变换域进行图像噪声估计, 进一步计算得到熵特征. 在主成分分析变换域, 通过统计有噪声图像与无噪声图像之间的显著差异得到峰度特征. 此外, 将熵和峰度特征与梯度系数结合, 提高熵和峰度特征与主观得分之间的一致性. 通过不同方向的滤波器对图像进行梯度特征提取, 最后支持向量回归将所有提取的特征映射到综合评分系统中. 为验证算法性能, 在3个主流数据库 (即LIVE、 TID2013以及CSIQ) 中对该方法进行评价. 实验结果验证了该方法的优越性, 尤其是在反映预测精度的皮尔逊线性相关系数方面的突出性能.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

References

Download references

Author information

Authors and Affiliations

Authors

Contributions

Heng YAO designed the algorithms. Ben MA drafted the manuscript. Mian ZOU processed the data. Dong XU and Jincao YAO supervised the algorithms, and revised and finalized the paper.

Corresponding authors

Correspondence to Dong Xu  (徐栋) or Jincao Yao  (姚劲草).

Ethics declarations

Heng YAO, Ben MA, Mian ZOU, Dong XU, and Jincao YAO declare that they have no conflict of interest.

Additional information

Project supported by the National Natural Science Foundation of China (No. 61702332) and the Zhejiang Provincial Natural Science Foundation of China (Nos. LZY21F030001 and LSD19H180001)

Heng YAO, first author of this invited paper, received his BS degree from Hefei University of Technology, China, in 2004, his MS degree from Shanghai Normal University, China, in 2008, and his PhD degree in Signal and Information Processing from Shanghai University, China, in 2012. He is currently an associate professor at University of Shanghai for Science and Technology. His research interests include multimedia security, image processing, and pattern recognition. He has published more than 40 peer-reviewed papers in international journals.

Dong XU, corresponding author of this invited paper, received his BS and MS degrees in Medical Imaging from Southeast University and Zhejiang University in 2002 and 2008, respectively. In 2011, he received his PhD degree in Clinical Specialty of Integrated Traditional Chinese and Western Medicine from Zhejiang Chinese Medical University. He is now a professor at the Institute of Basic Medicine and Cancer (IBMC), Chinese Academy of Sciences and Cancer Hospital of the University of Chinese Academy of Sciences (Zhejiang Cancer Hospital). His current research interests include medical image processing, machine learning, radiomics, and medical imaging diagnosis of tumor.

Jincao YAO, corresponding author of this invited paper, received his BS degree in Computer and Information Science from Hefei University of Technology in 2004, and his MS degree in Signal Processing from Shanghai Normal University in 2007. In 2017, he received his PhD degree in Signal and Information Processing at the College of Information Science and Electronic Engineering, Zhejiang University, China. He is now an imaging physicist at the IBMC, Chinese Academy of Sciences and Cancer Hospital of the University of Chinese Academy of Sciences (Zhejiang Cancer Hospital). His current research interests include machine learning, computer vision, medical image recognition, radiomics, and shape-driven techniques in image processing.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yao, H., Ma, B., Zou, M. et al. No-reference noisy image quality assessment incorporating features of entropy, gradient, and kurtosis. Front Inform Technol Electron Eng 22, 1565–1582 (2021). https://doi.org/10.1631/FITEE.2000716

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1631/FITEE.2000716

Keywords

关键词

CLC number