基于信息理论的图像相似度测量方法
发布时间：2021-01-20 09:15
Image similarity or distortion assessment is fundamental to a broad range of applications throughout the field of image processing and machine vision. Many existing image similarity measures have been proposed to handle specific types of image distortions. Also, there are methods such as the classical structural similarity （SSIM） index that are applicable to a wider range of applications. Most of existing image similarity measures are based on statistical approaches. Image similarity measures th...
【文章来源】：华中师范大学湖北省 211工程院校 教育部直属院校
【文章页数】：114 页
【学位级别】：博士
【文章目录】：
Abstract
1 Introduction
1.0 Overview
1.1 Motivations
1.2 Objective
1.3 Contributions
1.4 Thesis Organization
2 Literature survey
2.1 Image Quality Assessment
2.2 Structural（statistical）Similarity Based Image Quality Assessment
2.2.1 The Structural Similarity（SSIM）Index
2.2.1.1 Multi-Scale SSIM
2.2.1.2 Complex Wavelet-SSIM
2.3 Information Theoretic Similarity Based Image Quality Assessment
2.3.1 Information Entropy and Uncertainty
2.3.2 Joint entropy
2.3.3 Mutual Information
2.3.4 Joint Histogram
2.4 An Application of Similarity:Face Recognition
2.4.1 Face Datasets
2.4.1.1 FERET
2.4.1.2 ORL
2.4.1.3 LFW
2.4.1.4 MOBIO
3 High-Performance Information-Theoretic Image Similarity Measures
3.0 Overview
3.1 First Proposed Framework（HSSIM）Based on Joint Histogram
3.1.1 The Test Environment of （HSSIM）
3.2 Second Proposed Framework （ISSIM） For Face Recognition Based on Joint Histogram
3.2.1 Recognition Confidence
3.2.2 Image Database
4 Results and Discussion
4.1 Tests on HSSIM with Image Quality Database
4.1.1 Performance of HSSIM under Gaussian Noise
4.1.2 Effects of Analysis Parameters
4.2 Tests ISSIM with Face Image Database
4.2.1 Testing
5 Conclusion and Future Work
5.1 Conclusion
5.2 Future work
References
List of Abbreviations & Symbols
Publications Associated with This work
ACKNOWLEDGEMENTS
Dedication
本文编号：2988782
【文章来源】：华中师范大学湖北省 211工程院校 教育部直属院校
【文章页数】：114 页
【学位级别】：博士
【文章目录】：
Abstract
1 Introduction
1.0 Overview
1.1 Motivations
1.2 Objective
1.3 Contributions
1.4 Thesis Organization
2 Literature survey
2.1 Image Quality Assessment
2.2 Structural（statistical）Similarity Based Image Quality Assessment
2.2.1 The Structural Similarity（SSIM）Index
2.2.1.1 Multi-Scale SSIM
2.2.1.2 Complex Wavelet-SSIM
2.3 Information Theoretic Similarity Based Image Quality Assessment
2.3.1 Information Entropy and Uncertainty
2.3.2 Joint entropy
2.3.3 Mutual Information
2.3.4 Joint Histogram
2.4 An Application of Similarity:Face Recognition
2.4.1 Face Datasets
2.4.1.1 FERET
2.4.1.2 ORL
2.4.1.3 LFW
2.4.1.4 MOBIO
3 High-Performance Information-Theoretic Image Similarity Measures
3.0 Overview
3.1 First Proposed Framework（HSSIM）Based on Joint Histogram
3.1.1 The Test Environment of （HSSIM）
3.2 Second Proposed Framework （ISSIM） For Face Recognition Based on Joint Histogram
3.2.1 Recognition Confidence
3.2.2 Image Database
4 Results and Discussion
4.1 Tests on HSSIM with Image Quality Database
4.1.1 Performance of HSSIM under Gaussian Noise
4.1.2 Effects of Analysis Parameters
4.2 Tests ISSIM with Face Image Database
4.2.1 Testing
5 Conclusion and Future Work
5.1 Conclusion
5.2 Future work
References
List of Abbreviations & Symbols
Publications Associated with This work
ACKNOWLEDGEMENTS
Dedication
本文编号：2988782
本文链接：https://www.wllwen.com/shoufeilunwen/xxkjbs/2988782.html
