請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/96966完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 丁建均 | zh_TW |
| dc.contributor.advisor | Jian-Jiun Ding | en |
| dc.contributor.author | 李沅罡 | zh_TW |
| dc.contributor.author | Yuan-Kang Lee | en |
| dc.date.accessioned | 2025-02-25T16:16:09Z | - |
| dc.date.available | 2025-02-26 | - |
| dc.date.copyright | 2025-02-25 | - |
| dc.date.issued | 2025 | - |
| dc.date.submitted | 2025-02-11 | - |
| dc.identifier.citation | [1] Wang, Zhou, et al. "Image quality assessment: from error visibility to structural similarity." IEEE transactions on image processing 13.4 (2004): 600-612.
[2] Sheikh, Hamid R., and Alan C. Bovik. "Image information and visual quality." IEEE Transactions on image processing 15.2 (2006): 430-444. [3] Li, Chaofeng, and Alan C. Bovik. "Content-partitioned structural similarity index for image quality assessment." Signal Processing: Image Communication 25.7 (2010): 517-526. [4] Zhang, Lin, et al. "FSIM: A feature similarity index for image quality assessment." IEEE transactions on Image Processing20.8 (2011): 2378-2386. [5] Xue, Wufeng, et al. "Gradient magnitude similarity deviation: A highly efficient perceptual image quality index." IEEE transactions on image processing 23.2 (2013): 684-695. [6] Liu, Hao, et al. "Enhanced image no‐reference quality assessment based on colour space distribution." IET Image Processing 14.5 (2020): 807-817. [7] Soundararajan, Rajiv, and Alan C. Bovik. "RRED indices: Reduced reference entropic differencing for image quality assessment." IEEE Transactions on Image Processing 21.2 (2011): 517-526. [8] Bampis, Christos G., et al. "SpEED-QA: Spatial efficient entropic differencing for image and video quality." IEEE signal processing letters 24.9 (2017): 1333-1337. [9] Mittal, Anish, Anush Krishna Moorthy, and Alan Conrad Bovik. "No-reference image quality assessment in the spatial domain." IEEE Transactions on image processing 21.12 (2012): 4695-4708. [10] Moorthy, Anush Krishna, and Alan Conrad Bovik. "Blind image quality assessment: From natural scene statistics to perceptual quality." IEEE transactions on Image Processing20.12 (2011): 3350-3364. [11] Mittal, Anish, Rajiv Soundararajan, and Alan C. Bovik. "Making a “completely blind” image quality analyzer." IEEE Signal processing letters 20.3 (2012): 209-212. [12] Ye, Peng, and David Doermann. "No-reference image quality assessment using visual codebooks." IEEE Transactions on Image Processing 21.7 (2012): 3129-3138. [13] Min, Xiongkuo, et al. "Blind image quality estimation via distortion aggravation." IEEE Transactions on Broadcasting64.2 (2018): 508-517. [14] Zeng, Hui, Lei Zhang, and Alan C. Bovik. "A probabilistic quality representation approach to deep blind image quality prediction." arXiv preprint arXiv:1708.08190 (2017). [15] Bosse, Sebastian, et al. "Deep neural networks for no-reference and full-reference image quality assessment." IEEE Transactions on image processing 27.1 (2017): 206-219. [16] Kim, Jongyoo, Anh-Duc Nguyen, and Sanghoon Lee. "Deep CNN-based blind image quality predictor." IEEE transactions on neural networks and learning systems 30.1 (2018): 11-24. [17] Zhu, Hancheng, et al. "MetaIQA: Deep meta-learning for no-reference image quality assessment." Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020. [18] Liu, Yutao, et al. "Unsupervised blind image quality evaluation via statistical measurements of structure, naturalness, and perception." IEEE Transactions on Circuits and Systems for Video Technology 30.4 (2019): 929-943. 59 [19] Hu, Runze, et al. "Toward a no-reference quality metric for camera-captured images.” IEEE Transactions on Cybernetics53.6 (2021): 3651-3664. [20] Liu, Ziming, et al. "Kan: Kolmogorov-arnold networks." arXiv preprint arXiv:2404.19756 (2024). [21] Ponomarenko, N., et al. "Color image database for evaluation of image quality metrics." 2008 IEEE 10th workshop on multimedia signal processing. IEEE, 2008. [22] Ponomarenko, Nikolay, et al. "A new color image database TID2013: Innovations and results." Advanced Concepts for Intelligent Vision Systems: 15th International Conference, ACIVS 2013, Poznań, Poland, October 28-31, 2013. Proceedings 15. Springer International Publishing, 2013. [23] Lin, Hanhe, Vlad Hosu, and Dietmar Saupe. "KADID-10k: A large-scale artificially distorted IQA database." 2019 Eleventh International Conference on Quality of Multimedia Experience (QoMEX). IEEE, 2019. [24] Fang, Yuming, et al. "No-reference quality assessment of contrast-distorted images based on natural scene statistics." IEEE Signal Processing Letters 22.7 (2014): 838-842. [25] Zhang, Lin, Lei Zhang, and Alan C. Bovik. "A feature-enriched completely blind image quality evaluator." IEEE Transactions on Image Processing 24.8 (2015): 2579-2591. [26] Zhou, Wei, et al. "No-reference quality assessment for 360-degree images by analysis of multifrequency information and local-global naturalness." IEEE Transactions on Circuits and Systems for Video Technology 32.4 (2021): 1778-1791. [27] Zhang, Min, et al. "No reference image quality assessment based on local binary pattern statistics." 2013 Visual Communications and Image Processing (VCIP). IEEE, 2013.60 [28] Zhang, Min, et al. "Blind image quality assessment using the joint statistics of generalized local binary pattern." IEEE Signal Processing Letters 22.2 (2014): 207-210. [29] Li, Qiaohong, Weisi Lin, and Yuming Fang. "No-reference quality assessment for multiply-distorted images in gradient domain." IEEE Signal Processing Letters 23.4 (2016): 541-545. [30] Rezaie, Farshad, Mohammad Sadegh Helfroush, and Habibollah Danyali. "No-reference image quality assessment using local binary pattern in the wavelet domain." Multimedia Tools and Applications 77 (2018): 2529-2541. [31] Brandão, Tomás, and Maria Paula Queluz. "No-reference image quality assessment based on DCT domain statistics." Signal processing 88.4 (2008): 822-833. [32] Hadizadeh, Hadi, and Ivan V. Bajić. "No-reference image quality assessment using statistical wavelet-packet features." Pattern Recognition Letters 80 (2016): 144-149. [33] Hachicha, Walid, et al. "No-reference stereo image quality assessment based on joint wavelet decomposition and statistical models." Signal Processing: Image Communication54 (2017): 107-117. [34] Bosse, Sebastian, et al. "Deep neural networks for no-reference and full-reference image quality assessment." IEEE Transactions on image processing 27.1 (2017): 206-219. [35] Ke, Junjie, et al. "Musiq: Multi-scale image quality transformer." Proceedings of the IEEE/CVF international conference on computer vision. 2021. [36] Zhu, Hancheng, et al. "MetaIQA: Deep meta-learning for no-reference image quality assessment." Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020. 61 [37] Zhu, Hancheng, et al. "Generalizable no-reference image quality assessment via deep meta-learning." IEEE Transactions on Circuits and Systems for Video Technology32.3 (2021): 1048-1060. [38] Huang, Guang-Bin, Qin-Yu Zhu, and Chee-Kheong Siew. "Extreme learning machine: theory and applications." Neurocomputing 70.1-3 (2006): 489-501. [39] Huang, Guang-Bin, et al. "Extreme learning machine for regression and multiclass classification." IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) 42.2 (2011): 513-529. [40] Bouzerdoum, Abdesselam, A. Havstad, and A. Beghdadi. "Image quality assessment using a neural network approach." Proceedings of the Fourth IEEE International Symposium on Signal Processing and Information Technology, 2004. IEEE, 2004. [41] Li, Yuming, et al. "No-reference image quality assessment with deep convolutional neural networks." 2016 IEEE International Conference on Digital Signal Processing (DSP). IEEE, 2016. [42] Zhong, Jiafeng, et al. "Research on a Multidimensional Digital Printing Image Quality Evaluation Method Based on MLP Neural Network Regression." Applied Sciences (2076-3417)14.14 (2024). [43] Abu Doush, Iyad, et al. "Archive-based coronavirus herd immunity algorithm for optimizing weights in neural networks." Neural Computing and Applications 35.21 (2023): 15923-15941. [44] Liu, Min, et al. "Blind image quality assessment for noise." 2014 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting. IEEE, 2014. [45] Friston, Karl. "The free-energy principle: a unified brain theory?." Nature reviews neuroscience 11.2 (2010): 127-138. [46] Jähne, Bernd, Horst Haussecker, and Peter Geissler, eds. Handbook of computer vision and applications. Vol. 2. San Diego: Academic Press, 1999. [47] Huang, Xiaotong, et al. "Blind noisy image quality assessment using block homogeneity." Computers & Electrical Engineering40.3 (2014): 796-807. [48] Itti, Laurent, Christof Koch, and Ernst Niebur. "A model of saliency-based visual attention for rapid scene analysis." IEEE Transactions on pattern analysis and machine intelligence20.11 (1998): 1254-1259. [49] Zhai, Guangtao, et al. "A dual-model approach to blind quality assessment of noisy images." APSIPA Transactions on Signal and Information Processing 4 (2015): e4. [50] Srivastava, Anuj, et al. "On advances in statistical modeling of natural images." Journal of mathematical imaging and vision18 (2003): 17-33. [51] Geisler, Wilson S. "Visual perception and the statistical properties of natural scenes." Annu. Rev. Psychol. 59.1 (2008): 167-192. [52] Oszust, Mariusz. "No-reference quality assessment of noisy images with local features and visual saliency models." Information Sciences 482 (2019): 334-349. [53] Bay, Herbert. "Surf: Speeded up robust features." Computer Vision—ECCV (2006). [54] Zhang, Lin, Ying Shen, and Hongyu Li. "VSI: A visual saliency-induced index for perceptual image quality assessment." IEEE Transactions on Image processing 23.10 (2014): 4270-4281. [55] Deng, Chenwei, et al. "Blind noisy image quality assessment using sub-band kurtosis." IEEE transactions on cybernetics50.3 (2019): 1146-1156. [56] Su, Shaolin, et al. "Blindly assess image quality in the wild guided by a self-adaptive hyper network." Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020. [57] He, Kaiming, et al. "Deep residual learning for image recognition." Proceedings of the IEEE conference on computer vision and pattern recognition. 2016. [58] Li, Dingquan, et al. "Which has better visual quality: The clear blue sky or a blurry animal?." IEEE Transactions on Multimedia 21.5 (2018): 1221-1234. [59] Zhou, Zihan, et al. "Deep Blind Image Quality Assessment Using Dynamic Neural Model with Dual-order Statistics." IEEE Transactions on Circuits and Systems for Video Technology (2024). [60] Pruchnik, Bartosz Czesław, Piotr Adam Putek, and Teodor Paweł Gotszalk. "Wavelet-based information theory in quantitative assessment of AFM images’ quality." Scientific Reports 14.1 (2024): 3996. [61] BAXTER, D. "Development of the I3A CPIQ spatial metric." Electron. Imaging 8293 (2012): 1-12. [62] Pimpalkhute, Varad A., et al. "Digital image noise estimation using DWT coefficients." IEEE transactions on image processing 30 (2021): 1962-1972. [63] Kodak Lossless Color Image Suite, https://r0k.us/graphics/kodak/ [64] Bergstra, James, et al. "Algorithms for hyper-parameter optimization." Advances in neural information processing systems 24 (2011). [65] Chen, Guangyong, Fengyuan Zhu, and Pheng Ann Heng. "An efficient statistical method for image noise level estimation." Proceedings of the IEEE International Conference on Computer Vision. 2015. [66] Wang, Zhou, et al. "Image quality assessment: from error visibility to structural similarity." IEEE transactions on image processing 13.4 (2004): 600-612. [67] Khosravi, Mohammad Hossein, and Hamid Hassanpour. "A new paradigm for image quality assessment based on human abstract layers of quality perception." Multimedia Tools and Applications 81.16 (2022): 23193-23215. [68] Xue, Wufeng, et al. "Blind image quality assessment using joint statistics of gradient magnitude and Laplacian features." IEEE Transactions on Image Processing 23.11 (2014): 4850-4862. [69] Zhai, Guangtao, and Xiaolin Wu. "Noise estimation using statistics of natural images." 2011 18th IEEE International Conference on Image Processing. IEEE, 2011. [70] Ma, Jupo, et al. "Blind image quality assessment with active inference." IEEE Transactions on Image Processing 30 (2021): 3650-3663. [71] Pan, Zhaoqing, et al. "VCRNet: Visual compensation restoration network for no-reference image quality assessment." IEEE Transactions on Image Processing 31 (2022): 1613-1627. [72] Liu, Lixiong, et al. "No-reference image quality assessment in curvelet domain." Signal Processing: Image Communication29.4 (2014): 494-505. [73] Chen, Xiaoqiao, et al. "No-reference color image quality assessment: From entropy to perceptual quality." EURASIP Journal on Image and Video Processing 2019 (2019): 1-14. [74] Ou, Fu-Zhao, Yuan-Gen Wang, and Guopu Zhu. "A novel blind image quality assessment method based on refined natural scene statistics." 2019 IEEE international conference on image processing (ICIP). IEEE, 2019. [75] Liu, Lixiong, et al. "Blind image quality assessment by relative gradient statistics and adaboosting neural network." Signal Processing: Image Communication 40 (2016): 1-15. [76] Varga, Domonkos. "No-reference image quality assessment based on the fusion of statistical and perceptual features." Journal of Imaging 6.8 (2020): 75. [77] Liu, Lixiong, et al. "No-reference image quality assessment based on spatial and spectral entropies." Signal processing: Image communication 29.8 (2014): 856-863. [78] Varga, Domonkos. "No-reference image quality assessment with global statistical features." Journal of Imaging 7.2 (2021): 29. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/96966 | - |
| dc.description.abstract | 由於所有相機拍攝的影像不可避免地會受到各種雜訊的影響，無參考雜訊影像品質評估在多媒體處理領域具有重要的實際價值。我們提出的方法基於以下兩個核心理念： 1. 影像的客觀品質主要取決於人類視覺系統 (HVS) 感知的有效資訊量與雜訊。2. 影像雜訊水平估計的精確性對於雜訊失真影像的品質預測性能至關重要。我們設計了一個基於人類視覺系統的影像資訊容量，利用影像功率譜、雜訊估計和對比敏感度函數 (CSF)，以確定雜訊失真影像中的最大感知資訊量。此外，本文還提出了一種基於離散小波變換 (DWT) 的精確影像雜訊估計算法。影像在不同雜訊類型下的變化，則可透過局部均值減法和對比度正規化 (MSCN) 係數的分布來捕捉影像自然特徵。我們採用了柯爾莫哥洛夫-阿諾德網絡 (KANs) 進行訓練，將特徵向量映射到對應的主觀評分。實驗結果顯示，在 TID2008、 TID2013 和 KADID-10k 資料庫上，我們的方法 ICNEN-IQA 在雜訊影像品質預測方面優於其他最先進的影像品質評估方法。 | zh_TW |
| dc.description.abstract | Since all camera-captured images are inevitably subjected to various types of noises, no-reference noisy image quality assessment holds significant practical value in the field of multimedia processing. Our proposed method is based on the following two ideas: 1. The objective image quality is largely determined by the amount of useful information perceived by the Human Visual System (HVS) and noises. 2. Accurate image noise level estimation is the key to the perceptual quality of a noisy image. We design a HVS-based Shannon Information Capacity which leverages image power spectrum, noise estimation and a Contrast Sensitivity Function (CSF) to determine the maximum perception information in noise-distorted images. An accurate DWT-based image noise estimation algorithm is also proposed in this paper. Additionally, the variations in images under different types of noises can be captured via naturalness measurements, as characterized by the distributions of locally mean subtracted and contrast normalized (MSCN) coefficients. Kolmogorov-Arnold Networks (KANs) are used for training to map our feature vectors into corresponding subjective scores. Experimental results on TID2008, TID2013, and KADID-10k databases demonstrate that our method using image information capacity, noise estimation, and naturalness measurements, ICNENM-IQA, outperforms other state-of-the-art image quality assessment methods for noisy image quality prediction. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2025-02-25T16:16:09Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2025-02-25T16:16:09Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 口試委員會審定書 ........................................................................................................... #
誌謝 ................................................................................................................................... i 中文摘要 .......................................................................................................................... ii ABSTRACT .................................................................................................................... iii CONTENTS .................................................................................................................... iv LIST OF FIGURES ........................................................................................................ vii LIST OF TABLES ......................................................................................................... viii Chapter 1 Introduction .............................................................................................. 1 1.1 Problem Statement……………….. ................................................................ 1 1.2 Research Motivation ....................................................................................... 3 1.3 Primary Contribution ...................................................................................... 4 1.4 Thesis Organization ........................................................................................ 5 Chapter 2 Theoretical Background .......................................................................... 6 2.1 Feature Extraction ........................................................................................... 6 2.1.1 Natural Scene Statistics (NSS) .............................................................. 6 2.1.2 Local Binary Patterns (LBP) ................................................................. 7 2.1.3 Frequency Domain Statistics ................................................................. 8 2.1.4 Learning-based Feature Extraction ....................................................... 8 2.2 Score Regression ............................................................................................ 9 2.2.1 Support Vector Machines (SVM) .......................................................... 9 2.2.2 Extreme Learning Machine (ELM) ..................................................... 10 2.2.3 Multilayer Perceptron (MLP) .............................................................. 11 Chapter 3 Literature Review and Related Work .................................................. 12 3.1 BIQAN [44] .................................................................................................. 12 3.1.1 Free Energy Principle .......................................................................... 12 3.1.2 Image Gradient Extraction .................................................................. 14 3.1.3 Texture Masking .................................................................................. 14 3.1.4 Insights of BIQAN .............................................................................. 15 3.2 BNIQA-BH [47] ........................................................................................... 15 3.2.1 Block-Based Image Noise Variance Estimation .................................. 16 3.2.2 Blind Image Noise Assessment ........................................................... 17 3.2.3 Insights of BNIQA-BH ....................................................................... 18 3.3 DMDM [49] .................................................................................................. 19 3.3.1 Near-threshold Model: Statistic-based Noise Estimation ................... 20 3.3.2 Suprathreshold Model: Structure Inference ........................................ 22 3.3.3 Insights of DMDM .............................................................................. 23 3.4 QENI [52] ..................................................................................................... 23 3.4.1 Local Feature Descriptor ..................................................................... 24 3.4.2 Visual Saliency Model ........................................................................ 24 3.4.3 Insights of QENI ................................................................................. 25 3.5 SBK [55] ....................................................................................................... 25 3.5.1 Kurtosis Model of Noisy Image DWT Coefficients ........................... 26 3.5.2 Insights of SBK ................................................................................... 28 3.6 Hyper-IQA [56] ............................................................................................ 28 3.6.1 Self-Adaptive IQA Model ................................................................... 29 3.6.2 Semantic Feature Extraction Network ................................................ 30 3.6.3 Hyper Network for Learning Perception Rule .................................... 30 3.6.4 Hyper Network for Learning Perception Rule .................................... 31 3.6.5 Insights of Hyper-IQA ........................................................................ 31 3.7 DDNet [59] ................................................................................................... 31 3.7.1 Dual-Order Global Pooling ................................................................. 32 3.7.2 Dynamic Quality Regression .............................................................. 33 3.7.3 Insights of DDNet ............................................................................... 33 Chapter 4 Proposed Noise-Specific NR-IQA ......................................................... 34 4.1 HVS-based Image Information Capacity...................................................... 35 4.2 DWT-based Noise Estimation Model ........................................................... 37 4.3 Image Naturalness Measurements ................................................................ 42 4.4 Proposed Feature Vectors and KANs Regression ......................................... 43 Chapter 5 Experiments and Results ....................................................................... 47 5.1 Accuracy of Noise Estimation ...................................................................... 47 5.2 Performance of Quality Prediction ............................................................... 50 Chapter 6 Conclusions ............................................................................................. 57 REFERENCE .................................................................................................................. 58 | - |
| dc.language.iso | en | - |
| dc.subject | 影像自然度 | zh_TW |
| dc.subject | 柯爾莫哥洛夫-阿諾德網絡 | zh_TW |
| dc.subject | 雜訊估計 | zh_TW |
| dc.subject | 影像資訊容量 | zh_TW |
| dc.subject | 無參考影像品質評估 | zh_TW |
| dc.subject | Kolmogorov-Arnold Networks | en |
| dc.subject | No-reference image quality assessment | en |
| dc.subject | image information capacity | en |
| dc.subject | noise estimation | en |
| dc.subject | image naturalness | en |
| dc.title | 基於消息理論之無參考視覺品質評估於相機雜訊影像 | zh_TW |
| dc.title | No-Reference Visual Quality Assessment for Camera Noisy Images Based on Information Theory | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 113-1 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 余執彰;許文良;歐陽良昱 | zh_TW |
| dc.contributor.oralexamcommittee | Chih-Chang Yu;Wen-Liang Hsue;Liang-Yu Ou Yang | en |
| dc.subject.keyword | 無參考影像品質評估,影像資訊容量,雜訊估計,影像自然度,柯爾莫哥洛夫-阿諾德網絡, | zh_TW |
| dc.subject.keyword | No-reference image quality assessment,image information capacity,noise estimation,image naturalness,Kolmogorov-Arnold Networks, | en |
| dc.relation.page | 66 | - |
| dc.identifier.doi | 10.6342/NTU202500551 | - |
| dc.rights.note | 未授權 | - |
| dc.date.accepted | 2025-02-12 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 電信工程學研究所 | - |
| dc.date.embargo-lift | N/A | - |
| 顯示於系所單位： | 電信工程學研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-113-1.pdf 未授權公開取用 | 4.02 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。