- 期刊
Multi-Scale Patch Prior Learning for Image Denoising Using Student's-t Mixture Model
摘要
Patch prior based image regularization technique has drawn much attention recently. The Multi-Scale Expected Patch Log Likelihood (MSEPLL) algorithm as a popular method for learning multi-scale prior of image patches has shown competitive results. However, the current algorithm learns patch prior with the Gaussian Mixture Model that is sensitive to outliers commonly. In this paper, we extend the MSEPLL method and attempt to employ the student's-t mixture model (SMM) to learn multi-scale image patch prior in a more robust way. Experiment results demonstrate that our proposed method performs well both in visual effect and quantitative evaluation.
延伸閱讀
- 吳究、張奇、劉銘哲（2009）。Precise Multisource Image Registration Based on Scale Invariant Feature Transform Points。航測及遙測學刊，14(2)，141-155。https://doi.org/10.6574/JPRS.2009.14(2).5
- Chen, W. N. (2004). A Multi-Scale Approach For Image Inpainting [master's thesis, Tatung University]. Airiti Library. https://www.airitilibrary.com/Article/Detail?DocID=U0081-0607200917234872
- 許嘉元（2006）。Study on Image Matching and Registration by Modulating Segmental Radiometric Parameters for Different-Source Images〔碩士論文，國立中央大學〕。華藝線上圖書館。https://www.airitilibrary.com/Article/Detail?DocID=U0031-0207200917341890
- 潘偉庭、楊明德、趙智凡（2016）。Image-based modeling for multi-source images and establishing an accuracy index of reconstruction。航測及遙測學刊，21(2)，125-138。https://doi.org/10.6574/JPRS.2016.21(2).5
- Su, G. C. (2014). Using boundary detection and path-based method to solve labeling problem in image segmentation [master's thesis, National Tsing Hua University]. Airiti Library. https://www.airitilibrary.com/Article/Detail?DocID=U0016-2912201413553168