Image Denoising by Gaussian Patch Mixture Model and Low Rank Patches
报告题目(Title)：Image Denoising by Gaussian Patch Mixture Model and Low Rank Patches
报告人(Speaker)：金其余 副教授 （内蒙古大学）
地点(Place)：腾讯会议 ID：770 831 501 密码：123456
时间(Time)：2020年9月21日（星期一）18:00-19:00
邀请人(Inviter)：刘君
报告摘要
Non-local self-similarity based low rank algorithms are the state-of-the-art methods for image denoising. In this paper, a new method proposed by solving two problems: how to improve similar patches matching accuracy and build an appropriate low rank matrix approximation model for Gaussian noise. For the first problem, similar patches can be found locally or globally. Local patch matching is to find similar patches in a large neighborhood which can alleviate noise effect, but the number of patches may not be sufficient. Global patch matching is to determine enough similar patches but the error rate of patch matching may be higher. In this paper, we propose and develop a novel image denoising algorithm by using Gaussian Patch Mixture Model so that both local and global matching can be achieved, and the mixture of patches can be further regularized via k-means clustering procedure and low rank minimization. The second problem is that there is no low rank matrix approximation model to adapt to Gaussian noise. We build a new model according to the characteristics of Gaussian noise, then prove that this is a globally optimal solution of the model. Experimental results are reported to show that the proposed approach outperforms the state-of-the-art denosing methods in both PSNR/SSIM values and visual quality。
主讲人简介
金其余，内蒙古大学副教授。法国南布列塔尼大学应用数学博士，巴黎六大、上海交通大学博士后，巴黎-萨克雷高等师范学校访问学者，2015年由内蒙古大学数学科学学院高层次引进。长期与国内外多所大学保持合作，包括法国巴黎-萨克雷高等师范学校、巴黎六大、Centre Inria Rennes等。研究领域包括: 图像处理、计算机视觉与最优化。相应成果发表于SIAM Journal on Imaging Sciences、Cell子刊Structure、Journal of scientific computing等期刊。主持国家自然科学基金、内蒙古自然科学基金等项目多项。
