讲座题目：Variational models for Bi-modality image reconstruction and fusion 主讲人：张小群 教授 开始时间😸：2019-11-30 16:05:00 讲座地址🔢：中北校区办公楼小礼堂 主办单位🖕🏼：计算机科学与技术学院
报告人简介： 张小群教授，教育部新世纪人才计划、全国青年拔尖人才计划入选者，自然科学研究院。武汉大学获得学士和硕士学位，法国南布列塔尼大学获得博士学位🪫，后在加州大学洛杉矶分校担任客座助理教授。2010年加入上海交通大学自然科学研究所和数学科学学院🧵。主要研究领域包括图像处理，计算机视觉，医学成像💃，反问题和变分方法，数值分析，凸优化等👩🏼🦳。在Journal of Mathematical Imaging and Vision👨🦱，Inverse Problems👨🏼✈️，SIAM J. Imaging Sci🐻❄️，Journal of Scientific Computing多个等国际期刊和会议上发表40余篇论文，谷歌学术引用2650余次。 报告内容： The developments of dual-modality medical imaging devices have gained increasing interests as dual-modality imaging presents significant advantages for information fusion and clinic diagnosis. In the first part of my talk, I will present a total variation based joint regularization with an adaptively estimated common edge indicator function as a weight. The common edge function takes into account the shared structures of two modalities in a flexible way. A proximal alternating algorithm is adopted to recover dual-modality images and the common edge, and the convergence of the overall numerical scheme is established. Finally, numerical tests for PET and MRI under different noise levels and subsampling patterns show that the proposed approach obtains favorable results compared to some existing methods. The second part of my talk is on bi-modality image fusion. We propose a three-step method for bi-modal image fusion. A tight frame system is firstly adaptively learned from bi-modal images for capturing source images features as much as possible. Following, a fused coefficient set is constructed by integrating the frame coefficients from both modalities. Finally, a variational model is designed to reconstruct a fused image based on the fused coefficients and the intensity information of those smooth regions. The alternating iteration scheme is proposed to solve the resulted variational problems in the third step. Numerical experiments on multi-modal medical images fusion and multi-focused natural images fusion show that the proposed approach outperforms some existing methods. |
