旧版入口
学术交流
2018年7月16日叶筱倞教授学术报告
上传时间:2018-07-05 作者:杭电理学院 浏览次数:
报告题目Joint image edge reconstruction and its application
 
报告人Professor Xiaojing Ye (叶筱倞)
 
报告摘要We propose a new joint image reconstruction method by recovering edge directly from observed data. More specifically, we reformulate joint image reconstruction with vectorial total-variation regularization as an $l_1$ minimization problem of the Jacobian of the underlying multi-modality or multi-contrast images. Derivation of data fidelity for Jacobian and transformation of noise distribution are also detailed. The new minimization problem yields an optimal $O(1/k^2)$ convergence rate, where $k$ is the iteration number, and the per-iteration cost is low thanks to the close-form matrix-valued shrinkage. We conducted numerical tests on a number multi-contrast magnetic resonance image (MRI) and computed tomography (CT) datasets, which show that the proposed method significantly improves reconstruction efficiency and accuracy compared to the state-of-the-arts. This is a joint work with Yunmei Chen (UFL) and Bin Li (SCUT).
 
报告时间:2018年7月16日上午10:30-11:30
报告地点:理学院学术报告厅(6教南528)
 
Copyright © 2014 杭州电子科技大学 版权所有
技术支持 : 捷点科技