国家数学与交叉科学中心合肥分中心报告会

题  目：Structured sparse representation for image restoration

报告人：董伟生，西安电子科技大学

时  间：2012年12月12日（周三）下午3:30-5:00

地  点：管理科研楼1218室

摘  要：Image restoration aiming at recovering a high-quality image from its degraded version has been
extensively studied in the past decades. The emerging of the compressive sensing theory has led to a
flurry of research on sparsity-based image restoration, showing some promising image reconstruction
results. However, the sparse representation model may not be robust for a faithful reconstruction of
the original image due to the degradation of the observed image. In this talk, I will introduce our
recent work on sparsity-based image interpolation using nonlocal autoregressive modeling. In this
work, we show that the nonlocal autoregressive model can serve as an effective constraint that can
increase the incoherence between the representation bases and the sampling matrix, and thus
significantly improve the interpolation performance. I this talk, I will also introduce our recent
work on low-rank approximation based sparse coding, showing some interesting connections between
structured sparse coding and low-rank approximation.
 

报告人简介：Weisheng Dong received the B.S. degree in communication engineering from Huazhong
University of science and technology, Wuhan, China in 2004 and the Ph. D. degree in circuit and
systems from Xidian University, Xi'an, China in 2010. From Sep. to Dec. 2006 he was an intern with
Microsoft Research Asia. From Jan. 2009 to Jun. 2010, he was a research assistant/associate with Dep.
of Computing, the Hong Kong Polytechnic University, Hong Kong. In Sep. 2010 he joined the school of
electronic engineering, Xidian University as a Lecturer, and has been an associate professor since
Jun. 2012. His research interests include inverse problems in image processing, sparse
representation, and image compression. He was the recipient of the best paper award at SPIE VCIP
2010.

主办单位：中国科学技术大学数学科学学院

         国家数学与交叉科学中心合肥分中心

欢迎感兴趣的师生参加！