报告题目：A Level Set Framework for Image Segmentation and Bias Correction with Applications to MRI
报告人：Chunming Li（美国 University of Pennsylvania）
地点：数统学院楼5楼510（信息系会议室）
时间：2011.11.29（周二）上午10点
Abstract: Image segmentation is an important and fundamental problem in image processing, computer vision, and medical imaging. In this talk, I will present two different methods for image segmentation. The first one is formulated in a level set framework, and image segmentation is achieved by a level set evolution process, called distance regularized level set evolution （DRLSE）. The distance regularization term defined with a double-well potential serves to regularize the level set function, and therefore completely eliminates the need for re-initialization. The second method is an energy minimization approach for simultaneous estimation of the bias field and image segmentation. The estimated bias field is used to obtain bias corrected image. Efficient matrix computations are used to minimize the proposed energy. Numerical stability of this method is verified by matrix analysis. This method is robust to initialization and has been shown to be more accurate than the well-known methods for brain MR images.
报告人简介：
Chunming Li received the Ph.D. degree in electrical engineering from University of Connecticut, Storrs, CT, in 2005. He is currently a senior researcher in medical image analysis at the University of Pennsylvania, Philadelphia. He was a Research Fellow at the Vanderbilt University Institute of Imaging Science, Nashville, TN, from 2005 to 2009. His research interests include image processing, computer vision, and medical imaging, with expertise in image segmentation, MRI bias correction, active contour models, variational and PDE methods, and level set methods. He has published a number of highly original and influential research articles on level set methods, image segmentation, and MRI bias correction in leading journals and conference proceedings. His papers have been frequently cited, with more than 1100 citations of his papers (all first-authored). In particular, one of his papers on the level set method has received more than 700 citations since its publication in 2005. He has served as referee and committee member for a number of international conferences and journals in image processing, computer vision, medical imaging, and applied mathematics.
加好友 
发短信
Post By：2011/11/25 17:15:16 [只看该作者]
