 |
Kang Li
About MyselfI have graduated with a Ph.D. in ECE from Carnegie Mellon University. I now work in Microsoft My research interests are in the areas of computer vision, image analysis and understanding, and medical imaging. Specifically, I am interested in the theories of graphical models, statistical learning, optimization, and their applications to the design and implementation of computer algorithms/systems for solving practical problems arising in computer-assisted medical diagnosis and treatment, developmental and computational biology, information retrieval and data mining, and robotics. A particular emphasis of my current research is on the development of computer algorithms and an automated vision-based system for tracking the individual identities and recognizing the various behaviors (migration, division, death, and differentiation) of large-scale stem cell populations in time-lapse microscopy images. I have demonstrated the system for simultaneously tracking (a record number of) over 4000 stem cells in real time. During the course of my Ph.D. research, I have written more than one million lines of C++ code, as well as hundreds of Python, MATLAB, and shell scripts. I am a member of a multidisciplinary research team that involves biologists, computer scientists, engineers, mathematicians, and industrial visitors. I was born in China's south-eastern city Nanjing, and lived in three Chinese cities: Nanjing, until I was 6; Zhanjiang, a southern coastal city, until I was 14; and Shenzhen, where my parents currently live, until I was 18. Click here to go to my "official" Robotics Institute homepage. Click here to visit Jenny's webpage. Selected Publications"Nonnegative Mixed-Norm Preconditioning for Microscopy Image Segmentation." Kang Li and Takeo Kanade. Proceedings of the 21st Biennial International Conference on Information Processing in Medical Imaging (IPMI). Williamsburg, VA. July 2009. pp. 362-373. [pdf] "Reliably Tracking Partially Overlapping Neural Stem Cells in DIC Microscopy Image Sequences." Ryoma Bise, Kang Li, Sungeun Eom, and Takeo Kanade. Proceedings of the MICCAI Workshop on Optical Tissue Image analysis in Microscopy, Histopathology and Endoscopy (OPTIMHisE). London, UK. September 2009. pp. 67-77. [pdf] "Computer Vision Tracking of Stemness" Kang Li, Eric D. Miller, Mei Chen, Takeo Kanade, Lee E. Weiss, and Phil G. Campbell. Proc. IEEE International Symposium on Biomedical Imaging (ISBI): Special Session on In Vivo Microscopic Image Analysis. Paris, France. May 14-17, 2008. Note: Oral presentation.[pdf] "Cell Population Tracking and Lineage Construction with Spatiotemporal Context" Kang Li, Mei Chen, and Takeo Kanade. Proceedings of the 10th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI). Brisbane, Australia. October 29-November 2 2007. Note: Oral presentation[pdf][slides][extended journal version] (MICCAI Young Scientist Award) "Online Tracking of Migrating and Proliferating Cells Imaged with Phase-Contrast Microscopy." Kang Li, Eric D. Miller, Lee E. Weiss, Phil G. Campbell, and Takeo Kanade. Proceedings of the 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW '06). June 19-21 2006. Note: Oral presentation (Acceptance rate 11.6%); patent pending. [pdf] "Optimal Surface Segmentation in Volumetric Images - A Graph-Theoretic Approach." Kang Li, Xiaodong Wu, Danny Z. Chen, and Milan Sonka. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). 28(1). January 2006. pp. 119-134. Note: Patent pending. [pdf] "Simultaneous Segmentation of Multiple Closed Surfaces Using Optimal Graph Searching." Kang Li, Steven Millington, Xiaodong Wu, Danny Z. Chen, and Milan Sonka. Proc. the 18th Biennial International Conference on Information Processing in Medical Imaging (IPMI). July 2005. pp. 406-417. Note: Oral presentation (Acceptance rate 11%). [pdf][swf][wmv] (more...) SoftwareUpdated: Image Stabilizer Plugin for ImageJ |
