Chunming Li

Ph.D. in Electrical Engineering
University of Connecticut

      
   
Vistors since Oct, 2005

 About | Publications | Research | Professional Activities | Code | Collaborators | Contact Info | Personal

About Me                                             

I received my Ph.D. degree in Electrical Engineering from University of Connecticut in 2005. My Ph.D. advisor was Prof. Martin D. Fox. Before I came to the U.S., I was trained in mathematics in China and got my B.S. and M.S. degrees in Math. My research interests include image processing, computer vision, medical imaging, and applied mathematics.

Selected Publications                                                                     Back to top

  1. Chunming Li, Fang Li, Chiu-Yen Kao, and Chenyang Xu, "Image Segmentation with Simultaneous Illumination and Reflectance Estimation: An Energy Minimization Approach", ICCV 2009.

  2. Chunming Li, Chris Gatenby, Li Wang, and John C. Gore, "A Robust Parametric Method for Bias Field Estimation and Segmentation of MR Images", CVPR 2009.

  3. Chunming Li, Rui Huang, Zhaohua Ding, Chris Gatenby, Dimitris Metaxas, John Gore, "A Variational Level Set Approach to Segmentation and Bias Correction of Images with Intensity Inhomogeneity", MICCAI 2008. (Oral presentation),  (pdf, BibTex, PPT slides, Code)

  4. Chunming Li, Chiu-Yen Kao, John C. Gore, and Zhaohua Ding, "Minimization of Region-Scalable Fitting Energy for Image Segmentation", IEEE Trans. Image Processing, vol 17 (10),  2008. (pdf, BibTex, Matlab code: .rar, .zip new ).

  5. Chunming Li, Chenyang Xu, Changfeng Gui, and Martin D. Fox, "Regularized Level Set Evolution and its Application to Image Segmentation", IEEE Trans. Image Processing, accepted, 2008.

  6. Chunming Li, Chiu-Yen Kao, John C. Gore, and Zhaohua Ding, "Implicit Active Contours Driven by Local Binary Fitting Energy", CVPR 2007. (pdf, BibTex, Demos, Code)

  7. Chunming Li, Chenyang Xu, Changfeng Gui, and  Martin D. Fox, "Level Set Evolution Without Re-initialization: A New Variational Formulation", CVPR 2005. (Oral presentation). (pdf, BibTex, Citations, Demos, Matlab code)

  8. Chunming Li, Jundong Liu, and Martin D. Fox, "Segmentation of Edge Preserving Gradient Vector Flow: An Approach Toward Automatically Initializing and Splitting of Snakes", CVPR 2005. (pdf, BibTex, Demos)

Research Projects                                                                           Back to top

My Research at UConn:
  • Level set methods: method 1, method 2, ...
  • Snake models
  • Surface reconstruction from unorganized points
  • Multiple target tracking
  • Ultrasound image denoising
  • Texture segmentation

My Research in Industry:

ABB Robotics Technology Group (6/2001--2/2003):

  • Robot calibration algorithm and software development
  • Camera calibration algorithm for 3D reconstruction
  • Sub-pixel edge detection and laser line detection for 3D scanner
  • Numerical methods for optimization

Pfizer Global Research & Development (5/2004--8/2005):

  • Ultrasound image analysis and measurement of carotid artery intima-media 
  • Carotid artery motion analysis
. 

Professional Activities                                                     Back to top

Reviewer for:

  • IEEE Trans. Pattern Analysis and Machine Intelligence
  • IEEE Trans. Image Processing
  • IEEE Trans. Nuclear Science
  • Medical Image Analysis
  • Journal of Computational Physics
  • Journal of Mathematical Imaging and Vision
  • Image and Vision Computing
  • Magnetic Resonance Imaging
  • Signal Processing
  • Machine Vision and Application
  • Pattern Recognition Letters
  • Medical Image Computing and Computer Aided Intervention (MICCAI)
  • IEEE conference on Computer Vision and Pattern Recognition (CVPR)

Invited Talks                                                                                                Back to top

  • "Variational and Level Set Methods in Image Segmentation", Mathematics Department, Ohio State University, June 7, 2007. (PPT slides)
  • "Vessel Segmentation Using Local Binary Fitting Active Contours", Mathematics Department, University of Connecticut, October, 2006
  • "Active Contours, Level Sets, and Image Segmentation", Statistics Department, Florida State University, January, 2006.
  • "Diffusion Tensor Imaging: Concepts and Processing Techniques" and "Level Set Methods and Medical Image Segmentation", Engineering Physics Department, Tsinghua University, December, 2006
  • "Level Set Evolution without Reinitialization", Mathematics Department, Vanderbilt University, November, 2005.
  • "Mathematical Methods in Medical Imaging", Mathematics Department, Fudan University, October, 2005.

Level Set/Active Contour Models for Image Segmentation                                   Back to top

Edge based models:
  1. Level Set Evolution without Re-initialization: A New Variational Formulation, CVPR'05 (oral presentation). Click here to see some demos and download Matlab code for this method. C code for this method is available by email request. This method was improved in my IEEE TIP paper ( try the code). The new paper and the source code will be available here. Note: In the new method, the level set function is intrinsically maintained as an approximate signed distance only near the zero level set.
  2. Fast narrow band implementation of the above method, (pdf, demo code).
  3. Segmentation of external force field for a snake model, CVPR'05.

 
Region based models:
  • A Robust Parametric Method for Bias Field Estimation and Segmentation of MR Images, CVPR'09. (pdf, BibTex)
  • Implicit Active Contours Driven by Local Binary Fitting Energy, CVPR'07. (pdf, BibTex)
  • Minimization of Region-Scalable Fitting Energy for Image Segmentation, IEEE Trans. Image Processing, 2008.  (pdf, BibTex).

Implementations of the original LBF model and further developments:

  1. LBF_v0. (Matlab source code for the original LBF model in the above CVPR and IEEE TIP papers).
  2. LBF_v0.1  (.rar or .zip) for Matlab 7.0 or higher versions in Windows. (Note: this version is an improvement of LBF_v0, much more robust to contour initialization).
  3. LBF_1.0 (simultaneous segmentation and bias field estimation) (MICCAI 2008, oral presentation)
  • Segmentation of brain MR images with intensity inhomogeneity. This model is able to simultaneously segment gray matter, white matter, cerebrospinal fluid (CSF), and the background. One page abstract to appear in ISMRM'08 (oral presentation).
3D versions:
Implementations of other level set/active contour methods: 
Back to top