Dong LI (李东)  (CV)
Associate Professor
Faculty of Automation Department
Guangdong University of Technology

Office: Room 403, Engneering Building No.2, Guangdong University of Technology, Guangzhou, China, 510006

Research Interests: face recognition, feature extraction, and high-resolution image analysis

I am looking for research collaboration and partners for pore-scale facial feature applications. Please email me if you are interested.
I am an Associate Professor in the Faculty of Automation at Guangdong University of Technology (GDUT). I received my PhD degree in the Department of Electronic and Information Engineering at The Hong Kong Polytechnic University in Feb 2014. I worked under the supervision of Professor Kin-Man (Kenneth) Lam.

My research interest lies in computer vision, pattern recognition and image analysis. My earlier work designed robust and distinctive features to describe pore-scale facial keypoints, such as pores, fine winkles and hair. More specifically, I focus on: 1) designing new pore-scale feature extraction algorithms, 2) developing pore-scale facial feature applications, such as face verification, 3) adapting existing algorithms to pore-scale application. In the area of image analysis, I am especially interested in color correction and image restoration. 

My current projects include:
1. Differentiating identical twins based on facial images
2. 3D face reconstruction
3. Skin biometric
4. Facial landmark localizaiton

Previous projects:
1. High-Resolution face verification using pore-scale facial features

2. Design and Learn Distinctive Features from Pore-scale Facial Keypoints
3. Color Correction with Blind Image Restoration based on Multiple Images Using a Low-Rank Model


Selected Publications (Full List)

High-Resolution Face Verification Using Pore-scale Facial Features
Dong Li, Huiling Zhou and Kin-Man Lam
IEEE Transaction on Image Processing
(TIP), 2015.
Impact factor: 3.11

Design and Learn Distinctive Features from Pore-scale Facial Keypoints
Dong Li and Kin-Man Lam
Pattern Recognition
(PR), 2015.
Impact factor: 2.58



Last update: April/26/2015