Department of Systems Engineering and Engineering Management,

                        The Chinese University of Hong Kong




Title: Part Based Object Retrieval in Cluttered Environment


Speaker: Maylor K.H. Leung, Associate Professor

   Nanyang Technological University, Singapore


Date    : August 25th, 2006 (Friday)

Time   : 10:30am --11:30am.

Venue : Room 909, ERP Lab

             MMW Engineering Building (Engineering Building Complex Phase 2)







A novel local structural approach, which is a sequel to our previous work, is proposed in this talk for object retrieval in cluttered and occluded environment without identifying the outlines of an object. It works by first extracting consistent and structurally unique local neighborhood from inputs or models, and then voting on the optimal matches employing dynamic programming and a novel hyper cube based indexing structure. The proposed concepts have been tested on a database with thousands of images and compared with the 6 nearest-neighbors shape description with superior results.





Maylor K.H. Leung received the BSc degree in physics from the National Taiwan University in 1979, and the BSc, MSc and PhD degrees in computer science from the University of Saskatchewan, Canada, in 1983, 1985 and 1992 respectively.  Currently, Dr. Leung is an Associate Professor with Nanyang Technological University, Singapore.  His research interest is in the area of Computer Vision, Pattern Recognition and Image Processing.  Particular interest is on improving security using visual information.  Some demo works on video surveillance, face recognition and shape analysis can be found in www.ntu.edu.sg/home/asmkleung


************************  ALL ARE WELCOME  **********************


Host :  Prof. Chris Yang

Tel :   (852) 2609-8239

Email : yang@se.cuhk.edu.hk


Enquiries: Mr. Peixiang Zhao or Prof. Jeffrey Xu Yu,

                Department of Systems Engineering and Engineering Management


Website:   http://www.se.cuhk.edu.hk/~seg5810

Email:       seg5810@se.cuhk.edu.hk