Welcome to Huang Dong’s Homepage

 

 

 

 

Dong Huang  黄 东

 

Received the B.Sc. degree in Automation from Southwest Petroleum University in 2002 and the M.Sc. degree in Automation from University of Electronic Science and Technology of China (UESTC), in 2005.

 

I’m currently pursuing the Ph.D. degree in Computational Intelligence Laboratory，School of Computer Science and Engineering, UESTC. My supervisor is Prof. Zhang Yi.

 

 

 

 

 

<>  Research Interests   <>

 

Neural Networks, Manifold Learning, Image Processing.

 

<>        Publications        <>

 

 

*  Dong Huang, Zhang Yi  and Xiaorong Pu, Manifold Based Learning and Synthesis,  IEEE Transactions on Systems, Man and Cybernetics - Part B, regular paper, Accepted.

*  Dong Huang, Zhang Yi and Xiaorong Pu, A Kernel View of Manifold Analysis for Face Images. IEEE 3rd International Conference on Intelligent System and Knowledge Engineering (ISKE 2008), Accepted.

*  Dong Huang and Xiaorong Pu, Manifold Learning With Local Geometry Preserving and Global Affine Transformation,   IEEE International Conferences on Cybernetics & Intelligent Systems (CIS) and Robotics, Automation & Mechatronics (RAM) (CIS-RAM 2008)，Accepted.

*  Dong Huang and Zhang Yi, A New Incremental PCA Algorithm With Application to Visual Learning,   Revised.

*  Dong Huang, Zhang Yi and Xiaorong Pu, A New Local PCA SOM Algorithm，Neurocomputing (SCI)，71 (2008) 3544–3552.

*  Dong Huang and Zhang Yi, Shape Recovery by A Generalized Topology Preserving SOM, Neurocomputing (SCI), In Press, Accepted in Nov, 2007.

*  Dong Huang, Huizhong Qiu and Zhang Yi, Local-Bandwidth Mean Shift Segmentation of MR Images Using Nonlinear Diffusion.    Dynamics of Continuous, Discrete and Impulsive systems，Series A: Mathematical Analysis, Vol. 14(S1) 737—741, 2007.

 

 

 

 

<>  Research Projects   <>

 

LEARNING, SYNTHESIS, RECOGNITION AND HUMAN COMPUTER INTERACTION (Present )

 

 

 

The objective is to find the relationships between low level image structure and higher order representations and recognition, and use these relations as aids in human computer interaction.

In real world applications, high dimensional data set usually subjects to the underlying low dimensional manifolds. Typical examples include variations of Expression, Poses, and Gestures. Analysis and Synthesis are the two main aspects of the human-computer interactions.

The underlying assumptions are: 1) The local sub-manifold lies in the at most k-dimensional subspace;2) The sub-manifolds are locally smooth if connected.

 

 

 

u                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    *Preliminary results of the proposed LGGA algorithm:

 

u      Punctured Sphere

u      Swiss Roll

u      Swiss Hole

u      Twin Peaks

u      Duck Image Manifold

u      Image Shifting Manifold

u      Image Synthesis for 3D Object

u                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                >>more coming…

 

 

 

 Scene Driven 3-D Facial Animation Based on Neural Networks (2007- Present)

 

 

 

This work is supported by a grant from National High Technology Research and Development Program of China. Grant 2007AA01Z321.

 

 

 

 

 

Multi-stability of Recurrent Neural Networks (2005-Present)

 

 

National Nature Science Funding of China under Grant 60471055

 

 

Multi-stability Analysis of Neural Networks (2005-Present)

 

 

 

Specialized Research Fund for the Doctoral Program of Higher Education under Grant 20040614017

 

 

 

 

 

 

 

 

<>         Contact me        <>

 

Computational Intelligence Laboratory,

School of Computer Science and Engineering,

University of Electronic Science and Technology of China.

Chengdu, 610054, P.R. China.

Email: Donnyhuang@uestc.edu.cn

hdairtiger@gmail.com

 

 

 

 

Last Modified: Sept. 2008

Dong Huang © 2006