GVIP Journal    

ICGST

Issue(4)

GVIP
Apply neural schemes to deformation objects
 
Yu-Ju Shen and Ming-Shi Wang
 
Abstract:
In this paper, a novel Self-organizing mapping (SOM) neural network is proposed for identifying and simulating deformation objects. The weights of the network nodes can be initialized according to the mass and spring parameters. SOM is a very simple and easy means of visualization. The proposed method support adaptive time steps, and dynamic modifications of physical parameters, including mass and spring ' s stiffness . The advantage of the proposed method is that an external force can be simply added to any node of the model and the structure of the object freely adjusted. Simulation results show that the SOM neural network presents a convincing model of deformation objects and provide an alternative approach of solving this class of physics-based models.
 
Key words: Virtual Reality, Self-organizing maps , Neural Network , Visualization .
 
Biographies:
 

Yu-Ju Shen received the M.S. degree in Electrical Engineering from Feng Chia University , Taichung , Taiwan , in 19 98 . She is a Ph.D. student at National Cheng Kung University now, Tainan , Taiwan . Her currently research interests include virtual reality , computer vision , and grid computing .

 

Ming-shi Wang received the B.S. degree in Electronics Engineering from Feng Chia University , Taichung , Taiwan , in 1977, the M.S. degree in Electrical Engineering from National Cheng Kung University , Tainan , Taiwan , in 1982, and the Ph.D. degree in Computation from UMIST, Manchester , U.K. , in 1992. Currently, Dr. Wang is an Associate Professor in Department of Engineering Science and the Director of the Division of Teaching and Research, Computer and Network Center, both at National Cheng Kung University, Tainan, Taiwan. His major research interests are digital image processing, computer vision, content filtering, virtual reality, and grid computing.

BibTex:

@ARTICLE{P1150508001,

AUTHOR = {Yu-Ju Shen and Ming-Shi Wang},

TITLE = {Apply neural schemes to deformation objects },

JOURNAL = {ICGST International Journal on Graphics, Vision and Image Processing},

YEAR = {2005},

MONTH = {April},

VOLUME = {05},

ISSUE = {4},

PAGES = {7--14}

}

( Full paper 550 Kb)