3D modeling of virtualized reality objects using neural computing

A methodology for 3D modeling of virtualized reality objects using neural computing is presented. In this paper the objects are represented in virtualized reality and their 3D data are acquired by one of three acquisition systems: endoneurosonographic equipment (ENS), stereo vision system and non-contact 3D digitizer. These objects are modeled by one of three neural architectures: Multilayer Feed-Forward Neural Network (MLFFNN), Self-Organizing Maps (SOM) and Neural Gas Network (NGN). The 3D virtualized representations correspond to several objects as phantom brain tumors, faces, archaeological items, fruits, among others. We carry out comparisons in terms of computational cost, architectural complexity, training method, training epochs and performance. Finally, we present the modeling results and conclude that SOM and NGN models achieve the best performances and the lowest displaying times, while MLFFNN models have the lowest memory requirements and acceptable training times.

[1]  Fernand S. Cohen,et al.  Ordering and Parameterizing Scattered 3D Data for B-Spline Surface Approximation , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Eduardo Bayro-Corrochano.  Neural Computing for 2D Contour and 3D Surface Reconstruction , 2010 .

[3]  Roy Hall,et al.  Supporting Complexity and Conceptual Design in Modeling Tools , 1991 .

[4]  3D Object Modeling - Issues and Techniques , 2003 .

[5]  S. Haykin.  Kalman Filtering and Neural Networks , 2001 .

[6]  Eduardo Bayro-Corrochano,et al.  Spatio-temporal Image Tracking Based on Optical Flow and Clustering: An Endoneurosonographic Application , 2010, MICAI.

[7]  Timo Honkela,et al.  On the Quantization Error in SOM vs. VQ: A Critical and Systematic Study , 2009, WSOM.

[8]  Namho Hur,et al.  3D model compression in MPEG , 2008, 2008 15th IEEE International Conference on Image Processing.

[9]  David G. Stork,et al.  Pattern Classification (2nd ed.) , 1999 .

[10]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[11]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[12]  Ana-Maria Cretu,et al.  Neural-network-based models of 3-D objects for virtualized reality: a comparative study , 2006, IEEE Transactions on Instrumentation and Measurement.

[13]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[14]  Ana-Maria Cretu,et al.  Data acquisition and modeling of 3D deformable objects using neural networks , 2009, 2009 IEEE International Conference on Systems, Man and Cybernetics.

[15]  Eduardo Bayro-Corrochano,et al.  Joint Freehand Ultrasound and Endoscopic Reconstruction of Brain Tumors , 2008, CIARP.

[16]  Peter Eisert,et al.  3-D reconstruction of real-world objects using extended voxels , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

[17]  Eiji Kawai,et al.  COMMUNICATIONS RESEARCH LABORATORY , 2003 .

[18]  Hanbo Liu,et al.  Implicit surface reconstruction from 3D scattered points based on variational level set method , 2008, 2008 2nd International Symposium on Systems and Control in Aerospace and Astronautics.

[19]  Stephen Cameron.  Efficient bounds in constructive solid geometry , 1991, IEEE Computer Graphics and Applications.

[20]  Mark E. Oxley,et al.  Comparative Analysis of Backpropagation and the Extended Kalman Filter for Training Multilayer Perceptrons , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  Thomas Martinetz,et al.  'Neural-gas' network for vector quantization and its application to time-series prediction , 1993, IEEE Trans. Neural Networks.