ABSTRACT
3D object reconstruction is frequent used in various fields such as product design, engineering, medical and artistic applications. Numerous reconstruction techniques and software were introduced and developed. However, the purpose of this paper is to fully integrate an adaptive artificial neural network (ANN) based method in reconstructing and representing 3D objects. This study explores the ability of neural networks in learning through experience when reconstructing an object by estimating it's z-coordinate. Neural networks' capability in representing most classes of 3D objects used in computer graphics is also proven. Simple affined transformation is applied on different objects using this approach and compared with the real objects. The results show that neural network is a promising approach for reconstruction and representation of 3D objects.
- MICHAEL JUSCHKE. 1996. True Colour Holography. Deg Thesis, Department of Electrical and Electronic Engineering: University of Western Australia.Google Scholar
- WOLFGANG NIEM, JOCHEN WINGBERMUHLE. 1997. Automatic Reconstruction of 3D Objects Using a Mobile Monoscopic Camera. In Proceedings of the International Conference on Recent Advances in 3D Imaging and Modelling", Ottawa, Canada Google ScholarDigital Library
- VIT ZYKA, RADIM SARA. 1997. Scale Model Refinement For 3D Reconstruction. Center of Machine Perception: Czech Technical University.Google Scholar
- RUIZ, OSCAR EDUARDO, CADAVID, CARLOS ALBERTO, MIGUEL. 2001. Evaluation of 2D Shape Likeness for Surface Reconstruction. XIII International Congress on Graphics Engineering.Google Scholar
- MICHAEL NEGNEVITSKY. 2002. Artificial Intelligence. A Guide to Intelligent Systems. Pearson Education Limited 2002, England, 164--178. Google ScholarDigital Library
- YING WU. 2001. An Introduction to ECE510 Computer Vision. Electrical and Computer Engineering: Northwestern University, Evanston.Google Scholar
- INGE SODERKVIST. 1999. Introductory Overview of Surface Reconstruction Methods." Department of Mathematics: Lulea University, Sweden.Google Scholar
- EMMANOUIL PIPERAKIS, ITSUO KUMAZAWA. 2001. Affine Transformations of 3D Objects Represented with Neural Networks. 3-D Digital Imaging and Modeling, Proceedings. 213--223.Google Scholar
- HOD LIPSON, MOSHE SHPITALNI. 2001. Correlation-Based Reconstruction of a 3D Object from a Single Freehand Sketch. Cornell University, University of Michigan, USA. Google ScholarDigital Library
- VOLKER KRUGER, GERALD SOMMER. 2000. Gabor Wavelet Networks for Object Representation and Face Recognition. Kiel, Germany. Google ScholarDigital Library
- GARY BRADSKI, STEPHEN GROSSBERG. 1995. Fast Learning VIEWNET Architectures for Recognizing 3D Objects from Multiple 2D Views. Neural Networks Special Issue on Automatic Target Recognition. Google ScholarDigital Library
- YOSHIHIRO KAWAI, TOSHIO UESHIBA, TAKASHI YOSHIMI, MASAKI OSHIMA. 1992 Reconstruction of 3D Objects by Integration of Multiple Range Data. Japan.Google Scholar
- JOSE GASPAR, ETIENNE GROSSMANN, JOSE SANTOS-VICTOR. 2001. INTERACTIVE RECONSTRUCTION FROM AN OMNIDIRECTIONAL IMAGE. 9th International Symposium on Intelligent Robotic Systems.Google Scholar
- ANDERS HEYDEN. 1995. Geometry and Algebra of Multiple Projective Transformations. Dept of Mathematics, Lund University, Sweden.Google Scholar
- MIKLOS HOFFMANN, LAJOS VARADY. 1998. Free-form Surfaces for Scattered Data by Neural Networks. Journal for Geometry and Graphics. Vol.2. 1--6.Google Scholar
- JOARDER KAMRUZZAMAN, S. M. AZIZ. 2002. A Note on Activation Function in Multilayer Feedforward Learning. Monash University, University of South Australia, Australia.Google Scholar
- CS. SZEPESVARI, A. LORINCZ. 1994. Self-Organized Learning of 3 Dimensions. Hungary.Google Scholar
- TOHRU NITTA. 1994. Generalization Ability of the Three-Dimensional Back-Propagation Network. Ibaraki, Japan.Google Scholar
- AC EVANS, NA THACKER, JEW MAYHEW. 1993. A Practical View Based 3D Object Recognition System. University of Sheffield.Google Scholar
- RICHARD S. YOON, DON S. BORRETT, HON C. KWAN. 1995. Three-Dimensional Object Recognition Using a Recurrent Attractor Neural Network. IEEE-EMBC and CMBEC Theme 2: Imaging.Google Scholar
- 3D object reconstruction and representation using neural networks
Recommendations
A neural network approach for image reconstruction in electron magnetic resonance tomography
An object-oriented, artificial neural network (ANN) based, application system for reconstruction of two-dimensional spatial images in electron magnetic resonance (EMR) tomography is presented. The standard back propagation algorithm is utilized to train ...
Cochannel Interference Minimization Using Wilcoxon Multilayer Perceptron Neural Network
ITC '10: Proceedings of the 2010 International Conference on Recent Trends in Information, Telecommunication and ComputingThis paper presents the application of wilcoxon machines learning technique for artificial neural network in channel equalization application. The equalizer mitigates the effect of co-channel interference, inter-symbol interference in the presence of ...
3D object & light source representation with multi layer feed forward networks
In this paper, an experiment is conducted in order to prove that multilayer feed forward neural networks are capable of representing most classes of 3D objects, used in computer graphics. Furthermore, the use of neural networks for the representation of ...
Comments