3D object recognition from 2D invariant view sequence under translation, rotation and scale by means of ANN ensemble

In this paper, we present a supervised multiple-weight neural network ensemble strategy for 3D object recognition from 2D multiple-view invariant sequence, so as to achieve omnidirectional information accumulation or solution in large-scale database. View information with transition in explicitly temporal order, is empirically selected for training set. On condition that requirements could not be met to a certain extent in one 3D object, more complicated training set is adopted in order to regrow and expand knowledge until satisfactory, without affecting knowledge acquired previously in other 3D objects. Simulation experiment for 3D object recognition from 2D view sequence achieved encouraging results, and proved effective and feasible in the approach proposed.

[1]  Sang-Kyung Lee,et al.  Translation, rotation and scale invariant pattern recognition using spectral analysis and hybrid genetic-neural-fuzzy networks , 1996 .

[2]  Rae-Hong Park,et al.  A surface-based approach to 3-D object recognition using a mean field annealing neural network , 2002, Pattern Recognit..

[3]  Hao Feng,et al.  The application of DBF neural networks for object recognition , 2004, Inf. Sci..

[4]  Robert I. Damper,et al.  A Neural Network Approach to Planar-Object Recognition in 3D Space , 1999, Pattern Analysis & Applications.

[5]  Wang Shou Multi-Camera Human-Face Personal Identification System Based on the BIOMIMETIC PATTERN RECOGNITION , 2003 .

[6]  David P. Casasent,et al.  Classifier and shift-invariant automatic target recognition neural networks , 1995, Neural Networks.

[7]  Vladimir Vapnik,et al.  The Nature of Statistical Learning , 1995 .

[8]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[9]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[10]  Wang Shou Analysis and Theory of High-Dimension Space Geometry for Artificial Neural Networks , 2002 .

[11]  Wang Shou Discussion on the Basic Mathematical Models of Neurons in General Purpose Neurocomputer , 2001 .

[12]  Stephen Grossberg,et al.  Fast-learning VIEWNET architectures for recognizing three-dimensional objects from multiple two-dimensional views , 1995, Neural Networks.

[13]  Ramesh C. Jain,et al.  Three-dimensional object recognition , 1985, CSUR.