This paper addresses the pixel based classification of three dimensional objects from arbitrary views. To perform this task a coding strategy, inspired by the biological model of human vision, for pixel data is described. The coding strategy ensures that the input data is invariant against shift, scale and rotation of the object in the input domain. The image data is used as input to a class of self organizing neural networks, the Kohonen-maps or self-organizing feature maps (SOFM). To verify this approach two test sets have been generated: the first set, consisting of artificially generated images, is used to examine the classification properties of the SOFMs; the second test set examines the clustering capabilities of the SOFM when real world image data is applied to the network after it has been preprocessed to be invariant against shift, scale and rotation. It is shown that the clustering capability of the SOFM is strongly dependant on the invariance coding of the images.
[1]
Stephen Grossberg,et al.
Fast-learning VIEWNET architectures for recognizing three-dimensional objects from multiple two-dimensional views
,
1995,
Neural Networks.
[2]
Teuvo Kohonen,et al.
Self-Organizing Maps
,
2010
.
[3]
Karl-Friedrich Kraiss,et al.
Pixel based 3D object recognition with bidirectional associative memories
,
1997,
Proceedings of International Conference on Neural Networks (ICNN'97).
[4]
Alberto Del Bimbo,et al.
3D object classification using multi-object Kohonen networks
,
1996,
Pattern Recognit..
[5]
Alireza Khotanzad,et al.
Recognition and pose estimation of unoccluded three-dimensional objects from a two-dimensional perspective view by banks of neural networks
,
1996,
IEEE Trans. Neural Networks.