TY  - CHAP
A1  - Elsen, Ingo
T1  - A pixel based approach to view based object recognition with self-organizing neural networks
T2  - IECON'98. Proceedings of the 24th Annual Conference of the IEEE Industrial Electronics Society
N2  - 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.
Y1  - 1998
SN  - 0-7803-4503-7
U6  - http://dx.doi.org/10.1109/IECON.1998.724032
N1  - Aachen, 31 August 1998 - 04 September 1998
SP  - 2040
EP  - 2044
PB  - IEEE
CY  - New York
ER  -