Rotation-Invariant Pattern Recognition: A Procedure Slightly Inspired on Olfactory System and Based on Kohonen Network
A computational scheme for rotation-invariant pattern recognition based on Kohonen neural network is developed. This scheme is slightly inspired on the vertebrate olfactory system, and its goal is to recognize spatiotemporal patterns produced in a two-dimensional cellular automaton that would represent the olfactory bulb activity when submitted to odor stimuli. The recognition occurs through a multi-layer Kohonen network that would represent the olfactory cortex. The recognition is invariant to rotations of the patterns, even when a noise lower than 1% is added.
KeywordsOlfactory Bulb Cellular Automaton Spatiotemporal Pattern Olfactory System Output Matrix
Unable to display preview. Download preview PDF.
- 3.Breakspear, M.: Perception of odors by a nonlinear model of the olfactory bulb. Int. J. Bifurcat. Chaos 11, 101–124 (2001)Google Scholar
- 14.Sachse, S., Galizia, C.G.: Role of inhibition for temporal and spatial odor representation in olfactory output neurons: a calcium imaging study. J. Neurophysiol. 87, 1106–1117 (2002)Google Scholar
- 15.Sheng, Y., Lejeune, C.: Invariant pattern recogniton using Fourier-Mellin transforms and neural networks. J. Optics (Paris) 22, 223–228 (1991)Google Scholar