Advances in Self-Organizing Maps pp 105-114
Sparse Coding Neural Gas Applied to Image Recognition
- Cite this paper as:
- Coman H., Barth E., Martinetz T. (2013) Sparse Coding Neural Gas Applied to Image Recognition. In: Estévez P., Príncipe J., Zegers P. (eds) Advances in Self-Organizing Maps. Advances in Intelligent Systems and Computing, vol 198. Springer, Berlin, Heidelberg
A generalization of the Sparse Coding Neural Gas (SCNG) algorithm for feature learning is proposed and is then discussed in the context of modern classifier techniques for images. Two versions are presented. The latter obtains faster convergence by exploiting the nature of particular feature coding methods. The algorithm is then used as part of a larger image classification system, which is tested on the MNIST handwritten digit dataset and the NORB object dataset, obtaining results close to state-of-the-art methods.
KeywordsNeural Gas Sparse Coding Sparse Coding Neural Gas Image Recognition Matching Pursuit
Unable to display preview. Download preview PDF.