A Study on Behaviour of Neural Gas on Images

Neural gas basically a artificial neural network, motivated through self organizing map. The neural gas approach former successfully applied previously to clustering, image processing, and pattern recognition to extract the feature values and to find & identify unique pattern for the input database. In this research work five subjects of images are considered like animal, building, cloud, flower & vehicle, to find whether the neural gas is able to distinguish the pattern of images between them. Different types of parameters are used to extract the feature value of images using neural gas. The parameters are epochs, delta, iteration, alpha0 (initial value), alphaf (final value), lambda0 (initial value) & lambdaf (final value). Maximum and minimum difference values on these parameters are used as the feature values. These feature values are used to distinguish the images to each other. Their observed results on the basis of feature values are represented in the form of graphs, which yields good results.

[1]  Jürgen Schmidhuber,et al.  Self-organizing nets for optimization , 2004, IEEE Transactions on Neural Networks.

[2]  Thomas Villmann,et al.  Batch and median neural gas , 2006, Neural Networks.

[3]  Francesco Camastra,et al.  Combining neural gas and learning vector quantization for cursive character recognition , 2003, Neurocomputing.

[4]  Andreas Zell,et al.  Evolution Strategy with Neighborhood Attraction Using a Neural Gas Approach , 2002, PPSN.

[5]  P. N. Suganthan,et al.  Robust growing neural gas algorithm with application in cluster analysis , 2004, Neural Networks.

[6]  A. Kai Qin,et al.  Enhanced neural gas network for prototype-based clustering , 2005, Pattern Recognit..

[7]  Hsinchun Chen,et al.  Incorporating Web Analysis Into Neural Networks: An Example in Hopfield Net Searching , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[8]  Oscar Mayora-Ibarra,et al.  Competitive Learning Methods for Efficient Vector Quantizations in a Speech Recognition Environment , 2000, MICAI.

[9]  P ? ? ? ? ? ? ? % ? ? ? ? , 1991 .

[10]  Ponnuthurai N. Suganthan,et al.  Hierarchical overlapped neural gas network with application to pattern classification , 2000, Neurocomputing.

[11]  Thomas Martinetz,et al.  'Neural-gas' network for vector quantization and its application to time-series prediction , 1993, IEEE Trans. Neural Networks.

[12]  Shen Furao,et al.  An incremental network for on-line unsupervised classification and topology learning , 2006, Neural Networks.