Principal Feature Extraction of Image Data Using Neural Networks of Learning Algorithrn Based on Steepest Descent and Dynamic Tunneling


The Transactions of the Korea Information Processing Society (1994 ~ 2000), Vol. 6, No. 5, pp. 1393-1402, May. 1999
10.3745/KIPSTE.1999.6.5.1393,   PDF Download:

Abstract

This paper proposes an efficient principal feature extraction of the image data using neural networks of a new learning algorithm. The proposed learning algorithm is a backpropagation(BP) algorithm based on the steepest descent and dynamic tunneling. The BP algorithm based on the steepest descent is applied for high-speed optimization, and the BP algorithm based on the dynamic tunneling is also applied for global optimization. Converging to the local minimum by the BP algorithm of steepest descent, the new initial weights for escaping the local minimum is estimated by the BP algorithm of dynamic tunneling. The proposed algorithm has been applied to the 3 image data of 12?12 pixels and the Lenna image of 128?128 pixels respectively. The simulation results show that the proposed algorithm has better performances of the convergence and the feature extraction, in comparison with those using the Sanger method and the Foldiak method for single-layer nerual networks and the BP algorithm for multilayer neural network.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
C. Y. Hyun, "Principal Feature Extraction of Image Data Using Neural Networks of Learning Algorithrn Based on Steepest Descent and Dynamic Tunneling," The Transactions of the Korea Information Processing Society (1994 ~ 2000), vol. 6, no. 5, pp. 1393-1402, 1999. DOI: 10.3745/KIPSTE.1999.6.5.1393.

[ACM Style]
Cho Yong Hyun. 1999. Principal Feature Extraction of Image Data Using Neural Networks of Learning Algorithrn Based on Steepest Descent and Dynamic Tunneling. The Transactions of the Korea Information Processing Society (1994 ~ 2000), 6, 5, (1999), 1393-1402. DOI: 10.3745/KIPSTE.1999.6.5.1393.