Abstract
Object extraction algorithms with a Neural Network (NN) are described. The objective function to be minimized for object extraction from a scene is shown to be similar to the expression of energy of a neural network. A modified version of Hopfield's Neural Network model is used here. The weights and input biases are given in such a way that the network self-organizes to form compact clusters. Both the discrete and the continuous dynamics of the network have been used for this purpose. Performance of the proposed methods has been compared with that of the relaxation technique.
Dates
Type | When |
---|---|
Created | 20 years, 9 months ago (Nov. 24, 2004, 2:50 p.m.) |
Deposited | 6 years ago (Aug. 7, 2019, 8:47 a.m.) |
Indexed | 3 months, 1 week ago (May 18, 2025, 11:05 a.m.) |
Issued | 32 years, 8 months ago (Dec. 1, 1992) |
Published | 32 years, 8 months ago (Dec. 1, 1992) |
Published Online | 13 years, 9 months ago (Nov. 21, 2011) |
Published Print | 32 years, 8 months ago (Dec. 1, 1992) |
@article{GHOSH_1992, title={OBJECT BACKGROUND CLASSIFICATION USING HOPFIELD TYPE NEURAL NETWORK}, volume={06}, ISSN={1793-6381}, url={http://dx.doi.org/10.1142/s0218001492000485}, DOI={10.1142/s0218001492000485}, number={05}, journal={International Journal of Pattern Recognition and Artificial Intelligence}, publisher={World Scientific Pub Co Pte Lt}, author={GHOSH, ASHISH and PAL, NIKHIL R. and PAL, SANKAR K.}, year={1992}, month=dec, pages={989–1008} }