Share Email Print
cover

Proceedings Paper

Random neural network texture model
Author(s): Erol Gelenbe; Khaled F. Hussain; Hossam Abdelbaki
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

This paper presents a novel technique for texture modeling and synthesis using the random neural network (RNN). This technique is based on learning the weights of a recurrent network directly from the texture image. The same trained recurrent network is then used to generate a synthetic texture that imitates the original one. The proposed texture learning technique is very efficient and its computation time is much smaller than that of approaches using Markov Random Fields. Texture generation is also very fast. We have tested our method with different synthetic and natural textures. The experimental results show that the RNN can efficiently model a large category of homogeneous microtextures. Statistical features extracted from the co- occurrence matrix of the original and the RNN based texture are used to evaluate the quality of fit of the RNN based approach.

Paper Details

Date Published: 14 April 2000
PDF: 8 pages
Proc. SPIE 3962, Applications of Artificial Neural Networks in Image Processing V, (14 April 2000); doi: 10.1117/12.382903
Show Author Affiliations
Erol Gelenbe, Univ. of Central Florida (United States)
Khaled F. Hussain, Univ. of Central Florida (United States)
Hossam Abdelbaki, Univ. of Central Florida (United States)


Published in SPIE Proceedings Vol. 3962:
Applications of Artificial Neural Networks in Image Processing V
Nasser M. Nasrabadi; Aggelos K. Katsaggelos, Editor(s)

© SPIE. Terms of Use
Back to Top