Abstract | ||
---|---|---|
In this paper we introduce a neural network implementation of fuzzy mathematical morphology operators and apply it to image denoising. Using a supervised training method and differentiable equivalent representations for the fuzzy morphological operators, we derive efficient adaptation algorithms to optimize the structuring elements. We can then design fuzzy morphological filters for processing multi-level or binary images. The convergence behavior of basic structuring elements for the opening filter and different signals, and its significance for other structuring elements of different shape is discussed. To illustrate the performance of the fuzzy opening filter we consider the removal of impulse noise in multi-level and binary images. |
Year | DOI | Venue |
---|---|---|
1998 | 10.1109/ICASSP.1998.678132 | PROCEEDINGS OF THE 1998 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-6 |
Keywords | Field | DocType |
digital filters,binary image,design,neural network,mathematical morphology,noise,shape,impulse noise,learning artificial intelligence,filtering,convergence,adaptive filters,morphology,binary images,neural networks | Neuro-fuzzy,Digital filter,Pattern recognition,Mathematical morphology,Computer science,Binary image,Fuzzy logic,Filter (signal processing),Adaptive filter,Artificial intelligence,Artificial neural network | Conference |
ISSN | Citations | PageRank |
1520-6149 | 1 | 0.54 |
References | Authors | |
7 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jinsung Oh | 1 | 32 | 4.91 |
L. F. Chaparro | 2 | 45 | 11.06 |