Please use this identifier to cite or link to this item:
Title: Texture classification using ART-based neural networks and fractals
Authors: Kasparis, Takis 
Charalampidis, Dimitrios
Georgiopoulos, Michael N.
Keywords: Classification;Fractals;Computer vision;Neural networks
Issue Date: 1998
Publisher: SPIE
Source: Signal Processing, Sensor Fusion, and Target Recognition VII, 1998, Orlando, Florida
Abstract: In this paper texture classification is studied based on the fractal dimension (FD) of filtered versions of the image and the Fuzzy ART Map neural network (FAMNN). FD is used because it has shown good tolerance to some image transformations. We implemented a variation of the testing phase of Fuzzy ARTMAP that exhibited superior performance than the standard Fuzzy ARTMAP and the 1-nearest neighbor (1-NN) in the presence of noise. The performance of the above techniques is tested with respect to segmentation of images that include more than one texture.
ISSN: 0277786X
DOI: 10.1117/12.327099
Rights: © 1998 SPIE
Type: Conference Papers
Appears in Collections:Δημοσιεύσεις σε συνέδρια/Conference papers

Show full item record

Citations 20

checked on Dec 9, 2018

Page view(s)

Last Week
Last month
checked on Dec 10, 2018

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.