Please use this identifier to cite or link to this item:
|Title:||Texture classification using ART-based neural networks and fractals||Authors:||Kasparis, Takis
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.||URI:||http://ktisis.cut.ac.cy/handle/10488/7164||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
checked on Dec 9, 2018
checked on Dec 10, 2018
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.