Please use this identifier to cite or link to this item:
|Title:||Image pattern algorithms using neural networks||Authors:||Kasparis, Takis
Georgiopoulos, Michael N.
|Issue Date:||1990||Publisher:||SPIE||Source:||Hybrid Image and Signal Processing II, 1990, Orlando, Florida||Abstract:||The ability to classify texture regions in images is considered to be an important aspect of scene analysis. The information gained from such classification can be used by a computer vision system to assist in image segmentation as well as object identification. In this paper, the use of a neural network model in performing classification of images containing regular textures is investigated. The texture features used in the classification process are Hough transform-based descriptors. The performance and capabilities of the neural network approach are then compared to classical technique utilizing a linear associative memory.||URI:||http://ktisis.cut.ac.cy/handle/10488/7208||ISSN:||0277786X||DOI:||10.1117/12.21323||Rights:||© 1990 SPIE|
|Appears in Collections:||Δημοσιεύσεις σε συνέδρια/Conference papers|
Show full item record
checked on Jul 23, 2017
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.