DocumentCode :
2819147
Title :
Using Growing Neural Gas Networks to Represent Visual Object Knowledge
Author :
Donatti, Guillermo S. ; Wurtz, Rolf
Author_Institution :
Int. Grad. Sch. of Neurosci., Ruhr-Univ., Bochum, Germany
fYear :
2009
fDate :
2-4 Nov. 2009
Firstpage :
54
Lastpage :
58
Abstract :
We present a so-called neural map, a novel memory framework for visual object recognition and categorization systems. The properties of its computational theory include self-organization and intelligent matching of the image features that are used to build their object models. Its performance for representing the visual object knowledge comprised by these models and for recognizing unknown objects is measured using three different types of image features, which extract different granularity of information from object views of the ETH-80 image set. The obtained experimental results slightly outperform previous ones using PCA-based methods on the same image set, and they suggest that the medium-sized image features maximize the object models´ informativeness and distinctiveness.
Keywords :
feature extraction; knowledge representation; neural nets; principal component analysis; PCA-based methods; computational theory; image features; intelligent matching; neural gas networks; neural map; object categorization; visual object knowledge representation; visual object recognition; Artificial intelligence; Computational intelligence; Data mining; Feature extraction; Humans; Image recognition; Layout; Neuroscience; Object recognition; Shape; Computational Neuroscience; Computer Vision; Growing Neural Gas Networks; Organic Computing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Tools with Artificial Intelligence, 2009. ICTAI '09. 21st International Conference on
Conference_Location :
Newark, NJ
ISSN :
1082-3409
Print_ISBN :
978-1-4244-5619-2
Electronic_ISBN :
1082-3409
Type :
conf
DOI :
10.1109/ICTAI.2009.81
Filename :
5363467
Link To Document :
بازگشت