DocumentCode :
3642074
Title :
Hierarchical rule-based neural network for multi-object classification using invariant features
Author :
N. İmamoğlu;A. Eresen;A. M. Özbayoğlu
Author_Institution :
School of Computer Engineering, Nanyang Technological University, Nanyang Avenue, 639798 Singapore
fYear :
2011
fDate :
6/1/2011 12:00:00 AM
Firstpage :
296
Lastpage :
299
Abstract :
Feature extraction techniques play a vital part in pattern recognition applications. In order to achieve the best performance in a particular classification problem, the most appropriate feature extractor for the problem is pursued. In this paper, a Pseudo-Zernike Moments based model is used as the feature extractor due to its reliability in illumination and rotation invariant multi-class object classification. A Hierarchical Rule-Based Neural Networks (HRB-NN) approach is proposed to classify multi-class data using hierarchical classification based on similarity measures between different classes. HRB-NN performance is compared to Nearest Neighbor and Bayesian classifiers. For implementation, a database of 960 images (640 training, 320 testing) for 8 different objects is used. The proposed method was able to classify the given data without any failure by giving the best performance outperforming the other chosen classifiers.
Keywords :
"Feature extraction","Artificial neural networks","Bayesian methods","Training data","Pattern recognition","Training","Classification algorithms"
Publisher :
ieee
Conference_Titel :
Innovations in Intelligent Systems and Applications (INISTA), 2011 International Symposium on
Print_ISBN :
978-1-61284-919-5
Type :
conf
DOI :
10.1109/INISTA.2011.5946079
Filename :
5946079
Link To Document :
بازگشت