Universiti Teknologi Malaysia Institutional Repository

Classification of aircraft images using different architectures of radial basis function neural network : a performance comparison

Saad, Puteh and Ibrahim, Subariah and Mahshos, Nur Safawati (2008) Classification of aircraft images using different architectures of radial basis function neural network : a performance comparison. Jurnal Teknologi Maklumat, 20 (4). pp. 1-16. ISSN 0128-3790

[img]
Preview
PDF - Published Version
941Kb

Abstract

Four Radial Basis Network architectures are evaluated for their performance in terms of classification accuracy and computation time. The architectures are Radial Basis Neural Network, Goal Oriented Radial Basis Architecture, Generalized Gaussian Network, Probabilistic Neural Network. Zemike Invariant Moment is utilized to extract a set of features from the aircraft image. Each of the architectures is used to'classify the image feature vectors. It is found that Generalized Gaussian Neural Network Architecture portrays perfect classification of 100% at a fastest time. Hence, the Generalized Gaussian Neural Network Architecture has a high potential to be adopted to classify images in a real-time environment.

Item Type:Article
Uncontrolled Keywords:zemike invariant moment, aircraft image classification, radial basis neural network, generalized gaussian network, probabilistic neural network
Subjects:Q Science > QA Mathematics > QA76 Computer software
Divisions:Computer Science and Information System (Formerly known)
ID Code:10701
Deposited By: Ms Zalinda Shuratman
Deposited On:25 Oct 2010 01:48
Last Modified:25 Oct 2010 01:48

Repository Staff Only: item control page