Image classification with the use of radial basis function neural networks and the minimization of the localized generalization error

Authors:
Wing W. Y. Ng;Andres Dorado;Daniel S. Yeung;Witold Pedrycz;Ebroul Izquierdo
Affiliations:
Department of Computing, The Hong Kong Polytechnic University, China and Media and Life Science Computing Lab, Shenzhen Graduate School, Harbin Institute of Technology, China;Department of Electronic Engineering, Queen Mary, University of London, UK;Department of Computing, The Hong Kong Polytechnic University, China and Media and Life Science Computing Lab, Shenzhen Graduate School, Harbin Institute of Technology, China;Department of Electrical and Computer Engineering, University of Alberta, Canada;Department of Electronic Engineering, Queen Mary, University of London, UK
Venue:
Pattern Recognition
Year:
2007

Citing 14
Cited 11

A sequential learning scheme for function approximation using minimal radial basis function neural networks

Neural Computation
Statistical Pattern Recognition: A Review

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Computationally Efficient Approach to Indoor/Outdoor Scene Classification

ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 4 - Volume 4
Image classification using hybrid neural networks

Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval
Introduction to MPEG-7: Multimedia Content Description Interface

Introduction to MPEG-7: Multimedia Content Description Interface
Old Fashioned State-of-the-Art Image Classification

ICIAP '03 Proceedings of the 12th International Conference on Image Analysis and Processing
On the algorithmic implementation of multiclass kernel-based vector machines

The Journal of Machine Learning Research
Bringing User Satisfaction to Media Access: The IST BUSMAN Project

IV '04 Proceedings of the Information Visualisation, Eighth International Conference
Overview of the MPEG-7 standard

IEEE Transactions on Circuits and Systems for Video Technology
Color and texture descriptors

IEEE Transactions on Circuits and Systems for Video Technology
Support vector machines for histogram-based image classification

IEEE Transactions on Neural Networks
Model complexity control for regression using VC generalization bounds

IEEE Transactions on Neural Networks
Implementation of an RBF neural network on embedded systems: real-time face tracking and identity verification

IEEE Transactions on Neural Networks
Localized Generalization Error Model and Its Application to Architecture Selection for Radial Basis Function Neural Network

IEEE Transactions on Neural Networks

Classifier learning with a new locality regularization method

Pattern Recognition
Classifier learning with a new locality regularization method

Pattern Recognition
The theoretical foundations of statistical learning theory based on fuzzy number samples

Information Sciences: an International Journal
Feature selection using localized generalization error for supervised classification problems using RBFNN

Pattern Recognition
Using a non-uniform self-selective coder for option pricing

Applied Soft Computing
On-line evolving image classifiers and their application to surface inspection

Image and Vision Computing
An annotation rule extraction algorithm for image retrieval

Pattern Recognition Letters
Computation of multilayer perceptron sensitivity to input perturbation

Neurocomputing
Image classification based on effective extreme learning machine

Neurocomputing
Local scaling heuristic-based regularization for pattern classification

Neurocomputing
A new matching strategy for content based image retrieval system

Applied Soft Computing

Quantified Score

Hi-index	0.01

Visualization

Abstract

Image classification arises as an important phase in the overall process of automatic image annotation and image retrieval. In this study, we are concerned with the design of image classifiers developed in the feature space formed by low level primitives defined in the setting of the MPEG-7 standard. Our objective is to investigate the discriminatory properties of such standard image descriptors and look at efficient architectures of the classifiers along with their design pursuits. The generalization capabilities of an image classifier are essential to its successful usage in image retrieval and annotation. Intuitively, it is expected that the classifier should achieve high classification accuracy on unseen images that are quite ''similar'' to those occurring in the training set. On the other hand, we may assume that the performance of the classifier could not be guaranteed in the case of images that are very much dissimilar from the elements of the training set. To follow this observation, we develop and use a concept of the localized generalization error and show how it guides the design of the classifier. As image classifier, we consider the usage of the radial basis function neural networks (RBFNNs). Through intensive experimentation we show that the resulting classifier outperforms other classifiers such as a multi-class support vector machines (SVMs) as well as ''standard'' RBFNNs (viz. those developed without the guidance offered by the optimization of the localized generalization error). The experimental studies reveal some interesting interpretation abilities of the RBFNN classifiers being related with their receptive fields.