The effects of training algorithms in MLP network on image classification

Author

Coskun, Nihan ; Yildirim, Tulay

Author_Institution

Dept. of Electron. & Commun. Eng., Yildiz Univ., Istanbul, Turkey

Volume

2

fYear

2003

fDate

20-24 July 2003

Firstpage

1223

Abstract

This paper presents the use of multilayer perceptrons (MLP) trained with various training algorithms for image analysis and pattern recognition. Given a data set of images with known classifications, a system can predict the classification of new images. However, the accuracy of the networks, having the same size and same learning parameters, changes according to training algorithm used in MLP. The effects of the different algorithms are investigated and the best learning methods were proposed for image segmentation.

Keywords

image classification; image segmentation; learning (artificial intelligence); multilayer perceptrons; MLP network; classification prediction; image analysis; image classification; image segmentation; learning parameters; multilayer perceptrons; pattern recognition; training algorithms effects; Classification tree analysis; Image analysis; Image classification; Image databases; Image segmentation; Intelligent networks; Learning systems; Multilayer perceptrons; Nonhomogeneous media; Pattern recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2003. Proceedings of the International Joint Conference on

ISSN

1098-7576

Print_ISBN

0-7803-7898-9

Type

conf

DOI

10.1109/IJCNN.2003.1223867

Filename

1223867