Comparison of CBF, ANN and SVM classifiers for object based classification of high resolution satellite images

Author

Buddhiraju, Krishna Mohan ; Rizvi, Imdad Ali

Author_Institution

Centre of Studies in Resources Eng., Indian Inst. of Technol. Bombay, Mumbai, India

fYear

2010

fDate

25-30 July 2010

Firstpage

40

Lastpage

43

Abstract

Image classification is an important task for many aspects of global change studies and environmental applications. This paper emphasizes on the analysis and usage of different advanced image classification techniques like Cloud Basis Functions (CBFs) Neural Networks, Artificial Neural Networks (ANN) and Support Vector Machines (SVM) for object based classification to get better accuracy. For comparison, adaptive Gaussian filtered images were classified using ANN and post-processed using relaxation labeling process (RLP). The results are demonstrated using high spatial resolution remotely sensed images.

Keywords

Gaussian processes; adaptive filters; geophysical image processing; geophysics computing; image classification; image resolution; neural nets; remote sensing; support vector machines; adaptive Gaussian filtered image classification; artificial neural network; cloud basis function neural network; environmental application; high resolution satellite images; object based classification; relaxation labeling process; remotely sensed imaging; spatial resolution; support vector machine classifier; Accuracy; Artificial neural networks; Classification algorithms; Image segmentation; Kernel; Pixel; Support vector machines; ANN; High Resolution Satellite Images; Object Based Image Classification; Radial Basis Functions; SVM;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium (IGARSS), 2010 IEEE International

Conference_Location

Honolulu, HI

ISSN

2153-6996

Print_ISBN

978-1-4244-9565-8

Electronic_ISBN

2153-6996

Type

conf

DOI

10.1109/IGARSS.2010.5652033

Filename

5652033