Change Detection of Remote Sensing Images with Semi-supervised Multilayer Perceptron

Authors:
Swarnajyoti Patra;Susmita Ghosh;Ashish Ghosh
Affiliations:
Department of Computer Science and Engineering Jadavpur University, Kolkata 700 032, India. E-mail: {patra_swarna,susmita_de}@rediffmail.com;Department of Computer Science and Engineering Jadavpur University, Kolkata 700 032, India. E-mail: {patra_swarna,susmita_de}@rediffmail.com;(Correspd.) Machine Intelligence Unit and Center for Soft Computing Research Indian Statistical Institute, B.T.Road, Kolkata 700 108, India. E-mail: ash@isical.ac.in
Venue:
Fundamenta Informaticae
Year:
2008

Citing 10
Cited 0

Fuzzy sets and fuzzy logic: theory and applications

Fuzzy sets and fuzzy logic: theory and applications
Text Classification from Labeled and Unlabeled Documents using EM

Machine Learning - Special issue on information retrieval
Training Algorithm with Incomplete Data for Feed-ForwardNeural Networks

Neural Processing Letters
Using Unlabelled Data to Train a Multilayer Perceptron

Neural Processing Letters
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
Remote Sensing Digital Image Analysis: An Introduction

Remote Sensing Digital Image Analysis: An Introduction
Feature-based approach to semi-supervised similarity learning

Pattern Recognition
Unsupervised Change Detection in Remote-Sensing Images Using Modified Self-Organizing Feature Map Neural Network

ICCTA '07 Proceedings of the International Conference on Computing: Theory and Applications
An adaptive semiparametric and context-based approach to unsupervised change detection in multitemporal remote-sensing images

IEEE Transactions on Image Processing
Image change detection algorithms: a systematic survey

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

A context-sensitive change-detection technique based on semi-supervised learning with multilayer perceptron is proposed here. In order to take contextual information into account, input patterns are generated considering each pixel of the difference image along with its neighboring pixels. A heuristic technique is suggested to identify a few initial labeled patterns without using ground truth information. The network is initially trained using these labeled data. The unlabeled patterns are iteratively processed by the already trained perceptron to obtain a soft class label. Experimental results, carried out on two multispectral and multitemporal remote sensing images, confirm the effectiveness of the proposed approach.