Automatic Recognition of Village in Remote Sensing Images by Support Vector Machine Using Co-Occurrence Matrices
Abstract:Accurate and comprehensive extraction of village is meaningful for a land consolidation project. In consolidation work, it is necessary to recognize village objects quickly and accurately. The high resolution remote sensing images make it possible. However, a highly automatic classification is not easy to attain, because remote sensing images usually contain many complex factors and mixed pixels. The goal of this paper is to develop an automatic classifier for village recognition. Our approach uses a support vector machine (SVM) as a classifier, which tries to detect pixels belonging to villages in the image and reject the others. Texture features are used as inputs to the SVM classifier for identifying villages. The texture analysis is based on the grey-level co-occurrence matrix method. Here several co-occurrence parameters are computed and then compared. Three distinct co-occurrence texture features are selected for recognition. To improve the accuracy of the recognition, threshold filter, erosion filter and dilation filters are carried out after the SVM classification. Classification accuracy is measured by Kappa coefficients. The experimental results show that there is a well-recognized outcome. And it shows that texture-related features such as co-occurrence matrices might be high effective discriminators for high resolution remote sensing images and that SVM classification systems might lead to the successful discrimination of targets when fed with appropriate information.
Document Type: Research Article
Publication date: January 1, 2012
More about this publication?
- The growing interest and activity in the field of sensor technologies requires a forum for rapid dissemination of important results: Sensor Letters is that forum. Sensor Letters offers scientists, engineers and medical experts timely, peer-reviewed research on sensor science and technology of the highest quality. Sensor Letters publish original rapid communications, full papers and timely state-of-the-art reviews encompassing the fundamental and applied research on sensor science and technology in all fields of science, engineering, and medicine. Highest priority will be given to short communications reporting important new scientific and technological findings.
- Editorial Board
- Information for Authors
- Subscribe to this Title
- Terms & Conditions
- Ingenta Connect is not responsible for the content or availability of external websites