ANFIS Based Land Cover/Land Use Mapping of LISS IV Imagery Using Optimized Wavelet Packet Features
- PDF / 870,792 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 96 Downloads / 246 Views
RESEARCH ARTICLE
ANFIS Based Land Cover/Land Use Mapping of LISS IV Imagery Using Optimized Wavelet Packet Features S. Rajesh & S. Arivazhagan & K. Pratheep Moses & R. Abisekaraj
Received: 27 October 2012 / Accepted: 1 April 2013 # Indian Society of Remote Sensing 2013
Abstract Digital image classification is the process of sorting all the pixels in an image into a finite number of individual classes. But, it is difficult to classify satellite images since they include both pure pixels and boundary pixels. The boundary pixels are ‘mixed’ pixels, representing an area occupied by more than one ground cover. That is, class boundaries represented by pixels, are not sharp but fuzzy. This paper discuses the application of Adaptive Neuro-Fuzzy inference system (ANFIS) for classification of remotely sensed images that contains mixed pixels. Decision making was performed in two stages: feature extraction using the Wavelet Packet Transforms (WPT) and the ANFIS trained with the back propagation gradient descent method in combination with the least squares method for classification. Genetic Algorithms (GA) based approach is analysed for the selection of a subset from the combination of Wavelet Packet Statistical Features (WPSF) and Wavelet Packet Co-occurrence (WPC) textural feature set, which are used to classify the LISS IV images. GA has been employed to reduce the complexity and increase the Electronic supplementary material The online version of this article (doi:10.1007/s12524-013-0276-1) contains supplementary material, which is available to authorized users. S. Rajesh (*) Department of MCA, Mepco Schlenk Engineering College, Sivakasi 626005, India e-mail: [email protected] S. Arivazhagan Department of ECE, Mepco Schlenk Engineering College, Sivakasi 626005, India K. P. Moses Department of Planning, School of Architecture and Planning, Anna University, Chennai 600025, India R. Abisekaraj Naval Science and Technological Laboratory, DRDO, Vishakapatanam 530 627, India
accuracy of classification. Four indices—user’s accuracy, producer’s accuracy, overall accuracy and kappa co-efficient are used to assess the accuracy of the classified data. Experiments show that the proposed approach produces better results compared to the results obtained when classical classifiers are used. Keywords Wavelet packet decomposition . Wavelet statistical feature . Wavelet co-occurrence feature . Normalized vegetation index . Genetic algorithms . Adaptive neuro-fuzzy inference system . Mixed pixels classification
Introduction Land use/Land cover classification of satellite images is an important activity for extracting geospatial information for military and civil purposes like inaccessible areas. It is difficult to classify satellite images, since geographical information is imprecise in nature. During land cover mapping, a piece of land with sparse grass can be classified into either grassland or soil. There is not a well-specified criterion for distinguishing between the two cover-types. If hard classification algorithm is applied
Data Loading...
