A novel QIM-DCT based fusion approach for classification of remote sensing images via PSO and SVM models
- PDF / 1,555,454 Bytes
- 16 Pages / 595.276 x 790.866 pts Page_size
- 103 Downloads / 170 Views
(0123456789().,-volV)(0123456789().,-volV)
METHODOLOGIES AND APPLICATION
A novel QIM-DCT based fusion approach for classification of remote sensing images via PSO and SVM models K. Uma Maheswari1 • S. Rajesh2
Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Fusion of panchromatic and multispectral images has become a research interest for the classification of remote sensing images. The spectral and spatial resolutions of different images give better information with the aid of image classification. However, fusing pixels for various satellite images is difficult due to the nature of original image consists of complex information. Similarly, most of the existing fusion algorithms implement a unified processing over the whole part of the image, thereby leaving certain important needs out of consideration. The main aim of our proposed approach is to fuse the images by gathering all important information from multiple images with minimum errors. In this paper, we propose a novel quantization index modulation with discrete contourlet transform-based fusion approach for classification of remote sensing images (LISS IV sensor). In order to improve the image fusion performance, we eliminate certain noises (salt, pepper, and Gaussian) using Bayesian filter with Adaptive Type-2 Fuzzy System. After image fusion, we make image classification by two steps of processes including deep multi-feature extraction and feature selection. Multiple features such as spectral, shape, global and local features are extracted using Affine Transformation (0, 90, 180, and 270), and then the best set of features are chosen by mutual information and maximal information coefficients. Finally, the image is classified into seven classes using PSO and SVM namely Urban, Vegetation, Wetland, Tank, Water Area, Bare Land, and Roadways. MATLAB R2017b has been used for evaluation of the LISS IV images. Experimental results revealed that our proposed approach is very effective in terms of their classification accuracy. Keywords Image fusion Quantization index modulation with discrete contourlet transform Bayesian filter with adaptive type-2 fuzzy system Image classification and particle swarm optimization with support vector machine Abbreviations QIM Quantization index modulation SVM Support vector machine PSO Particle swarm optimization MIC Maximal information coefficient MI Mutual information PMF Primary membership function
SMF DCT A-T2FLS PCA WPT GMP
Secondary membership function Discrete contourlet transform Adaptive type-2 fuzzy system Principal component analysis Wavelet packet transform Gaussian membership function
Communicated by V. Loia. & K. Uma Maheswari [email protected] S. Rajesh [email protected] 1
Department of Computer Science and Engineering, University College of Engineering Ramanathapuram, Ramanathapuram, India
2
Department of Information Technology, MepcoSchlenk Engineering College (Autonomous), Sivakasi, India
1 Introduction Imagefusion is an emerging task in both computer vision
Data Loading...
