Open AccessImproving the Spatial Resolution of Real Time Satellite Image Fusion Using 2D Curvelet Transform
Author(s) -
Gandla Maharnisha,
R. Veerasundari,
Gandla Roopesh Kumar,
Arunraj
Publication year - 2018
Publication title -
international journal of engineering and technology
Language(s) - English
Resource type - Journals
ISSN - 2227-524X
DOI - 10.14419/ijet.v7i2.19.15047
Subject(s) - curvelet , panchromatic film , image fusion , artificial intelligence , multispectral image , image resolution , computer science , pattern recognition (psychology) , mean squared error , computer vision , principal component analysis , fusion , adaptive histogram equalization , image processing , mathematics , image (mathematics) , histogram equalization , wavelet transform , statistics , linguistics , philosophy , wavelet
The fused image will have structural details of the higher spatial resolution panchromatic images as well as rich spectral information from the multispectral images. Before fusion, Mean adjustment algorithm of Adaptive Median Filter (AMF) and Hybrid Enhancer (combination of AMF and Contrast Limited Adaptive Histogram Equalization (CLAHE)) are used in the pre-processing. Here, conventional Principal Component image fusion method will be compared with newly modified Curvelet transform image fusion method. Principal Component fusion technique will improve the spatial resolution but it may produce spectral degradation in the output image. To overcome the spectral degradation, Curvelet transform fusion methods can be used. Curvelet transform uses curve which represents edges and extraction of the detailed information from the image. Curvelet Transform of individual acquired low-frequency approximate component of PAN image and high-frequency detail components from PAN and MS image is used. Peak Signal to Noise Ratio (PSNR) and Root Mean Square Error (RMSE) are measured to evaluate the image fusion accuracy.