Neural Network Based Interpolation of Wind Tunnel Test Data

Abstract

Extracting more information from multi source images is an attractive thing in remotely sensed image processing, which is recently called data fusion. There are many image fusion methods so far, such as IHS, PC A, WT, GLP etc. Among these methods WT and GLP methods can preserve more image spectral characters than others. So here we adopt wavelet method (as it is proposed to improve the geometric resolution of the images) and prove how it is better than GLP using qualitative and statistical data. Generally, in multi resolution analysis, the images are decomposed into low and high frequency parts and then using different fusion rules, the low frequency parts alone are fused while the high frequency information such as edges, borders, corners etc. are unpreserved. So the resultant image is not accurate. Here we adopt a novel approach to decompose the original images into high and low frequency parts to the smallest pixel (to get high resolution) and then fuse both the parts separately using different fusion rules to get an accurate and high resolution image with greater details. The results are applied to different fields and verified on the basis of qualitative and quantitative analysis.