Rectification of remotely sensed images with artificial neural network

Raw digital images can not be used as maps because they contain geometric distortions which stem from the image acquisition process. To supply the same geometric integrity as a map, original raw images must be geometrically corrected and the distortions, such as variations in altitude, and earth curvature, must be compensated for. There are two techniques that can be used to correct the various types of geometric distortions present in digital image data: one is orbital geometry modelling and the other one, rather used in many image processing, is the transformation based on ground control points. In the last few years there has been a significant resurgence of interest in using artificial neural network algorithms for different image processing procedures. In this study besides the conventional image processing procedures, an artificial neural network algorithm for the rectification of the SPOT-P image of the study area in #stanbul was developed and applied for generating both new grids and corresponding brightness values. The rectification results were compared with those from the polynomials, and their merits and weakness were addressed.