3D BASED REMOTE SENSING IMAGE CONTRAST ENHANCEMENT USING SVM

A satellite image is full of noisy information thus it faces many problems just to get a clear view of a location. Various image enhancement techniques are used to remove the unwanted data from the satellite image. Existing techniques fail to clear noise from the satellite image enough to be used for real time purposes. To overcome this problem we propose SVM which has two significant parts. The first one is the interior point method and second one is boundary value selection. The majority of color histogram equalization methods do not yield uniform histogram in gray scale. Contrast of the converted image is worse in 1D and 2D, to overcome this we move on to 3D. The new satellite image contrast enhancement technique is based on the discrete wavelet transform (DWT) which decomposes the input image into the four frequency sub bands by using DWT and estimates the singular value matrix of the low- low sub band image, and, then, it reconstructs the enhanced image by applying inverse DWT.