Abstrakt

Shadow Detection and Reconstruction in Satellite Images using Support Vector Machine and Image In-painting

Hima P. N, Biju V. G

In this paper an approach for the detection of shadows in satellite images using Support Vector Machine is proposed. The first step is to classify the shadow and non-shadow regions with the help of Support Vector Machine. In order to remove the noise in the classified image median filter is used. The reconstruction of the shadow areas is done by using image in-painting technique. This technique is used to retain the missing parts in an image due to shadows. The performances are evaluated by means of Peak Signal-to-Noise Ratio (PSNR), and Mean Square Error (MSE).