Segmentation and Denoising of Noisy Satellite Images based on Modified Fuzzy C Means Clustering and Discrete Wavelet Transform for Information Retrieval

Image segmentation is one of the vital steps in satellite image processing for gathering information from the satellite images. Most of the satellite images suffer from noise and other disturbances. Sometimes noise pixels may be considered as image pixels resulting poor images. In this paper, to study the effectiveness of noise in the satellite images, different types of noises like Gaussian, poisson, salt & pepper and speckle noise are added to the original image. The discrete wavelet transform (DWT) and Bayes Shrink soft thresholding is then applied for the removal of noisy pixels and smoothen the image. In the final stage, the fuzzy based modified FCM clustering is performed on the denoised images to produce clusters or segmented result. This approach has been applied on the satellite images of various resolutions. The experimental results show that the proposed algorithm is efficient for providing robustness to noisy images. Keyword- Image Segmentation, Fuzzy-C-Means Clustering, Noise, Denoising, DWT, Threshoding