Segmentation of Satellite and Medical Imagery using Homomorphic Filtering based Level Set Evolution

Abstract

Objectives: The objective of this paper is to detection of the tissues and tumors, from medical images and oil spill regions and cloud regions from SAR Images respectively. Methods/Statistical Analysis: A novel region- based segmentation method for satellite and medical imagery using Homomorphic Filtering based Level Set Evolution (HLSE) approach. In real world images intensity inhomogeneity occurs, Segmentation of such images is a considerable challenge in image processing. Region based segmentation algorithms are widely used for intensity homogeneity of the Region of Interest (ROI). These images are still a tedious task and cumbersome due to weak contrast and poor resolution of images etc. The automatic segmentation of such images is very difficult. The main reason is a large amount of inhomogeneity present in the background and foreground of real world image. The conventional methods like C-V model and Distance Regularized Level Set (DRLS) method lead to getting improper segmentation with unconvinced results. Finding: We proposed an efficient segmentation method on satellite and medical using Homomorphic Filtering based Level Set Evolution (HLSE) approach. In the pre-processing step, we extract the illumination and reflectance components from the original image with the help of homomorphic decomposition process. Later, in the post- processing step, the illumination and reflectance images are applied to the level set model for accurate and robust segmentation. Improvements/Applications: The proposed segmentation results are effectiveness, superior and accurate compared to conventional methods. This new approach is very helpful for detection of the white matter and gray matter, cancerous cells in brain and bone in medical images. Similarly for SAR images detection of the oil slick, cloud regions etc.