Abstract—In this paper, we proposed a novel global segmentation method for satellite images with active contour model on noisy images with ten percentage of salt and pepper. It was implemented with a special technique selective binary and Gaussian filtering regularized level set evolution. First we selectively penalize the level set function to be binary and then use a Gaussian smoothing kernel to regularize it. The advantages of our method is a new region based signed pressure force(SPF) function is proposed, which can step effectively the contour at weak or blurred edges and automatically detect the interior and exterior boundaries with the initial contour being anywhere in the images effected with noise. The proposed method can implement by the simple finite difference scheme. Experiments on satellite images with noise demonstrate the advantages of the proposed method over the Chan-vase (CV) active contour in terms of the number of Iterations.

Index Terms—Active contours, image segmentation, Chan-vase model, level set method.

K. Ramudu, G. R. Reddy, and A. Srinivas are with the Department of ECE, Department of ECE, KITS, Warangal-15, KakatiyaUniversity, India (e-mail: grr_ece@yahoo.com, ramudukama@gmail.com, srinivas_azmeera@yahoo.com).
T. R. Krishna is with the Department of Physics, JNT University, Hyderabad, India.

Cite: K. Ramudu, G. Raghotham Reddy, A. Srinivas, and T. Radha Krishna, "Global Region Based Segmentation of Satellite and Medical Imagery with Active Contours and Level Set Evolution on Noisy Images," International Journal of Applied Physics and Mathematics  vol. 2, no. 6, pp. 449-453, 2012.