Improvised Method Of Tumor Segmentation Using Saliency

3049 WordsMar 9, 201513 Pages
Improvised Method of Tumor Segmentation Using Saliency M.A.Ruhaya Rameez Fathima Department of ECE National Engineering College Kovilpatti, India ruma986@gmail.com R.Manjula Devi M.E Department of ECE National Engineering College Kovilpatti, India manju.rengasamy@gmail.com Abstract—Saliency detection is used for many image processing applications. In this paper, single image saliency is used to improve the quality of the CT image. Single image saliency is obtained by measuring the contrast and spatial cue of a CT image. These cues are fused to obtain a kernel. In saliency filter the kernel is convolved with the CT image to improve the image quality for segmentation. The liver region is identified by adaptive thresholding and segmented by morphological operations and region growing method. The edge based active contour model using Distance Regularized Level Set Evolution is used to segment tumor from the liver region. The saliency based tumor segmentation provides better result in terms of accuracy. Index Terms—Saliency detection, Single image saliency, Morphological operation, Active contour model, Distance Regularized Level Set Evolution. I. Introduction Saliency detection is considered as a preferential allocation of computational resources. Saliency algorithms formulate on detecting the salient object from an individual image. The salient object is separated from the background using a set of novel features, including center surround histogram, color spatial
Open Document