International Journal of Pharma and Bio Sciences
ijpbs.net
editorijpbs@rediffmail.com (or) editorofijpbs@yahoo.com (or) prasmol@rediffmail.com
10.22376/ijpbs.2019.10.1.p1-12
Volume 8 Issue 3
2017 (July - September)
Detection of kidney fault using threshold Segmentation method
Image Enrichment is the first and foremost step that has to be done in all image processing applications. It is used to improve the quality of digital images. In this paper kidney is fully segmented into four components: renal cortex, renal pelvis, renal column and renal medulla .The segmentation is done with the threshold segmentation method. The segmented image is undergone with four types of noise: salt and pepper noise, gaussian noise, speckle noise and poisson noise influenced in kidney smear image and their removal using four types of filters : mean filter, median filter, gaussian filter and wiener filter in order to judge the efficiency of various filters over the different kind of noise. This enhanced image, in turn, undergoes further processing to extract valuable information. Segmentation is a method used to split the image into different pixel regions with similar attributes. Thresholding is the process used to segment the image. Extracting features from the region of interest (ROI) is a major step in image processing. These features are used to identify the specific characteristic and parameters of an image, which helps classification explained. The features of the nucleus alone have so far been considered sufficient to classify images. This work investigates whether the premise stated is true. The aim is to segment the ROI from the images, but due to problems with overlapping, the entire cell is segmented and, thereafter, the ROI alone needs to be separated. The classification rate is 87% and the disadvantage of the system is that misclassification occurs in adjacent classes since this method cannot differentiate between the classes. For estimation of parametric values we can use MSE, NAE, NK, PSNR.
SP.CHOKKALINGAM AND SAMIR BRAHIM BELHAOUARI
Kidney, noise, filters, parametric value, Localization of the Kidney, AAM.
995-1001