文章基本信息

标题：ADJUSTMENT OF NORMALIZED CUT PARAMETERS USING NEURAL NETWORKS
本地全文：下载
作者：SAMIA ELSIMARIE ; BENBELLA SAYED ; AHMED OTHMAN 等
期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2020
卷号：98
期号：8
页码：1290-1300
出版社：Journal of Theoretical and Applied
摘要：Image segmentation is an important process that used in both quantitative and qualitative analysis of medical ultrasound images, but medical images have features of strong noise and poor contrast and the results of image segmentation may not be good with traditional segmentation methods. in this paper we segment breast ultrasound medical images based on texture features and graph cut ,gray- level spatial dependence matrix(GLSDM) used to extract texture feature parameters ,the similarities matrix is created according to the parameters of texture feature and gray intensity of pixels .normalized cut spectral graph theoretic framework used to segment image depending on the similarity matrix. This paper introduces a new approach to overcome the problems associated with medical image segmentation such that the proposed approach (Neural Normalized Cut) has the ability to adjust the parameters of normalized cut segmentation technique , Neural normalized Cut has applied for breast ultrasound images , the results show the ability of neural normalized cut to adjust multiple parameters and enhance image segmentation ,especially for medical images.
关键词：Medical Ultrasound Images;Texture Feature;Neural Networks;Gray;Level Spatial Dependence Matrix (GLSDM);Graph Cut;Image Segmentation;Thresholding;Normalized cut;Neural Normalized Cut Segmentation;Genetic Algorithms;K-Means;SURF.