文章基本信息

标题：A Novel Framework for Image Segmentation with De-Oversegmentation Technique
本地全文：下载
作者：B.V.Kasar ; S.S.Sherekar ; Dr. V. M. Thakare 等
期刊名称：International Journal of Electronics, Communication and Soft Computing Science and Engineering
印刷版ISSN：2277-9477
出版年度：2014
卷号：3
期号：Special
出版社：IJECSCSE
摘要：Image segmentation is an important processing step inmany image, video and computer vision applications. Extensiveresearch has been done in creating many different approachesand algorithms for image segmentation, but it is still difficult toassess whether one algorithm produces more accuratesegmentations than another, whether it be for a particular imageor set of images, or more generally, for a whole class of images.This paper focused on some of the segmentation technologies i.eImproved AFCM Method, Interactive Image Segmentation,Multichannel pulse coupled Neural Network and MDS basedmulti-resolution. These segmentation methods are analysed withtheir parameters it gives efficient result but it produces slight oversegmentation in the results due to the textured patterns ofgrassland and rough surface of rocks and cause noise in the imageproduced. So we will propose, De-Over segmentation methodreduce these problems. Segmentation can be used for objectrecognition, occlusion boundary estimation within motion orstereo systems, image compression, image editing, or imagedatabase look-up.
关键词：Segmentation for M-FISH with IAFCM Method;Interactive Segmentation Method; Multichannel pulse coupled Neural Network and MDS based multi-resolution