文章基本信息

标题：Tree Image Segmentation Based on an Improved Two-Dimensional Otsu Algorithm
本地全文：下载
作者：Honge Ren ; Yang Zhou ; Meng Zhu 等
期刊名称：International Journal of Hybrid Information Technology
印刷版ISSN：1738-9968
出版年度：2016
卷号：9
期号：9
页码：199-210
出版社：SERSC
摘要：Influenced by light, houses,street lamps and other factors, tree imagesoften contain noise and complexbackground information. The existing Otsu segmentationalgorithms have deficienciessuch as poor anti-noise capability,ignoringthe class cohesionand so on.Based on the traditional gray value-neighborhood average gradient Otsu segmentation method,we propose animproved two-dimensional Otsu algorithmfor tree image segmentation. The algorithm takes into account the between-class distance and within-class distance, which combined the average variance concept of two categories and proposed new threshold selectionmethod, and reduce the interferenceofnoise effectively. To achieve the best segmentation and reduce over-segmentation of background information, a method of removingsmall areas and morphological processingareused to optimize segmentation results. Experimental results show that the proposedalgorithm has a good inhibitioneffectonnoiseand the effectof treeimage segmentationisbetter than that ofthe traditionalone.
关键词：noise; ;two;-;dimensional Otsu; image segmentation;within;-;class distance