文章基本信息

标题：IMAGE SEGMENTATION METHOD FOR COTTON MITE DISEASE BASED ON COLOR FEATURES AND AREA THRESHOLDING
本地全文：下载
作者：DIAO ZHIHUA ; WANG HUAN ; SONG YINMAO 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：2013
卷号：48
期号：1
页码：527-533
出版社：Journal of Theoretical and Applied
摘要：Cotton mite disease is a common disease. Taking the cotton mite disease as the research subject, a segmentation method based on color features and area thresholding is proposed under the complex background. The proposed algorithm is comprised of three main steps. First, to extract the analogous disease spots (disease spots and stems) from green plants. Second, some special characteristics are detected in gray histrogram, afterwards convert the segmented images into 8 bit gray-scale images based on single thresholding. Finally, compare the disease spots� area with stems� and then segmented binary images by using area thresholding. The experimental results show that this algorithm is of effective in segmenting cotton disease spots; the average correct extraction rate of the algorithm can reach 94.79%.
关键词：Image Segmentation; Cotton Mite Disease; Color Features; Area Thresholding