中国农业科学院农业信息研究所 中国农学会
Agricultural Information Institute of CAAS China Association of Agricultural Science Societies
En
Ch
中国农业科学院农业信息研究所 中国农学会 主办

AI检索

订阅

返回顶部
当前位置: 首页 > 文章 > 一种基于小波变换的图像过渡区提取及分割方法 农业工程学报 2005,21 (11)
Position: Home > Articles > Image transition region extraction and segmentation method based on wavelet transform Transactions of the Chinese Society of Agricultural Engineering 2005,21 (11)

一种基于小波变换的图像过渡区提取及分割方法

作  者：
赵茂程;郑加强;凌小静
单  位：
南京交通规划研究所;南京林业大学机械电子工程学院
关键词：
小波变换;小波包;过渡区;树木图像;分割;阈值;神经网络
摘  要：
具有复杂背景的树木图像的分割对于精确对靶施药及智能化植保机械的设计具有重要意义。为实现树木图像的精确分割,针对该类图像的特点,该文提出了一种基于小波变换的过渡区提取树木图像分割方法。通过对比小波变换系数、小波变换系数聚类以及小波包系数,最终选取了同时能够分解出更多高频、低频信息的小波包变换系数提取特征,根据小波包变换系数定义了小波能量比参数,将小波能量比参数值归一化为图像灰度值,采用自适应阈值和神经网络两种方法提取了过渡区,实现了具有复杂背景树木图像的分割。试验表明,该方法分割精度高,对于分割复杂背景的树木图像具有特别意义。
译  名：
Image transition region extraction and segmentation method based on wavelet transform
作  者：
Zhao Maocheng~1,Zheng Jiaqiang~1,Ling Xiaojing~2(1.College of Mechanical and Electronic Engineering,Nanjing Forestry University,Nanjing 210037,China;2.Nanjing Institute of City Transportation Planning,Nanjing 210029,China)
关键词：
wavelet transform;wavelet box;transition region;tree image;segmentation;threshold;neural(network)
摘  要：
It is very important to segment the complicated tree image precisely in precision toward-target pesticide application and intelligent plant-protection machinery design.The segmentation method based on image transition region extraction was supported in view of tree image features.The wavelet transform feature coefficients which could break down much more high-frequent and low-frequent information were determined by comparing wavelet transform coefficients,coefficient clustering and wavelet box coefficients.Wavelet energy ratio parameter was(defined) based on wavelet feature coefficients and clustered into image gray value.Both self-adjusting threshold and neural network methods were employed to extract the transition area on which the tree images with complicated background were segmented based.The experiments showed that the images were segmented precisely and the method was superior to other methods in segmenting complicated images.

相似文章

导出引用
计量
文章访问数: 7
HTML全文浏览量: 0
PDF下载量: 0

所属期刊

推荐期刊

友情链接Friendly link
农业信息研究所Agricultural information institute 农业智能知识服务平台Agricultural intelligent knowledge service platform 农业学术服务平台Agricultural Knowledge Service System 中国知网CNKI 维普网VIP 万方WANFANG DATA
联系我们Contact us

电话Tell：010-82109652-808

邮箱E-mail：agrijournal@caas.cn

服务Service
关于我们About us 意见建议Opinions and suggest
版权说明Copyright
单位：中国农业科学院农业信息研究所 中国农学会 © 2017中国农业科学院农业信息研究所 ICP备案号：京ICP备09089781号-46