形态学多尺度重建结合凹点匹配分割枸杞图像

针对枸杞分级过程中因图像噪声、光照不均匀和粘连等造成枸杞难以准确分割的问题,提出了一种基于形态学多尺度开闭重建结合凹点匹配的分割方法。首先提取原始图像的红色分量去除枸杞光照阴影噪声,利用形态学多尺度混合开闭重建对红色分量图像进行重建,平滑枸杞内部而保留轮廓边缘信息;然后采用8邻域跟踪算法提取粘连枸杞轮廓边缘;最后运用圆形模板检测粘连枸杞的轮廓凹点,以凹点间最短欧氏距离为匹配条件连接凹点对,并对匹配错误的凹点对进行修正,实现粘连枸杞分割。试验结果表明,该文方法分割准确率较高,而过分割率较低,相比标记控制的分水岭和直接凹点匹配分割等方法,对粘连枸杞分割效果较好,分割准确率可达到96%。该研究可为枸...

Full description

Saved in:
Bibliographic Details
Published in农业工程学报 Vol. 34; no. 2; pp. 212 - 218
Main Author 王小鹏;姚丽娟;文昊天;赵君君
Format Journal Article
LanguageChinese
Published 兰州交通大学 电子与信息工程学院,兰州,730070 2018
Subjects
农作物
凹点匹配
图像分割
图像采集
多尺度开闭重建
边缘提取
凹点匹配
multi-scale opening and closing reconstruction
农作物
image segmentation
多尺度开闭重建
图像分割
edge extraction
边缘提取
image acquisition
crops
concave points matching
图像采集
Online AccessGet full text
ISSN1002-6819
DOI10.11975/j.issn.1002-6819.2018.02.029

Cover

More Information
Summary:针对枸杞分级过程中因图像噪声、光照不均匀和粘连等造成枸杞难以准确分割的问题,提出了一种基于形态学多尺度开闭重建结合凹点匹配的分割方法。首先提取原始图像的红色分量去除枸杞光照阴影噪声,利用形态学多尺度混合开闭重建对红色分量图像进行重建,平滑枸杞内部而保留轮廓边缘信息;然后采用8邻域跟踪算法提取粘连枸杞轮廓边缘;最后运用圆形模板检测粘连枸杞的轮廓凹点,以凹点间最短欧氏距离为匹配条件连接凹点对,并对匹配错误的凹点对进行修正,实现粘连枸杞分割。试验结果表明,该文方法分割准确率较高,而过分割率较低,相比标记控制的分水岭和直接凹点匹配分割等方法,对粘连枸杞分割效果较好,分割准确率可达到96%。该研究可为枸杞分割技术提供理论支撑。
Bibliography:Wang Xiaopeng, Yao Lijuan, Wen Haotian, Zhao Junjun （School of Electronic and Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China）
11-2047/S
The traditional Chinese wolfberry classification usually adopts manual grading in terms of the wolfberry characteristics of size,color,surface defects,and so on.It is a time-consuming and inefficient work.Fortunately,machine vision provides an efficient and fast way to improve the classification efficiency and accuracy.During the process of wolfberry classification by machine vision,the first and important task is to segment wolfberry particles from the image,and then classify them into different grades according to their characteristics.However,the accuracy of wolfberry image segmentation process is often hindered by a number of constraints including noise,inhomogeneous intensity,complex adherent and overlapped particles,which easily cause the decline of segmentation accuracy,and subsequently affect the wolfberry classification effect.For the purpo
ISSN:1002-6819
DOI:10.11975/j.issn.1002-6819.2018.02.029