[1]李艳雪,吕芳.向日葵叶部病害图像分割方法[J].计算机技术与发展,2019,29(05):148-151.[doi:10. 3969 / j. issn. 1673-629X. 2019. 05. 031]
　LI Yan-xue,LYU Fang.Image Segmentation Method of Sunflower Leaf Disease Image[J].,2019,29(05):148-151.[doi:10. 3969 / j. issn. 1673-629X. 2019. 05. 031]
点击复制

向日葵叶部病害图像分割方法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
29
期数:
2019年05期
页码:
148-151
栏目:
应用开发研究
出版日期:
2019-05-10

文章信息/Info

Title:
Image Segmentation Method of Sunflower Leaf Disease Image
文章编号:
1673-629X(2019)05-0148-04
作者:
李艳雪; 吕芳
内蒙古工业大学 信息学院,内蒙古 呼和浩特 010000
Author(s):
LI Yan-xue; LYU Fang
School of Information,Inner Mongolia University of Technology,Hohhot 010000,China
关键词:
采集; 图像预处理; 颜色空间; 图像分割; 聚类算法; K-means 聚类; DBSCAN 算法
Keywords:
acquisition; image preprocessing; color space; image segmentation; clustering algorithm; K-means clustering; DBSCAN algorith
分类号:
TN911
DOI:
10. 3969 / j. issn. 1673-629X. 2019. 05. 031
摘要:
为了有效提高向日葵的产量,除了需要掌握向日葵的栽培技术外,研究可以模拟人甚至超越人的视觉功能的图像识别成为研究图像处理的一大关键。 为了实现对向日葵叶部病害图像的准确识别,需要用分辨率较高的相机在自然光照下采集,之后需要先进行图像预处理与病斑分割,从而达到病害的精确高识别率。 采集向日葵病害图像之后,图像预处理部分使用平滑滤波方法进行去噪和增强,选用合适的邻域模板达到良好的处理效果,对预处理之后的病害图像进行分割,病斑分割时将 K-means 聚类方法与 DBSCAN 算法进行对比,最终选择 DBSCAN 算法进行分割。 针对随机选取初始聚类中心的问题,DBSCAN 算法主要是改进 K-means 聚类算法和结果对初始聚类中心的敏感依赖程度,主要目的是清晰地分割出病斑部分。
Abstract:
In order to effectively improve the yield of sunflower,besides mastering the sunflower cultivation techniques,researching a image recognition which can simulate people beyond the visual function has become a key to the research of image processing. In order to accurately identify the disease image of sunflower leaves, a higher resolution camera is required to collect in natural light whencollecting. Then,image pretreatment and spot segmentation are needed to achieve high recognition rate of disease. Image preprocessingpart using smoothing filter to mania and strengthen, choose the appropriate template to achieve well treatment effect. After thepretreatment of image segmentation,in the segmentation of disease spots,K-means clustering method is used to compare the DBSCANalgorithm,and finally DBSCAN algorithm is selected for segmentation. The DBSCAN algorithm is to improve the sensitivity and dependence of K-means clustering algorithm and results on the initial clustering center,aiming at the problem of randomly selecting theinitial clustering center. Its main purpose is to clearly segment the disease spots.

相似文献/References:

[1]黄鑫娟 房岩 周洁敏 刘伯扬 王占军 陶思钰.基于改进模糊熵的车牌定位方法[J].计算机技术与发展,2010,(01):189.
　HUANG Xin-juan,FANG Yan,ZHOU Jie-min,et al.A License Plate Location Method Based on Improved Fuzzy Entropy[J].,2010,(05):189.
[2]左强翔 吴洁.一种基于分块采集和压缩技术的屏幕共享方案[J].计算机技术与发展,2008,(04):206.
　ZUO Qiang-xiang,WU Jie.A Screen Sharing Scheme Based on Block Collection and Data Compression[J].,2008,(05):206.
[3]杨述斌 张阳.复杂车辆图像中的车牌快速形态定位算法[J].计算机技术与发展,2008,(06):50.
　YANG Shu-bin,ZHANG Yang.Fast Morphological Locating Algorithm of Vehicle License Plate in Complex Vehicle Images[J].,2008,(05):50.
[4]江良洲 龙凤.磨粒图像自动拼接与预处理技术研究[J].计算机技术与发展,2010,(10):250.
　JIANG Liang-zhou,LONG Feng.Wear Particle Image Mosaicing and Preprocessing Technique Research for Ferrography[J].,2010,(05):250.
[5]孟晓莉 赵安军 马光思.基于数学形态学的车牌定位研究与实现[J].计算机技术与发展,2010,(11):84.
　MENG Xiao-li,ZHAO An-jun,MA Guang-si.Car License Plate Location Research and Implementation Based on Mathematical Morphology[J].,2010,(05):84.
[6]张志佳,王博实,李雅红,等. 基于双视角的可见外壳三维重建研究[J].计算机技术与发展,2015,25(03):50.
　ZHANG Zhi-jia,WANG Bo-shi,LI Ya-hong,et al. Research on 3 D Reconstruction of Visible Hull Based on Double Perspectives[J].,2015,25(05):50.
[7]邓轲,田泽,郭亮,等. 机载光纤通道采集记录仪的设计及实现[J].计算机技术与发展,2015,25(04):162.
　DENG Ke,TIAN Ze,GUO Liang,et al. Design and Implementation of FC Acquisition & Recorder[J].,2015,25(05):162.
[8]刘艳洋,曹玉东. EAN-13条形码图像的识别[J].计算机技术与发展,2015,25(06):202.
　LIU Yan-yang,CAO Yu-dong. EAN-13 Bar-code Image Recognition[J].,2015,25(05):202.
[9]庞瑞涛,雍珊珊,王新安,等.地震监测系统的电磁信号的采集设计与实现[J].计算机技术与发展,2018,28(02):27.[doi:10．3969/j．issn．1673－629X．2018．02．007]
　PANG uitao,YONG Shanshan,WANG Xinan,et al.Design and Implementation of Electromagnetic Signal Processing Circuit for Earthquake Monitoring System[J].,2018,28(05):27.[doi:10．3969/j．issn．1673－629X．2018．02．007]
[10]陈利.基于深度学习的车牌识别系统设计[J].计算机技术与发展,2018,28(06):85.[doi:10.3969/ j. issn.1673-629X.2018.06.019]
　CHEN Li.Design of License Plate Recognition System Based on Deep Learning[J].,2018,28(05):85.[doi:10.3969/ j. issn.1673-629X.2018.06.019]

更新日期/Last Update: 2019-05-10