基于融合多特征图切割的作物病害图像自动分割
为提高黄瓜叶部病害图像的分割性能,该文提出一种基于融合多特征图切割的病害图像自动分割方法。首先采用一种新的阈值化方法对原始病害图像的红色分量进行二值化处理;然后融合纹理、灰度、距离3个特征构建能量函数的边界项,描述像素间的相似性;再利用分割区域像素与区域边界像素的红色分量差值自动建立能量函数的区域项,反映像素归属于背景和目标的程度;最后运用最大流算法求解能量函数得到分割结果。将该方法应用于黄瓜3种病害(靶斑病、霜霉病和白粉病)叶部图像分割中,并与OTSU算法及半自动图切割算法的分割结果进行比较。试验结果表明,该方法的平均错分率为1.81%,低于其他2种算法,平均分割速度约为2.34 s并无大幅...
Saved in:
Published in | 农业工程学报 Vol. 30; no. 17; pp. 212 - 219 |
---|---|
Main Author | |
Format | Journal Article |
Language | Chinese |
Published |
中国科学技术大学信息科学技术学院,合肥 230026
2014
中国科学院合肥智能机械研究所,合肥 230031%中国科学院合肥智能机械研究所,合肥,230031 |
Subjects | |
Online Access | Get full text |
ISSN | 1002-6819 |
DOI | 10.3969/j.issn.1002-6819.2014.17.027 |
Cover
Summary: | 为提高黄瓜叶部病害图像的分割性能,该文提出一种基于融合多特征图切割的病害图像自动分割方法。首先采用一种新的阈值化方法对原始病害图像的红色分量进行二值化处理;然后融合纹理、灰度、距离3个特征构建能量函数的边界项,描述像素间的相似性;再利用分割区域像素与区域边界像素的红色分量差值自动建立能量函数的区域项,反映像素归属于背景和目标的程度;最后运用最大流算法求解能量函数得到分割结果。将该方法应用于黄瓜3种病害(靶斑病、霜霉病和白粉病)叶部图像分割中,并与OTSU算法及半自动图切割算法的分割结果进行比较。试验结果表明,该方法的平均错分率为1.81%,低于其他2种算法,平均分割速度约为2.34 s并无大幅增加。该研究可为黄瓜病害的自动识别和诊断提供技术参考。 |
---|---|
Bibliography: | 11-2047/S Wu Na, Li Miao, Chen Sheng, Yuan Yuan, Zeng Xinhua, Chen Lei, Sun Xiongwei, Bian Chengfei (1. School of Information Science and Technolog3,, University of Science and Technolog2 of China, Hefei 230026, China; 2. Institute of Intelligence Machines, Chinese Academy of Science, Hefei 230031, China) crops; diseases; image processing; graph cuts; multiple features; cucumber Diseases in crops can lead to declines of production and quality, which cause economic losses in agricultural industry worldwide. Therefore, detection of the diseases in plants is extremely critical for sustainable agriculture. Many crop diseases perform on the leaves, and often present in the form of spots, so processing the leaf images is a feasible way for identifying and diagnosing diseases. Spots separation from the leaf is a very important step in the process of disease recognition and diagnosis. And the segmentation accuracy affects the reliability of the subsequent feature extraction and the accurateness of following classificati |
ISSN: | 1002-6819 |
DOI: | 10.3969/j.issn.1002-6819.2014.17.027 |