| 基于图像处理和蚁群优化的形状特征选择与杂草识别 |
| |
| 引用本文： | 李先锋,朱伟兴,纪 滨,刘 波,马长华.基于图像处理和蚁群优化的形状特征选择与杂草识别[J].农业工程,2010(10):178-182. |
| |
| 作者姓名： | 李先锋 朱伟兴 纪 滨 刘 波 马长华 |
| |
| 作者单位： | 1．江苏大学电气信息工程学院，镇江 212013； 2．盐城工学院信息工程学院，盐城 224051;1．江苏大学电气信息工程学院，镇江 212013;1．江苏大学电气信息工程学院，镇江 212013;1．江苏大学电气信息工程学院，镇江 212013;1．江苏大学电气信息工程学院，镇江 212013 |
| |
| 基金项目： | 江苏大学现代农业装备与技术省部共建教育部重点试验室开放基金资助项目（NZ200709） |
| |
| 摘 要： | 利用叶片形状特征区分杂草和作物是杂草识别的一个重要方法。为了提高杂草识别的精度和效率，通过形态学运算和基于距离变换的阈值分割方法分离交叠叶片，从单个叶片中提取包括几何特征和矩特征的17个形状特征，用蚁群优化（ACO）算法和支持向量机（SVM）分类器进行特征选择和分类识别，选取有利于分类的较优特征并实现特征的优化组合。棉田杂草试验结果表明，该方法能实现分类特征的有效缩减，经优化组合得到的最优特征子集用于杂草识别的准确率达95%以上，识别率高，稳定性好，对识别杂草时如何兼顾准确率和实时性具有参考意义。
|
| 关 键 词： | 图像处理，特征提取，支持向量机，蚁群优化算法 |
| 收稿时间： | 4/1/2010 12:00:00 AM |
Using shape features of plant leaf to identify the weed from the crop is an important method for weed recognition. In order to improve the accuracy and efficiency, overlapped leaves were separated through morphology operation and threshold segmentation ba |
| |
| Li Xianfeng,Zhu Weixing,Ji Bin,Liu Bo and Ma Changhua.Using shape features of plant leaf to identify the weed from the crop is an important method for weed recognition. In order to improve the accuracy and efficiency, overlapped leaves were separated through morphology operation and threshold segmentation ba[J].Agricultural Engineering,2010(10):178-182. |
| |
| Authors: | Li Xianfeng Zhu Weixing Ji Bin Liu Bo and Ma Changhua |
| |
| Abstract: | Using shape features of plant leaf to identify the weed from the crop is an important method for weed recognition. In order to improve the accuracy and efficiency, overlapped leaves were separated through morphology operation and threshold segmentation ba |
| |
| Keywords: | image processing feature extraction support vector machine ant colony optimization algorithm |
|
| 点击此处可从《农业工程》浏览原始摘要信息 |
| 点击此处可从《农业工程》下载免费的PDF全文 |
