| 张红涛，阮朋举，母建茹，孙志勇，李德伟.基于ABC-SVM的内部含虫麦粒多光谱图像特征选择研究[J].麦类作物学报,2016,36(10):1391 |
| 基于ABC-SVM的内部含虫麦粒多光谱图像特征选择研究 |
| Multispectral Image Feature Selection of Insect-infected Wheat Grains Based on ABC and SVM Algorithm |
| |
| DOI：10.7606/j.issn.1009-1041.2016.10.18 |
| 中文关键词: 内部含虫麦粒 人工蜂群算法 支持向量机 特征选择 识别 |
| 英文关键词:Insect-infected wheat grains Artificial bee colony algorithm Support vector machine Feature selection Recognition |
| 基金项目:国家自然科学基金项目（31671580）；国家自然科学基金项目(31101085)；河南省科技攻关项目(162102110112)；华北水利水电大学教学名师培育项目(2104108) |
|
| 摘要点击次数: 1077 |
| 全文下载次数: 1337 |
| 中文摘要: |
| 为探讨利用人工蜂群算法（ABC）对内部含虫麦粒进行特征选择的可行性，基于该算法，以交叉验证训练模型的识别率作为特征子集的性能评价准则, 对内部含虫麦粒的特征进行分析。结果表明，该算法从内部含虫麦粒的32维直方图特征和纹理特征中自动选择出6个特征的最优特征子空间，采用参数优化之后的SVM分类器对80个麦粒样本进行分类，识别率达到92%以上，说明应用人工蜂群算法对内部含虫麦粒进行特征选择是可行的。 |
| 英文摘要: |
| In order to study the feature selection of insect-infected wheat grains based on artificial bee colony algorithm and support vector machine algorithm, and to explore the feasibility of the feature selection of insect-infected wheat grains, the feature selection was firstly proposed based on the artificial bee colony algorithm, and the recognition accuracy of fold cross validation training model was taken as the evaluation principle of the feature subset. The artificial bee colony algorithm was applied to the feature selection of the insect-infected wheat grains.The results showed that the the optimal feature subspace of six features were extracted from 32 histogram features and textural features, and 80 image samples of the insect-infected wheat grains were automatically recognized by the optimized SVM classifier, with the recognition accuracy over 92%. The experiment showed that the application of artificial bee colony algorithm for the feature selection of grain insects was feasible． |
|
查看全文 查看/发表评论 下载PDF阅读器 |
| 关闭 |
基本信息
