| 朱旭阳， 唐正宁.基于机器视觉的玉米头尾识别[J].轻工机械,2022,40(2):61-66 |
| 基于机器视觉的玉米头尾识别 |
| Recognition of Corn Head and Tail Based on Machine Vision |
| |
| DOI：10.3969/j.issn.1005 2895.2022.02.010 |
| 中文关键词: 玉米 头尾识别 方向梯度直方图 主成分分析法 支持向量机 |
| 英文关键词:corn head and tail recognition histogram of oriented gradient principal component analysis support vector machine |
| 基金项目: |
|
| 摘要点击次数: 190 |
| 全文下载次数: 170 |
| 中文摘要: |
| 为进行玉米棒头尾识别，课题组提出了一种基于机器视觉和机器学习的玉米头尾识别方法。该方法先对玉米图像进行分割，后对分割后图像提取其方向梯度直方图(histogram of oriented gradient, HOG)特征向量;并利用主成分分析法(principal component analysis, PCA)对特征向量进行降维，最后使用降维后的特征向量和交叉验证方法训练支持向量机(support vector machine, SVM)，最终实现对玉米的头尾识别。试验结果表明该方法的识别率为97.2%。该方法具有较高的可行性和准确率，可用于玉米的头尾识别。 |
| 英文摘要: |
| In order to realize the head and tail recognition of corn, a corn head and tail recognition method based on machine vision and machine learning was proposed. In this method, the corn image was segmented firstly. Then, the feature vector based on the histogram of oriented gradient was extracted from the segmented image, and the dimension of the feature vector was reduced by principal component analysis. Finally, the dimension reduced feature vector and cross validation method were used to train the support vector machine. Thus, the head and tail of corn can be recognized. The experimental results show that the recognition rate of this method is 97.2%. This method has high feasibility and accuracy, which can be used to identify the head and tail of corn. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| 关闭 |
