岳有军1,杨 雪1,赵 辉1,2,王红君1.基于支持向量机的油菜缺素诊断研究[J].广东农业科学,2015,42(20):145-148 |
查看全文
HTML
基于支持向量机的油菜缺素诊断研究 |
Diagnosis of rape nutrient deficiency basedon support vector machine |
|
DOI: |
中文关键词: 支持向量机 遗传算法 颜色特征 纹理特征 缺素 |
英文关键词: support vector machine GA color feature texture feature nutrient deficiency |
基金项目:天津市农业科技成果转化与推广项目
(201203060);天津市自然科学基金(10JCZDJC23100) |
|
摘要点击次数: 1537 |
全文下载次数: 717 |
中文摘要: |
针对油菜常见的缺素现象,提出将支持向量机应用于油菜缺素种类识别。首先,确定支持向量机
分类过程中所用的特征值,选择RGB 和HSV 颜色空间中的分量作为颜色特征,选择能量、熵、对比度、相关
性的均值和方差作为纹理特征;其次,将支持向量机用于分类模式识别,并与神经网络分类识别进行比较,仿
真结果表明:支持向量机的分类精度高,性能更好;最后,通过遗传算法对支持向量机参数进行优化,可以看
到最终的分类准确率有所提升,起到了优化的效果。 |
英文摘要: |
Aimed at rape nutrient deficiency,we applied support vector machine in rape nutrient deficiency
diagnosis. Firstly,we determined the feature value for support vector machine classification,chose the RGB and HSV
color space as color features,and chose the mean and variance of energy,entropy,contrast,correlation as texture
features. Then,the support vector machine was applied to classify pattern recognition and was compared to BP neural
network. The results showed that the support vector machine was superior to BP in classification performance. Finally,
through genetic algorithm to optimize the parameters of support vector machine,the final classification accuracy was
improved. |
查看/发表评论 下载PDF阅读器 |