摘要
农作物虫害预防是农业生产中的重要环节。针对传统的虫害预防工作强度大、耗时长、效率低的问题,本文应用机器学习理论,在农作物害虫识别方面进行相关的研究,提出一种基于级联AdaBoost分类器的虫害识别方法。使用Haar-like特征提取害虫的特征,将提取到的特征构建弱分类器,并通过AdaBoost算法将构建得到的弱分类器集合得到强分类器,最后通过级联的方式得到一个级联AdaBoost分类器来识别害虫。试验表明,本文方法对简单背景的虫害图片能够达到95.71%的识别率,对复杂背景的虫害图片能达到86.67%的识别率,为农作物虫害的识别和预防提供有效途径。
Prevention of crop pests is an important part in agricultural production.To solve the problems of high intensity,long time-consuming and low efficiency of traditional pest prevention,machine learning theory is applied to identify crop pests in this paper and put forward a pest recognition method based on cascaded AdaBoost classifier.The method uses Haar-like feature to extract pest features and using these extracted features constructing weak classifiers.Then using these weak classifier constructing strong classifier set by Adaboost algorithm.Finally,using a cascading way to get a cascade AdaBoost classifier and to recognize pests.Test shows that the method can achieve 95.71%recognition rate for simple background pest images and 86.67%recognition rate for complex background pest images,which provides an effective way for the recognition and prevention of crop pests.
作者
卢柳江
匡迎春
陈兰鑫
李国睿
Lu Liujiang;Kuang Yingchun;Chen Lanxin;Li Guorui(School of Information Science and Technology,Hunan Agricultural University,Changsha,410128,China)
出处
《中国农机化学报》
北大核心
2019年第8期127-131,共5页
Journal of Chinese Agricultural Mechanization
基金
国家“十二五”科技计划支撑项目(2012BAD35B00)
