基于卷积神经网络的农作物智能图像识别分类研究  

Research on Crop Intelligent Image Recognition and Classification Based on Convolution Neural Network

作　　者：吴蓓 肖黎 Wu Bei;Xiao Li(Wuhan University of Engineering Science,Wuhan 430200,China)

机构地区：[1]武汉工程科技学院,武汉430200

出　　处：《农机化研究》2023年第12期20-23,29,共5页Journal of Agricultural Mechanization Research

基　　金：湖北省高等学校省级教学研究项目(2020743);武汉工程科技学院2020年度校级教学改革研究项目(JY202023)。

摘　　要：首先,介绍了卷积神经网络结构、各个模块的工作原理和Retina-Net目标检测算法;然后,采用颜色直方图特征提取方法,实现了卷积神经网络的农作物智能图像识别分类算法。实验结果表明:该算法可以准确地对番茄枝上的番茄进行识别测试,且准确率较高,有效性和准确性强,能够满足实时果实识别的应用需要。It first introduces the structure of convolutional neural network,the working principle of each module and retina net target detection algorithm,and then uses the color histogram feature extraction method to realize the intelligent image recognition and classification algorithm of crops based on convolutional neural network.Experiments show that the algorithm can accurately identify and test tomatoes on Tomato branches,and the accuracy is high.It verifies the effectiveness and accuracy of the system,which meet the application needs of real-time fruit recognition.

关 键 词：农作物 图像识别 卷积神经网络 Retina-Net 目标检测 特征提取 

分 类 号：S126[农业科学—农业基础科学] TP391.3[自动化与计算机技术—计算机应用技术]