摘要
随着人口的增长,生活垃圾分类问题日益突出。文章提出了一种基于改进快速的区域卷积神经网络(Faster-Region Convolutional Neural Network,Faster-RCNN)的生活垃圾分类方法,将特征提取网络改为ResNet50网络,并在区域推荐网络(Region Proposal Network,RPN)中使用K-means聚类算法。结果表明,基于改进Faster-RCNN的网络模型的准确率达到94.5%,具有较高的准确率和较快的分类速度,可为解决生活垃圾分类提供一种有效的技术手段。
With the growth of population,the problem of household waste classification is becoming increasingly prominent.This article proposes a household waste classification method based on improved Faster-Region Convolutional Neural Network(Faster-RCNN),which changes the feature extraction network to ResNet50 network and uses K-means clustering algorithm in Region Proposal Network(RPN).The results show that the accuracy of the network model based on the improved Faster RCNN reaches 94.5%.This method has high accuracy and fast classification speed,providing an effective technical means for solving the problem of household waste classification.
作者
葛焰
刘心中
GE Yan;LIU Xinzhong(Fujian University of Technology,Fuzhou Fujian 350000,China)
出处
《信息与电脑》
2023年第8期95-98,共4页
Information & Computer
