摘要
深度学习在语音识别、视觉识别以及其他领域都引起了很多研究者越来越多的关注。在图像处理领域,采用深度学习方法可以获得较高的识别率。本文以玻尔兹曼机和卷积神经网络作为深度学习的研究模型应用于农业方面,从病虫破坏农作物图像识别的角度,结合上述研究模型,并分别结合不同应用场景对模型进行改进。针对病虫破坏农作物的图像识别采用玻尔兹曼机+动量卷积神经网络结合方法。通过大量实验证明采用上述方法识别正确率达到85%以上,采用优化后的深度学习算法其运行速度较传统算法有一定的提升。
Deep learning has attracted more and more attention in speech recognition,visual recognition and other fields.In the field of image processing,using deep learning method can obtain higher recognition rate.In this paper,Boltzmann machine and convolutional neural network are used as the research models of deep learning in agriculture,and the model is improved in different application scenarios in image recognition of crop damage caused by pests and diseases.Through a large number of experiments,it is proved that the correct rate of image recognition using Boltzmann machine and momentum convolution neural network is more than 85%,and the running speed of the optimized deep learning algorithm is higher than that of the traditional algorithm.
作者
强敏杰
QIANG Minjie(School of Computer Science&Technology,Soochow University,Suzhou,China,215000)
出处
《福建电脑》
2021年第2期1-5,共5页
Journal of Fujian Computer
关键词
深度学习
图像处理
玻尔兹曼机
卷积神经网络
Deep Learning
Image Processing
Boltzmann Machine
Convolutional Neural Network
