基于深度学习的植物病虫害图像识别研究

IF 0.6 Q4 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

International Journal of Cognitive Informatics and Natural Intelligence Pub Date : 2021-10-01 DOI:10.4018/ijcini.295810

W. Feng, Huang Xue Hua

{"title":"基于深度学习的植物病虫害图像识别研究","authors":"W. Feng, Huang Xue Hua","doi":"10.4018/ijcini.295810","DOIUrl":null,"url":null,"abstract":"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 high recognition rate. In this paper, the convolution neural network is used as the basic model of deep learning. The shortcomings of the model are analyzed, and the DBN is used for the image recognition of diseases and insect pests. In the experiment, firstly, we select 10 kinds of disease and pest leaves and 50000 normal leaves, each of which is used for the comparison of algorithm performance.In the judgment of disease and pest species, the algorithm proposed in this study can identify all kinds of diseases and insect pests to the maximum extent, but the corresponding software (openCV, Access) recognition accuracy will gradually reduce along with the increase of the types of diseases and insect pests. In this study, the algorithm proposed in the identification of diseases and insect pests has been kept at about 45%.","PeriodicalId":43637,"journal":{"name":"International Journal of Cognitive Informatics and Natural Intelligence","volume":"58 1","pages":"1-21"},"PeriodicalIF":0.6000,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Research of Image Recognition of Plant Diseases and Pests Based on Deep Learning\",\"authors\":\"W. Feng, Huang Xue Hua\",\"doi\":\"10.4018/ijcini.295810\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"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 high recognition rate. In this paper, the convolution neural network is used as the basic model of deep learning. The shortcomings of the model are analyzed, and the DBN is used for the image recognition of diseases and insect pests. In the experiment, firstly, we select 10 kinds of disease and pest leaves and 50000 normal leaves, each of which is used for the comparison of algorithm performance.In the judgment of disease and pest species, the algorithm proposed in this study can identify all kinds of diseases and insect pests to the maximum extent, but the corresponding software (openCV, Access) recognition accuracy will gradually reduce along with the increase of the types of diseases and insect pests. In this study, the algorithm proposed in the identification of diseases and insect pests has been kept at about 45%.\",\"PeriodicalId\":43637,\"journal\":{\"name\":\"International Journal of Cognitive Informatics and Natural Intelligence\",\"volume\":\"58 1\",\"pages\":\"1-21\"},\"PeriodicalIF\":0.6000,\"publicationDate\":\"2021-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Cognitive Informatics and Natural Intelligence\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.4018/ijcini.295810\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Cognitive Informatics and Natural Intelligence","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4018/ijcini.295810","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}

引用次数: 3

摘要

深度学习在语音识别、视觉识别等领域受到越来越多的关注。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。本文采用卷积神经网络作为深度学习的基本模型。分析了该模型的不足，将DBN用于病虫害图像识别。在实验中，我们首先选取10种病虫害叶片和50000片正常叶片，分别对算法性能进行比较。在病虫害种类的判断中，本研究提出的算法可以最大程度地识别各类病虫害，但相应的软件(openCV、Access)识别精度会随着病虫害种类的增加而逐渐降低。在本研究中，提出的病虫害识别算法一直保持在45%左右。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Research of Image Recognition of Plant Diseases and Pests Based on Deep Learning

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 high recognition rate. In this paper, the convolution neural network is used as the basic model of deep learning. The shortcomings of the model are analyzed, and the DBN is used for the image recognition of diseases and insect pests. In the experiment, firstly, we select 10 kinds of disease and pest leaves and 50000 normal leaves, each of which is used for the comparison of algorithm performance.In the judgment of disease and pest species, the algorithm proposed in this study can identify all kinds of diseases and insect pests to the maximum extent, but the corresponding software (openCV, Access) recognition accuracy will gradually reduce along with the increase of the types of diseases and insect pests. In this study, the algorithm proposed in the identification of diseases and insect pests has been kept at about 45%.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

International Journal of Cognitive Informatics and Natural Intelligence COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE-

CiteScore

2.00

自引率

11.10%

发文量

期刊介绍： The International Journal of Cognitive Informatics and Natural Intelligence (IJCINI) encourages submissions that transcends disciplinary boundaries, and is devoted to rapid publication of high quality papers. The themes of IJCINI are natural intelligence, autonomic computing, and neuroinformatics. IJCINI is expected to provide the first forum and platform in the world for researchers, practitioners, and graduate students to investigate cognitive mechanisms and processes of human information processing, and to stimulate the transdisciplinary effort on cognitive informatics and natural intelligent research and engineering applications.