Symptom recognition of disease and insect damage based on Mask R-CNN, wavelet transform, and F-RNet

Brown blight, target spot, and tea coal diseases are three major leaf diseases of tea plants, and Apolygus lucorum is a major pest in tea plantations. The traditional symptom recognition of tea leaf diseases and insect pests is mainly through manual identification, which has some problems, such as l...

Full description

Bibliographic Details
Main Authors: He Li, Hongtao Shi, Anghong Du, Yilin Mao, Kai Fan, Yu Wang, Yaozong Shen, Shuangshuang Wang, Xiuxiu Xu, Lili Tian, Hui Wang, Zhaotang Ding
Format: Article
Language:English
Published: Frontiers Media S.A. 2022-07-01
Series:Frontiers in Plant Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fpls.2022.922797/full
_version_ 1817969064303132672
author He Li
Hongtao Shi
Anghong Du
Yilin Mao
Kai Fan
Yu Wang
Yaozong Shen
Shuangshuang Wang
Xiuxiu Xu
Lili Tian
Hui Wang
Zhaotang Ding
Zhaotang Ding
author_facet He Li
Hongtao Shi
Anghong Du
Yilin Mao
Kai Fan
Yu Wang
Yaozong Shen
Shuangshuang Wang
Xiuxiu Xu
Lili Tian
Hui Wang
Zhaotang Ding
Zhaotang Ding
author_sort He Li
collection DOAJ
description Brown blight, target spot, and tea coal diseases are three major leaf diseases of tea plants, and Apolygus lucorum is a major pest in tea plantations. The traditional symptom recognition of tea leaf diseases and insect pests is mainly through manual identification, which has some problems, such as low accuracy, low efficiency, strong subjectivity, and so on. Therefore, it is very necessary to find a method that could effectively identify tea plants diseases and pests. In this study, we proposed a recognition framework of tea leaf disease and insect pest symptoms based on Mask R-CNN, wavelet transform and F-RNet. First, Mask R-CNN model was used to segment disease spots and insect spots from tea leaves. Second, the two-dimensional discrete wavelet transform was used to enhance the features of the disease spots and insect spots images, so as to obtain the images with four frequencies. Finally, the images of four frequencies were simultaneously input into the four-channeled residual network (F-RNet) to identify symptoms of tea leaf diseases and insect pests. The results showed that Mask R-CNN model could detect 98.7% of DSIS, which ensure that almost disease spots and insect spots can be extracted from leaves. The accuracy of F-RNet model is 88%, which is higher than that of the other models (like SVM, AlexNet, VGG16 and ResNet18). Therefore, this experimental framework can accurately segment and identify diseases and insect spots of tea leaves, which not only of great significance for the accurate identification of tea plant diseases and insect pests, but also of great value for further using artificial intelligence to carry out the comprehensive control of tea plant diseases and insect pests.
first_indexed 2024-04-13T20:16:40Z
format Article
id doaj.art-b6a299e9e46840dabf84e22a2943713a
institution Directory Open Access Journal
issn 1664-462X
language English
last_indexed 2024-04-13T20:16:40Z
publishDate 2022-07-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Plant Science
spelling doaj.art-b6a299e9e46840dabf84e22a2943713a2022-12-22T02:31:42ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2022-07-011310.3389/fpls.2022.922797922797Symptom recognition of disease and insect damage based on Mask R-CNN, wavelet transform, and F-RNetHe Li0Hongtao Shi1Anghong Du2Yilin Mao3Kai Fan4Yu Wang5Yaozong Shen6Shuangshuang Wang7Xiuxiu Xu8Lili Tian9Hui Wang10Zhaotang Ding11Zhaotang Ding12Tea Research Institute, Qingdao Agricultural University, Qingdao, ChinaSchool of Science and Information Science, Qingdao Agricultural University, Qingdao, ChinaSchool of Science and Information Science, Qingdao Agricultural University, Qingdao, ChinaTea Research Institute, Qingdao Agricultural University, Qingdao, ChinaTea Research Institute, Qingdao Agricultural University, Qingdao, ChinaTea Research Institute, Qingdao Agricultural University, Qingdao, ChinaTea Research Institute, Qingdao Agricultural University, Qingdao, ChinaTea Research Institute, Shandong Academy of Agricultural Sciences, Jinan, ChinaTea Research Institute, Shandong Academy of Agricultural Sciences, Jinan, ChinaTea Research Institute, Shandong Academy of Agricultural Sciences, Jinan, ChinaTea Research Institute, Rizhao Academy of Agricultural Sciences, Rizhao, ChinaTea Research Institute, Qingdao Agricultural University, Qingdao, ChinaTea Research Institute, Shandong Academy of Agricultural Sciences, Jinan, ChinaBrown blight, target spot, and tea coal diseases are three major leaf diseases of tea plants, and Apolygus lucorum is a major pest in tea plantations. The traditional symptom recognition of tea leaf diseases and insect pests is mainly through manual identification, which has some problems, such as low accuracy, low efficiency, strong subjectivity, and so on. Therefore, it is very necessary to find a method that could effectively identify tea plants diseases and pests. In this study, we proposed a recognition framework of tea leaf disease and insect pest symptoms based on Mask R-CNN, wavelet transform and F-RNet. First, Mask R-CNN model was used to segment disease spots and insect spots from tea leaves. Second, the two-dimensional discrete wavelet transform was used to enhance the features of the disease spots and insect spots images, so as to obtain the images with four frequencies. Finally, the images of four frequencies were simultaneously input into the four-channeled residual network (F-RNet) to identify symptoms of tea leaf diseases and insect pests. The results showed that Mask R-CNN model could detect 98.7% of DSIS, which ensure that almost disease spots and insect spots can be extracted from leaves. The accuracy of F-RNet model is 88%, which is higher than that of the other models (like SVM, AlexNet, VGG16 and ResNet18). Therefore, this experimental framework can accurately segment and identify diseases and insect spots of tea leaves, which not only of great significance for the accurate identification of tea plant diseases and insect pests, but also of great value for further using artificial intelligence to carry out the comprehensive control of tea plant diseases and insect pests.https://www.frontiersin.org/articles/10.3389/fpls.2022.922797/fulltea plantdisease and pest stressMask R-CNNwavelet transformF-RNet
spellingShingle He Li
Hongtao Shi
Anghong Du
Yilin Mao
Kai Fan
Yu Wang
Yaozong Shen
Shuangshuang Wang
Xiuxiu Xu
Lili Tian
Hui Wang
Zhaotang Ding
Zhaotang Ding
Symptom recognition of disease and insect damage based on Mask R-CNN, wavelet transform, and F-RNet
Frontiers in Plant Science
tea plant
disease and pest stress
Mask R-CNN
wavelet transform
F-RNet
title Symptom recognition of disease and insect damage based on Mask R-CNN, wavelet transform, and F-RNet
title_full Symptom recognition of disease and insect damage based on Mask R-CNN, wavelet transform, and F-RNet
title_fullStr Symptom recognition of disease and insect damage based on Mask R-CNN, wavelet transform, and F-RNet
title_full_unstemmed Symptom recognition of disease and insect damage based on Mask R-CNN, wavelet transform, and F-RNet
title_short Symptom recognition of disease and insect damage based on Mask R-CNN, wavelet transform, and F-RNet
title_sort symptom recognition of disease and insect damage based on mask r cnn wavelet transform and f rnet
topic tea plant
disease and pest stress
Mask R-CNN
wavelet transform
F-RNet
url https://www.frontiersin.org/articles/10.3389/fpls.2022.922797/full
work_keys_str_mv AT heli symptomrecognitionofdiseaseandinsectdamagebasedonmaskrcnnwavelettransformandfrnet
AT hongtaoshi symptomrecognitionofdiseaseandinsectdamagebasedonmaskrcnnwavelettransformandfrnet
AT anghongdu symptomrecognitionofdiseaseandinsectdamagebasedonmaskrcnnwavelettransformandfrnet
AT yilinmao symptomrecognitionofdiseaseandinsectdamagebasedonmaskrcnnwavelettransformandfrnet
AT kaifan symptomrecognitionofdiseaseandinsectdamagebasedonmaskrcnnwavelettransformandfrnet
AT yuwang symptomrecognitionofdiseaseandinsectdamagebasedonmaskrcnnwavelettransformandfrnet
AT yaozongshen symptomrecognitionofdiseaseandinsectdamagebasedonmaskrcnnwavelettransformandfrnet
AT shuangshuangwang symptomrecognitionofdiseaseandinsectdamagebasedonmaskrcnnwavelettransformandfrnet
AT xiuxiuxu symptomrecognitionofdiseaseandinsectdamagebasedonmaskrcnnwavelettransformandfrnet
AT lilitian symptomrecognitionofdiseaseandinsectdamagebasedonmaskrcnnwavelettransformandfrnet
AT huiwang symptomrecognitionofdiseaseandinsectdamagebasedonmaskrcnnwavelettransformandfrnet
AT zhaotangding symptomrecognitionofdiseaseandinsectdamagebasedonmaskrcnnwavelettransformandfrnet
AT zhaotangding symptomrecognitionofdiseaseandinsectdamagebasedonmaskrcnnwavelettransformandfrnet