Using a Two-Stage HOG-SVM / CNN Model to Identify and Classify Forms of Brown Planthoppers
Approximately ten percent of rice crop yields throughout the Asia-Pacific region are reduced due to pests called brown planthoppers (BPH). We use a two-stage model to identify BPH from rice crop images and use these to determine the form of each BPH in the image, which has implications for predictin...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item PeerReviewed |
| Language: | English |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://repository.ugm.ac.id/282685/1/Using_a_Two-Stage_HOG-SVM___CNN_Model_to_Identify_and_Classify_Forms_of_Brown_Planthoppers.pdf https://repository.ugm.ac.id/282685/ https://ieeexplore.ieee.org/document/10119374 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Universitas Gadjah Mada |
| Language: | English |
| id |
id-ugm-repo.282685 |
|---|---|
| record_format |
dspace |
| spelling |
id-ugm-repo.2826852023-11-17T07:46:34Z https://repository.ugm.ac.id/282685/ Using a Two-Stage HOG-SVM / CNN Model to Identify and Classify Forms of Brown Planthoppers Harris, Christopher G. Andika, Ignatius P. Trisyono, Y. Andi Plant Pathology Agricultural Land Management Approximately ten percent of rice crop yields throughout the Asia-Pacific region are reduced due to pests called brown planthoppers (BPH). We use a two-stage model to identify BPH from rice crop images and use these to determine the form of each BPH in the image, which has implications for predicting potential BPH outbreaks. Using a unique form of concentric Histograms of Oriented Gradient (HOG) descriptors and SVM classifiers, we can obtain to identify BPH with a recall of 96.56 and an FDR (false detection rate) of 2.91, surpassing other efforts on similar datasets. Applying a VGG-19 CNN architecture, we achieved a classification accuracy of 92.76for the three BPH forms. These outcomes provide a foundation for other efforts in pest identification and insect lifecycle detection. © 2022 IEEE. 2022 Conference or Workshop Item PeerReviewed application/pdf en https://repository.ugm.ac.id/282685/1/Using_a_Two-Stage_HOG-SVM___CNN_Model_to_Identify_and_Classify_Forms_of_Brown_Planthoppers.pdf Harris, Christopher G. and Andika, Ignatius P. and Trisyono, Y. Andi (2022) Using a Two-Stage HOG-SVM / CNN Model to Identify and Classify Forms of Brown Planthoppers. In: 2022 IEEE Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI). https://ieeexplore.ieee.org/document/10119374 |
| institution |
Universitas Gadjah Mada |
| building |
UGM Library |
| continent |
Asia |
| country |
Indonesia Indonesia |
| content_provider |
UGM Library |
| collection |
Repository Civitas UGM |
| language |
English |
| topic |
Plant Pathology Agricultural Land Management |
| spellingShingle |
Plant Pathology Agricultural Land Management Harris, Christopher G. Andika, Ignatius P. Trisyono, Y. Andi Using a Two-Stage HOG-SVM / CNN Model to Identify and Classify Forms of Brown Planthoppers |
| description |
Approximately ten percent of rice crop yields throughout the Asia-Pacific region are reduced due to pests called brown planthoppers (BPH). We use a two-stage model to identify BPH from rice crop images and use these to determine the form of each BPH in the image, which has implications for predicting potential BPH outbreaks. Using a unique form of concentric Histograms of Oriented Gradient (HOG) descriptors and SVM classifiers, we can obtain to identify BPH with a recall of 96.56 and an FDR (false detection rate) of 2.91, surpassing other efforts on similar datasets. Applying a VGG-19 CNN architecture, we achieved a classification accuracy of 92.76for the three BPH forms. These outcomes provide a foundation for other efforts in pest identification and insect lifecycle detection. © 2022 IEEE. |
| format |
Conference or Workshop Item PeerReviewed |
| author |
Harris, Christopher G. Andika, Ignatius P. Trisyono, Y. Andi |
| author_facet |
Harris, Christopher G. Andika, Ignatius P. Trisyono, Y. Andi |
| author_sort |
Harris, Christopher G. |
| title |
Using a Two-Stage HOG-SVM / CNN Model to Identify and Classify Forms of Brown Planthoppers |
| title_short |
Using a Two-Stage HOG-SVM / CNN Model to Identify and Classify Forms of Brown Planthoppers |
| title_full |
Using a Two-Stage HOG-SVM / CNN Model to Identify and Classify Forms of Brown Planthoppers |
| title_fullStr |
Using a Two-Stage HOG-SVM / CNN Model to Identify and Classify Forms of Brown Planthoppers |
| title_full_unstemmed |
Using a Two-Stage HOG-SVM / CNN Model to Identify and Classify Forms of Brown Planthoppers |
| title_sort |
using a two-stage hog-svm / cnn model to identify and classify forms of brown planthoppers |
| publishDate |
2022 |
| url |
https://repository.ugm.ac.id/282685/1/Using_a_Two-Stage_HOG-SVM___CNN_Model_to_Identify_and_Classify_Forms_of_Brown_Planthoppers.pdf https://repository.ugm.ac.id/282685/ https://ieeexplore.ieee.org/document/10119374 |
| _version_ |
1783956320439762944 |