Authors - @shubhamdivakar , @abhishek1015
\nTitle of paper - Smote-DL: A Deep Learning Based Plant Disease Detection Method (Plant Disease 2020 challenge)
Contribution :- In the due course of time, computer vision, machine learning and deep learning has been widely used to detect disease in the plant leaf. Most works done in this area focuses upon coming up with accurate models but does not focus on the false predictions which could be a serious cause. Misdiagnosis of the plant leaf could cause large scale crop destruction. We used a publicly available dataset which contained four categories of images belonging to Apple Plant-Healthy, Scab, Rust and Multiple disease.However this dataset upon visualization was found to be imbalanced. Our main objective isto reduce the false predictions. The main contribution lies in the use of SMOTE method to balance the dataset and the novel Ensemble algorithm which uses both F1 score and accuracy to compare and come up with the best classifier from among the classifiers. Upon experimentation we came up with Efficient NetB7 as the best classifier from our list of classifier which had both good accuracy and good F1 Score. It also predicts whether a leaf image has multiple disease or not which helps to reduce false predictions further.
\nOur own designed Algo achieves better results as comapred to existing methods.
\nLink to paper - https://ieeexplore.ieee.org/document/9417920
", "messages": [ { "id": "1303786", "postDate": "05/12/2021 08:35:28", "content": "Authors - @shubhamdivakar , @abhishek1015
\nTitle of paper - Smote-DL: A Deep Learning Based Plant Disease Detection Method (Plant Disease 2020 challenge)
Contribution :- In the due course of time, computer vision, machine learning and deep learning has been widely used to detect disease in the plant leaf. Most works done in this area focuses upon coming up with accurate models but does not focus on the false predictions which could be a serious cause. Misdiagnosis of the plant leaf could cause large scale crop destruction. We used a publicly available dataset which contained four categories of images belonging to Apple Plant-Healthy, Scab, Rust and Multiple disease.However this dataset upon visualization was found to be imbalanced. Our main objective isto reduce the false predictions. The main contribution lies in the use of SMOTE method to balance the dataset and the novel Ensemble algorithm which uses both F1 score and accuracy to compare and come up with the best classifier from among the classifiers. Upon experimentation we came up with Efficient NetB7 as the best classifier from our list of classifier which had both good accuracy and good F1 Score. It also predicts whether a leaf image has multiple disease or not which helps to reduce false predictions further.
\nOur own designed Algo achieves better results as comapred to existing methods.
\nLink to paper - https://ieeexplore.ieee.org/document/9417920
", "rawMarkdown": "Authors - @shubhamdivakar , @abhishek1015 \nTitle of paper - Smote-DL: A Deep Learning Based Plant Disease Detection Method (Plant Disease 2020 challenge)\n\nContribution :- In the due course of time, computer vision, machine learning and deep learning has been widely used to detect disease in the plant leaf. Most works done in this area focuses upon coming up with accurate models but does not focus on the false predictions which could be a serious cause. Misdiagnosis of the plant leaf could cause large scale crop destruction. We used a publicly available dataset which contained four categories of images belonging to Apple Plant-Healthy, Scab, Rust and Multiple disease.However this dataset upon visualization was found to be imbalanced. Our main objective isto reduce the false predictions. The main contribution lies in the use of SMOTE method to balance the dataset and the novel Ensemble algorithm which uses both F1 score and accuracy to compare and come up with the best classifier from among the classifiers. Upon experimentation we came up with Efficient NetB7 as the best classifier from our list of classifier which had both good accuracy and good F1 Score. It also predicts whether a leaf image has multiple disease or not which helps to reduce false predictions further.\n\nOur own designed Algo achieves better results as comapred to existing methods. \n\nLink to paper - https://ieeexplore.ieee.org/document/9417920", "votes": null }, { "id": "1305813", "postDate": "05/13/2021 13:44:31", "content": "I will post the code for our algo soon, also would be happy to find people who work on research projects. Especially in this area of plant disease detection.
", "rawMarkdown": "I will post the code for our algo soon, also would be happy to find people who work on research projects. Especially in this area of plant disease detection.", "votes": null }, { "id": "2285962", "postDate": "06/03/2023 06:02:31", "content": "Posted this article 2 years back since then it has got 10 citations and people are appreciating this work. Also I have extended this work using multiple color spaces. Really happy for the support from the community.
\nMy google scholar profile -
\nhttps://scholar.google.com/citations?user=44ecZj0AAAAJ&hl=en
Your datasets are useful, please describe Multimodal Plant Disease Dataset in detail, or with corresponding literature. Support you.
", "rawMarkdown": "Your datasets are useful, please describe Multimodal Plant Disease Dataset in detail, or with corresponding literature. Support you.", "votes": null }, { "id": "2670782", "postDate": "02/27/2024 05:58:37", "content": "I would be happy if you can describe Multimodal Plant Disease Dataset in detail.And my email is xiaozao183@gmail.com.
", "rawMarkdown": "I would be happy if you can describe Multimodal Plant Disease Dataset in detail.And my email is xiaozao183@gmail.com.", "votes": null }, { "id": "2906298", "postDate": "07/05/2024 13:45:21", "content": "Hi Alex, that dataset is still in compilation mode and not yet fully compiled. Also that dataset is actually a combination of two existing datasets and it is done to resemble closely the multimodal data for plant if it would exist. I am getting good results with it and I am looking for publishing it until then cant make it public. However I am open for collaboration.
\nCheck this below app where i will update soon. I am open for collaborations.
\nhttps://plantvizpredict.streamlit.app/
I will post the code for our algo soon, also would be happy to find people who work on research projects. Especially in this area of plant disease detection.
", "votes": null, "replies": [ { "id": 2670782, "author_name": "alexno1", "author_url": "", "post_date": "02/27/2024 05:58:37", "content": "I would be happy if you can describe Multimodal Plant Disease Dataset in detail.And my email is xiaozao183@gmail.com.
", "votes": null, "replies": [] } ] }, { "id": 2285962, "author_name": "shubhamdivakar", "author_url": "", "post_date": "06/03/2023 06:02:31", "content": "Posted this article 2 years back since then it has got 10 citations and people are appreciating this work. Also I have extended this work using multiple color spaces. Really happy for the support from the community.
\nMy google scholar profile -
\nhttps://scholar.google.com/citations?user=44ecZj0AAAAJ&hl=en
Your datasets are useful, please describe Multimodal Plant Disease Dataset in detail, or with corresponding literature. Support you.
", "votes": null, "replies": [ { "id": 2906298, "author_name": "shubhamdivakar", "author_url": "", "post_date": "07/05/2024 13:45:21", "content": "Hi Alex, that dataset is still in compilation mode and not yet fully compiled. Also that dataset is actually a combination of two existing datasets and it is done to resemble closely the multimodal data for plant if it would exist. I am getting good results with it and I am looking for publishing it until then cant make it public. However I am open for collaboration.
\nCheck this below app where i will update soon. I am open for collaborations.
\nhttps://plantvizpredict.streamlit.app/