A Deep Learning Enabled Multi-Class Plant Disease Detection Model Based on Computer Vision
In this paper, a deep learning enabled object detection model for multi-class plant disease has been proposed based on a state-of-the-art computer vision algorithm. While most existing models are limited to disease detection on a large scale, the current model addresses the accurate detection of fin...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-08-01
|
| Series: | AI |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-2688/2/3/26 |
| id |
doaj-17a1163c6d0a4c6fa374e89143fcafe5 |
|---|---|
| record_format |
Article |
| spelling |
doaj-17a1163c6d0a4c6fa374e89143fcafe52021-09-25T23:35:05ZengMDPI AGAI2673-26882021-08-0122641342810.3390/ai2030026A Deep Learning Enabled Multi-Class Plant Disease Detection Model Based on Computer VisionArunabha M. Roy0Jayabrata Bhaduri1Aerospace Engineering Department, University of Michigan, Ann Arbor, MI 48109, USADeep Learning & Data Science Division, Capacloud AI, Kolkata 711103, IndiaIn this paper, a deep learning enabled object detection model for multi-class plant disease has been proposed based on a state-of-the-art computer vision algorithm. While most existing models are limited to disease detection on a large scale, the current model addresses the accurate detection of fine-grained, multi-scale early disease detection. The proposed model has been improved to optimize for both detection speed and accuracy and applied to multi-class apple plant disease detection in the real environment. The mean average precision (mAP) and F1-score of the detection model reached up to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>91.2</mn><mo>%</mo></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>95.9</mn><mo>%</mo></mrow></semantics></math></inline-formula>, respectively, at a detection rate of 56.9 FPS. The overall detection result demonstrates that the current algorithm significantly outperforms the state-of-the-art detection model with a <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>9.05</mn><mo>%</mo></mrow></semantics></math></inline-formula> increase in precision and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>7.6</mn><mo>%</mo></mrow></semantics></math></inline-formula> increase in F1-score. The proposed model can be employed as an effective and efficient method to detect different apple plant diseases under complex orchard scenarios.https://www.mdpi.com/2673-2688/2/3/26real-time object detectionapple leaf diseasesdeep learningconvolution neural networksartificial intelligencecomputer vision |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Arunabha M. Roy Jayabrata Bhaduri |
| spellingShingle |
Arunabha M. Roy Jayabrata Bhaduri A Deep Learning Enabled Multi-Class Plant Disease Detection Model Based on Computer Vision AI real-time object detection apple leaf diseases deep learning convolution neural networks artificial intelligence computer vision |
| author_facet |
Arunabha M. Roy Jayabrata Bhaduri |
| author_sort |
Arunabha M. Roy |
| title |
A Deep Learning Enabled Multi-Class Plant Disease Detection Model Based on Computer Vision |
| title_short |
A Deep Learning Enabled Multi-Class Plant Disease Detection Model Based on Computer Vision |
| title_full |
A Deep Learning Enabled Multi-Class Plant Disease Detection Model Based on Computer Vision |
| title_fullStr |
A Deep Learning Enabled Multi-Class Plant Disease Detection Model Based on Computer Vision |
| title_full_unstemmed |
A Deep Learning Enabled Multi-Class Plant Disease Detection Model Based on Computer Vision |
| title_sort |
deep learning enabled multi-class plant disease detection model based on computer vision |
| publisher |
MDPI AG |
| series |
AI |
| issn |
2673-2688 |
| publishDate |
2021-08-01 |
| description |
In this paper, a deep learning enabled object detection model for multi-class plant disease has been proposed based on a state-of-the-art computer vision algorithm. While most existing models are limited to disease detection on a large scale, the current model addresses the accurate detection of fine-grained, multi-scale early disease detection. The proposed model has been improved to optimize for both detection speed and accuracy and applied to multi-class apple plant disease detection in the real environment. The mean average precision (mAP) and F1-score of the detection model reached up to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>91.2</mn><mo>%</mo></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>95.9</mn><mo>%</mo></mrow></semantics></math></inline-formula>, respectively, at a detection rate of 56.9 FPS. The overall detection result demonstrates that the current algorithm significantly outperforms the state-of-the-art detection model with a <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>9.05</mn><mo>%</mo></mrow></semantics></math></inline-formula> increase in precision and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>7.6</mn><mo>%</mo></mrow></semantics></math></inline-formula> increase in F1-score. The proposed model can be employed as an effective and efficient method to detect different apple plant diseases under complex orchard scenarios. |
| topic |
real-time object detection apple leaf diseases deep learning convolution neural networks artificial intelligence computer vision |
| url |
https://www.mdpi.com/2673-2688/2/3/26 |
| work_keys_str_mv |
AT arunabhamroy adeeplearningenabledmulticlassplantdiseasedetectionmodelbasedoncomputervision AT jayabratabhaduri adeeplearningenabledmulticlassplantdiseasedetectionmodelbasedoncomputervision AT arunabhamroy deeplearningenabledmulticlassplantdiseasedetectionmodelbasedoncomputervision AT jayabratabhaduri deeplearningenabledmulticlassplantdiseasedetectionmodelbasedoncomputervision |
| _version_ |
1717368517794201600 |