A Mobile-Based Deep Learning Model for Cassava Disease Diagnosis
Convolutional neural network (CNN) models have the potential to improve plant disease phenotyping where the standard approach is visual diagnostics requiring specialized training. In scenarios where a CNN is deployed on mobile devices, models are presented with new challenges due to lighting and ori...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2019-03-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/article/10.3389/fpls.2019.00272/full |
| _version_ | 1819262987474567168 |
|---|---|
| author | Amanda Ramcharan Peter McCloskey Kelsee Baranowski Neema Mbilinyi Latifa Mrisho Mathias Ndalahwa James Legg David P. Hughes David P. Hughes David P. Hughes |
| author_facet | Amanda Ramcharan Peter McCloskey Kelsee Baranowski Neema Mbilinyi Latifa Mrisho Mathias Ndalahwa James Legg David P. Hughes David P. Hughes David P. Hughes |
| author_sort | Amanda Ramcharan |
| collection | DOAJ |
| description | Convolutional neural network (CNN) models have the potential to improve plant disease phenotyping where the standard approach is visual diagnostics requiring specialized training. In scenarios where a CNN is deployed on mobile devices, models are presented with new challenges due to lighting and orientation. It is essential for model assessment to be conducted in real world conditions if such models are to be reliably integrated with computer vision products for plant disease phenotyping. We train a CNN object detection model to identify foliar symptoms of diseases in cassava (Manihot esculenta Crantz). We then deploy the model in a mobile app and test its performance on mobile images and video of 720 diseased leaflets in an agricultural field in Tanzania. Within each disease category we test two levels of severity of symptoms-mild and pronounced, to assess the model performance for early detection of symptoms. In both severities we see a decrease in performance for real world images and video as measured with the F-1 score. The F-1 score dropped by 32% for pronounced symptoms in real world images (the closest data to the training data) due to a decrease in model recall. If the potential of mobile CNN models are to be realized our data suggest it is crucial to consider tuning recall in order to achieve the desired performance in real world settings. In addition, the varied performance related to different input data (image or video) is an important consideration for design in real world applications. |
| first_indexed | 2024-12-23T20:06:25Z |
| format | Article |
| id | doaj.art-9ba2aa48e8e94fa29686c74398e71114 |
| institution | Directory Open Access Journal |
| issn | 1664-462X |
| language | English |
| last_indexed | 2024-12-23T20:06:25Z |
| publishDate | 2019-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj.art-9ba2aa48e8e94fa29686c74398e711142022-12-21T17:32:55ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2019-03-011010.3389/fpls.2019.00272425916A Mobile-Based Deep Learning Model for Cassava Disease DiagnosisAmanda Ramcharan0Peter McCloskey1Kelsee Baranowski2Neema Mbilinyi3Latifa Mrisho4Mathias Ndalahwa5James Legg6David P. Hughes7David P. Hughes8David P. Hughes9Department of Entomology, College of Agricultural Sciences, Penn State University, State College, PA, United StatesDepartment of Entomology, College of Agricultural Sciences, Penn State University, State College, PA, United StatesDepartment of Entomology, College of Agricultural Sciences, Penn State University, State College, PA, United StatesInternational Institute for Tropical Agriculture, Dar el Salaam, TanzaniaInternational Institute for Tropical Agriculture, Dar el Salaam, TanzaniaInternational Institute for Tropical Agriculture, Dar el Salaam, TanzaniaInternational Institute for Tropical Agriculture, Dar el Salaam, TanzaniaDepartment of Entomology, College of Agricultural Sciences, Penn State University, State College, PA, United StatesDepartment of Biology, Eberly College of Sciences, Penn State University, State College, PA, United StatesCenter for Infectious Disease Dynamics, Huck Institutes of Life Sciences, Penn State University, State College, PA, United StatesConvolutional neural network (CNN) models have the potential to improve plant disease phenotyping where the standard approach is visual diagnostics requiring specialized training. In scenarios where a CNN is deployed on mobile devices, models are presented with new challenges due to lighting and orientation. It is essential for model assessment to be conducted in real world conditions if such models are to be reliably integrated with computer vision products for plant disease phenotyping. We train a CNN object detection model to identify foliar symptoms of diseases in cassava (Manihot esculenta Crantz). We then deploy the model in a mobile app and test its performance on mobile images and video of 720 diseased leaflets in an agricultural field in Tanzania. Within each disease category we test two levels of severity of symptoms-mild and pronounced, to assess the model performance for early detection of symptoms. In both severities we see a decrease in performance for real world images and video as measured with the F-1 score. The F-1 score dropped by 32% for pronounced symptoms in real world images (the closest data to the training data) due to a decrease in model recall. If the potential of mobile CNN models are to be realized our data suggest it is crucial to consider tuning recall in order to achieve the desired performance in real world settings. In addition, the varied performance related to different input data (image or video) is an important consideration for design in real world applications.https://www.frontiersin.org/article/10.3389/fpls.2019.00272/fullcassava disease detectiondeep learningconvolutional neural networksmobile plant disease diagnosticsobject detection |
| spellingShingle | Amanda Ramcharan Peter McCloskey Kelsee Baranowski Neema Mbilinyi Latifa Mrisho Mathias Ndalahwa James Legg David P. Hughes David P. Hughes David P. Hughes A Mobile-Based Deep Learning Model for Cassava Disease Diagnosis Frontiers in Plant Science cassava disease detection deep learning convolutional neural networks mobile plant disease diagnostics object detection |
| title | A Mobile-Based Deep Learning Model for Cassava Disease Diagnosis |
| title_full | A Mobile-Based Deep Learning Model for Cassava Disease Diagnosis |
| title_fullStr | A Mobile-Based Deep Learning Model for Cassava Disease Diagnosis |
| title_full_unstemmed | A Mobile-Based Deep Learning Model for Cassava Disease Diagnosis |
| title_short | A Mobile-Based Deep Learning Model for Cassava Disease Diagnosis |
| title_sort | mobile based deep learning model for cassava disease diagnosis |
| topic | cassava disease detection deep learning convolutional neural networks mobile plant disease diagnostics object detection |
| url | https://www.frontiersin.org/article/10.3389/fpls.2019.00272/full |
| work_keys_str_mv | AT amandaramcharan amobilebaseddeeplearningmodelforcassavadiseasediagnosis AT petermccloskey amobilebaseddeeplearningmodelforcassavadiseasediagnosis AT kelseebaranowski amobilebaseddeeplearningmodelforcassavadiseasediagnosis AT neemambilinyi amobilebaseddeeplearningmodelforcassavadiseasediagnosis AT latifamrisho amobilebaseddeeplearningmodelforcassavadiseasediagnosis AT mathiasndalahwa amobilebaseddeeplearningmodelforcassavadiseasediagnosis AT jameslegg amobilebaseddeeplearningmodelforcassavadiseasediagnosis AT davidphughes amobilebaseddeeplearningmodelforcassavadiseasediagnosis AT davidphughes amobilebaseddeeplearningmodelforcassavadiseasediagnosis AT davidphughes amobilebaseddeeplearningmodelforcassavadiseasediagnosis AT amandaramcharan mobilebaseddeeplearningmodelforcassavadiseasediagnosis AT petermccloskey mobilebaseddeeplearningmodelforcassavadiseasediagnosis AT kelseebaranowski mobilebaseddeeplearningmodelforcassavadiseasediagnosis AT neemambilinyi mobilebaseddeeplearningmodelforcassavadiseasediagnosis AT latifamrisho mobilebaseddeeplearningmodelforcassavadiseasediagnosis AT mathiasndalahwa mobilebaseddeeplearningmodelforcassavadiseasediagnosis AT jameslegg mobilebaseddeeplearningmodelforcassavadiseasediagnosis AT davidphughes mobilebaseddeeplearningmodelforcassavadiseasediagnosis AT davidphughes mobilebaseddeeplearningmodelforcassavadiseasediagnosis AT davidphughes mobilebaseddeeplearningmodelforcassavadiseasediagnosis |