Authors :
Tharmithan Nanthakumar; Ishalini Senthamilpalan; Nirushan Pathmarajan; Kaviseshan Santhirapiragasam; Aruna Ishara Gamage; Jeewaka Perera
Volume/Issue :
Volume 8 - 2023, Issue 10 - October
Google Scholar :
https://tinyurl.com/3mkp3ar2
Scribd :
https://tinyurl.com/yedpznt6
DOI :
https://doi.org/10.5281/zenodo.10066534
Abstract :
This research aimed to harness the power of
machine learning techniques for comprehensive analysis
of tomato plants in the context of disease identification,
seed type prediction, and NPK estimation. Deep learning
models, including ResNet and VG19, were employed for
disease identification and NPK prediction, while an
Artificial Neural Network (ANN) model was utilized for
seed type prediction. The results revealed that ResNet
achieved a superior overall accuracy of approximately
0.71 compared to MobileNet for disease identification.
The VG19 model showcased impressive accuracy with
0.95 overall accuracy for NPK prediction, while the ANN
model achieved an accuracy of 0.37. These findings
highlight the potential of deep learning models and
transfer learning for accurate disease identification and
NPK estimation in tomato plants. The research
contributes valuable insights and guidance for the
development of intelligent systems to enhance tomato
cultivation practices and empower farmers with effective
tools for decision-making.
Keywords :
Image Processing, Image Classification, Machine Learning , Deep Learning , Computer Vision , Regression.
This research aimed to harness the power of
machine learning techniques for comprehensive analysis
of tomato plants in the context of disease identification,
seed type prediction, and NPK estimation. Deep learning
models, including ResNet and VG19, were employed for
disease identification and NPK prediction, while an
Artificial Neural Network (ANN) model was utilized for
seed type prediction. The results revealed that ResNet
achieved a superior overall accuracy of approximately
0.71 compared to MobileNet for disease identification.
The VG19 model showcased impressive accuracy with
0.95 overall accuracy for NPK prediction, while the ANN
model achieved an accuracy of 0.37. These findings
highlight the potential of deep learning models and
transfer learning for accurate disease identification and
NPK estimation in tomato plants. The research
contributes valuable insights and guidance for the
development of intelligent systems to enhance tomato
cultivation practices and empower farmers with effective
tools for decision-making.
Keywords :
Image Processing, Image Classification, Machine Learning , Deep Learning , Computer Vision , Regression.
