Implementation of real time root crop leaf classification using CNN on raspberry-Pi microprocessor

This work presents the implementation of deep learning models for classifying root crop leaves, specifically beetroot, potato, radish, and sweet potato. Applying ResNet50 and DenseNet121 architectures, the work demonstrates the classification based on a comprehensive dataset of over 2,500 images col...

Full description

Saved in:
Bibliographic Details
Main Authors: M.D. Rakesh, M. Jeevankumar, S.B. Rudraswamy
Format: Article
Language:English
Published: Elsevier 2025-03-01
Series:Smart Agricultural Technology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772375524003186
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850054202676477952
author M.D. Rakesh
M. Jeevankumar
S.B. Rudraswamy
author_facet M.D. Rakesh
M. Jeevankumar
S.B. Rudraswamy
author_sort M.D. Rakesh
collection DOAJ
description This work presents the implementation of deep learning models for classifying root crop leaves, specifically beetroot, potato, radish, and sweet potato. Applying ResNet50 and DenseNet121 architectures, the work demonstrates the classification based on a comprehensive dataset of over 2,500 images collected from various locations across Karnataka, India. Both models exhibited good performance, with ResNet50 achieving 99.60 % accuracy and DenseNet121 attaining 97.60 %. The models maintained high precision, recall, and F1 scores across all classes, using CPU. A key achievement was the successful deployment of these models on a Raspberry Pi 4B, with ResNet50 maintaining its high accuracy with 99.60 % and DenseNet121 achieving 96.81 % accuracy on this resource constrained device. The practical applicability was further validated through field testing, where the Raspberry Pi 4B setup was mounted on a vehicle with the webcam to capture root crop leaves in real time and successfully tested in actual agricultural field. This demonstrated the system's viability for real-time crop classification. The outcomes highlight the promise of deep learning models in agriculture technology by providing a dependable, effective, and portable method for classifying root crop leaves. The consistent high accuracy maintained across different hardware platforms and in real-world conditions demonstrates the robustness and versatility of the developed models.
format Article
id doaj-art-1fb56fbcf62b4bc6a1c4dc5821d667f3
institution DOAJ
issn 2772-3755
language English
publishDate 2025-03-01
publisher Elsevier
record_format Article
series Smart Agricultural Technology
spelling doaj-art-1fb56fbcf62b4bc6a1c4dc5821d667f32025-08-20T02:52:20ZengElsevierSmart Agricultural Technology2772-37552025-03-011010071410.1016/j.atech.2024.100714Implementation of real time root crop leaf classification using CNN on raspberry-Pi microprocessorM.D. Rakesh0M. Jeevankumar1S.B. Rudraswamy2Corresponding author.; Department of Electronics and Communication Engineering, Sri Jayachamarajendra College of Engineering, JSS Science and Technology University, Mysuru, IndiaDepartment of Electronics and Communication Engineering, Sri Jayachamarajendra College of Engineering, JSS Science and Technology University, Mysuru, IndiaDepartment of Electronics and Communication Engineering, Sri Jayachamarajendra College of Engineering, JSS Science and Technology University, Mysuru, IndiaThis work presents the implementation of deep learning models for classifying root crop leaves, specifically beetroot, potato, radish, and sweet potato. Applying ResNet50 and DenseNet121 architectures, the work demonstrates the classification based on a comprehensive dataset of over 2,500 images collected from various locations across Karnataka, India. Both models exhibited good performance, with ResNet50 achieving 99.60 % accuracy and DenseNet121 attaining 97.60 %. The models maintained high precision, recall, and F1 scores across all classes, using CPU. A key achievement was the successful deployment of these models on a Raspberry Pi 4B, with ResNet50 maintaining its high accuracy with 99.60 % and DenseNet121 achieving 96.81 % accuracy on this resource constrained device. The practical applicability was further validated through field testing, where the Raspberry Pi 4B setup was mounted on a vehicle with the webcam to capture root crop leaves in real time and successfully tested in actual agricultural field. This demonstrated the system's viability for real-time crop classification. The outcomes highlight the promise of deep learning models in agriculture technology by providing a dependable, effective, and portable method for classifying root crop leaves. The consistent high accuracy maintained across different hardware platforms and in real-world conditions demonstrates the robustness and versatility of the developed models.http://www.sciencedirect.com/science/article/pii/S2772375524003186Convolutional neural networkDeep learningAgriculture automationRaspberry-PiLeaf classification
spellingShingle M.D. Rakesh
M. Jeevankumar
S.B. Rudraswamy
Implementation of real time root crop leaf classification using CNN on raspberry-Pi microprocessor
Smart Agricultural Technology
Convolutional neural network
Deep learning
Agriculture automation
Raspberry-Pi
Leaf classification
title Implementation of real time root crop leaf classification using CNN on raspberry-Pi microprocessor
title_full Implementation of real time root crop leaf classification using CNN on raspberry-Pi microprocessor
title_fullStr Implementation of real time root crop leaf classification using CNN on raspberry-Pi microprocessor
title_full_unstemmed Implementation of real time root crop leaf classification using CNN on raspberry-Pi microprocessor
title_short Implementation of real time root crop leaf classification using CNN on raspberry-Pi microprocessor
title_sort implementation of real time root crop leaf classification using cnn on raspberry pi microprocessor
topic Convolutional neural network
Deep learning
Agriculture automation
Raspberry-Pi
Leaf classification
url http://www.sciencedirect.com/science/article/pii/S2772375524003186
work_keys_str_mv AT mdrakesh implementationofrealtimerootcropleafclassificationusingcnnonraspberrypimicroprocessor
AT mjeevankumar implementationofrealtimerootcropleafclassificationusingcnnonraspberrypimicroprocessor
AT sbrudraswamy implementationofrealtimerootcropleafclassificationusingcnnonraspberrypimicroprocessor