A Novel Approach for Classification and Detection of Apple Leaf Disease Using Enhanced RBVT-Net With Transfer Learning and YoloV7

Apples are a popular fruit worldwide, valued for their rich nutritional content and associated health benefits, such as reducing the risks for cancer, diabetes, and heart disease. However, apple production faces significant challenges from diseases and pests, which can lead to substantial losses for...

Full description

Saved in:
Bibliographic Details
Main Authors: Satish Kumar, Rakesh Kumar, Meenu Gupta, Korhan Cengiz, Nikola Ivkovic
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11115055/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849390397827055616
author Satish Kumar
Rakesh Kumar
Meenu Gupta
Korhan Cengiz
Nikola Ivkovic
author_facet Satish Kumar
Rakesh Kumar
Meenu Gupta
Korhan Cengiz
Nikola Ivkovic
author_sort Satish Kumar
collection DOAJ
description Apples are a popular fruit worldwide, valued for their rich nutritional content and associated health benefits, such as reducing the risks for cancer, diabetes, and heart disease. However, apple production faces significant challenges from diseases and pests, which can lead to substantial losses for farmers. Early and accurate detection of apple diseases is crucial for effective disease management and improved yield, however the identification process is complicated by the similarity of symptoms across different diseases. Variations in symptom expression, such as leaf discoloration and spot patterns, further complicate disease diagnosis, making it challenging to distinguish between pathogens. This study utilizes a manually collected and expertly validated dataset of 8,000 apple leaf images from orchards in Himachal Pradesh and Uttarakhand, India, encompassing three common diseases: Marssonina leaf blotch, Alternaria leaf spot, and powdery mildew. A novel approach is proposed that utilizes a Transfer Learning (TL) Enhanced Residual BottleNeck Vision Transformer (RBVT-Net) model for the classification of Apple Leaf Disease (ALD) and disease detection, leveraging YOLOv7 for high-precision identification. Extensive experiments demonstrated the effectiveness of the proposed model, achieving a classification accuracy of 98.58% and a mean Average Precision (mAP) of 0.599 for disease detection using YOLOv7. These results underscore the potential of TL-enhanced models in aiding apple disease management, offering a promising solution to support farmers in early disease identification and better crop quality.
format Article
id doaj-art-01ffc6f81bd94eccb2f5263e40eb9b10
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-01ffc6f81bd94eccb2f5263e40eb9b102025-08-20T03:41:40ZengIEEEIEEE Access2169-35362025-01-011313995313996710.1109/ACCESS.2025.359645111115055A Novel Approach for Classification and Detection of Apple Leaf Disease Using Enhanced RBVT-Net With Transfer Learning and YoloV7Satish Kumar0Rakesh Kumar1https://orcid.org/0000-0002-2659-5941Meenu Gupta2https://orcid.org/0000-0001-7366-0841Korhan Cengiz3https://orcid.org/0000-0001-6594-8861Nikola Ivkovic4https://orcid.org/0000-0003-1730-2518Department of Computer Science and Engineering, Chandigarh University, Punjab, Gharuan, IndiaDepartment of Computer Science and Engineering, Chandigarh University, Punjab, Gharuan, IndiaDepartment of Computer Science and Engineering, Chandigarh University, Punjab, Gharuan, IndiaDepartment of Electrical Engineering, Prince Mohammad Bin Fahd University, AI Khobar, Saudi ArabiaFaculty of Organization and Informatics, University of Zagreb, Varaždin, CroatiaApples are a popular fruit worldwide, valued for their rich nutritional content and associated health benefits, such as reducing the risks for cancer, diabetes, and heart disease. However, apple production faces significant challenges from diseases and pests, which can lead to substantial losses for farmers. Early and accurate detection of apple diseases is crucial for effective disease management and improved yield, however the identification process is complicated by the similarity of symptoms across different diseases. Variations in symptom expression, such as leaf discoloration and spot patterns, further complicate disease diagnosis, making it challenging to distinguish between pathogens. This study utilizes a manually collected and expertly validated dataset of 8,000 apple leaf images from orchards in Himachal Pradesh and Uttarakhand, India, encompassing three common diseases: Marssonina leaf blotch, Alternaria leaf spot, and powdery mildew. A novel approach is proposed that utilizes a Transfer Learning (TL) Enhanced Residual BottleNeck Vision Transformer (RBVT-Net) model for the classification of Apple Leaf Disease (ALD) and disease detection, leveraging YOLOv7 for high-precision identification. Extensive experiments demonstrated the effectiveness of the proposed model, achieving a classification accuracy of 98.58% and a mean Average Precision (mAP) of 0.599 for disease detection using YOLOv7. These results underscore the potential of TL-enhanced models in aiding apple disease management, offering a promising solution to support farmers in early disease identification and better crop quality.https://ieeexplore.ieee.org/document/11115055/Apple leaf disease 4 classes (ALD 4C)RBVT-NetYOLO v7BottelNeck transformer
spellingShingle Satish Kumar
Rakesh Kumar
Meenu Gupta
Korhan Cengiz
Nikola Ivkovic
A Novel Approach for Classification and Detection of Apple Leaf Disease Using Enhanced RBVT-Net With Transfer Learning and YoloV7
IEEE Access
Apple leaf disease 4 classes (ALD 4C)
RBVT-Net
YOLO v7
BottelNeck transformer
title A Novel Approach for Classification and Detection of Apple Leaf Disease Using Enhanced RBVT-Net With Transfer Learning and YoloV7
title_full A Novel Approach for Classification and Detection of Apple Leaf Disease Using Enhanced RBVT-Net With Transfer Learning and YoloV7
title_fullStr A Novel Approach for Classification and Detection of Apple Leaf Disease Using Enhanced RBVT-Net With Transfer Learning and YoloV7
title_full_unstemmed A Novel Approach for Classification and Detection of Apple Leaf Disease Using Enhanced RBVT-Net With Transfer Learning and YoloV7
title_short A Novel Approach for Classification and Detection of Apple Leaf Disease Using Enhanced RBVT-Net With Transfer Learning and YoloV7
title_sort novel approach for classification and detection of apple leaf disease using enhanced rbvt net with transfer learning and yolov7
topic Apple leaf disease 4 classes (ALD 4C)
RBVT-Net
YOLO v7
BottelNeck transformer
url https://ieeexplore.ieee.org/document/11115055/
work_keys_str_mv AT satishkumar anovelapproachforclassificationanddetectionofappleleafdiseaseusingenhancedrbvtnetwithtransferlearningandyolov7
AT rakeshkumar anovelapproachforclassificationanddetectionofappleleafdiseaseusingenhancedrbvtnetwithtransferlearningandyolov7
AT meenugupta anovelapproachforclassificationanddetectionofappleleafdiseaseusingenhancedrbvtnetwithtransferlearningandyolov7
AT korhancengiz anovelapproachforclassificationanddetectionofappleleafdiseaseusingenhancedrbvtnetwithtransferlearningandyolov7
AT nikolaivkovic anovelapproachforclassificationanddetectionofappleleafdiseaseusingenhancedrbvtnetwithtransferlearningandyolov7
AT satishkumar novelapproachforclassificationanddetectionofappleleafdiseaseusingenhancedrbvtnetwithtransferlearningandyolov7
AT rakeshkumar novelapproachforclassificationanddetectionofappleleafdiseaseusingenhancedrbvtnetwithtransferlearningandyolov7
AT meenugupta novelapproachforclassificationanddetectionofappleleafdiseaseusingenhancedrbvtnetwithtransferlearningandyolov7
AT korhancengiz novelapproachforclassificationanddetectionofappleleafdiseaseusingenhancedrbvtnetwithtransferlearningandyolov7
AT nikolaivkovic novelapproachforclassificationanddetectionofappleleafdiseaseusingenhancedrbvtnetwithtransferlearningandyolov7