Deep Learning-Based Improved ResNet Model for Accurate Detection of Jackfruit Leaf Diseases

Radhika Gunasekaran^1*and Mahendran Thambusamy²

¹Department of Computer Science,  Arignar Anna Government Arts College, Villupuram, Tamil Nadu, India.

²Department of Computer Applications, Arignar Anna Government Arts College, Villupuram, Tamil Nadu, India.

Corresponding Author E-mail:rad1988.guna@gmail.com

DOI : http://dx.doi.org/10.12944/CARJ.13.2.20

Article Publishing History

Received: 04 Jul 2025
Accepted: 19 Aug 2025
Published Online: 03 Aug 2025

Review Details

Reviewed by: Dr. Aditi Joshi
Second Review by: Dr. Muhammad Usman
Final Approval by: Dr. Aristeidis Matsoukis

Article Metrics

 

     PDF Downloads: 219

Abstract:

Jackfruit leaf diseases caused by bacteria, fungi, or environmental stress significantly affect tree health and fruit yield. This study presents a Deep Learning (DL)-based approach for accurately identifying and classifying jackfruit leaf diseases. The proposed method includes a preprocessing stage with techniques—flipping, rotation, noise reduction, contract adjustment and color enhancement—to improve dataset diversity, followed by a classification stage using an improved ResNet architecture is employed to perform disease classification. Experiments were conducted on a publicly available Kaggle dataset of jackfruit leaf images (three classes: Healthy Leaf, Black Spot, and Algal Leaf Spot). Implemented in MATLAB, the proposed model achieved a classification accuracy of 99.25%, outperforming existing conventional approaches across precision, recall, F1-score, sensitivity, and specificity. The results demonstrate the reliability and robustness of the proposed model in detecting jackfruit leaf diseases.

Keywords:

Color enhancement; Data augmentation; Deep learning model; Improved ResNet; jackfruit leaf disease detection

Download this article as: 

[ HTML Full Text]