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

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.