Manuscript received January 15, 2024; revised March 1, 2024; accepted April 22, 2024; published August 20, 2024

Abstract—The cashew (Anacardium occidentale L.) is one of the most important commercial crops grown globally. However, the Tea Mosquito Bug (TMB), the major pest of cashew plants may cause significant damage during the flushing, flowering, and fruiting period. Early detection of TMB insect pests in cashew plants is crucial for effective management and control of the infestation. In this research, a computer vision-based approach using the YOLOv5 algorithm is proposed to automatically detect and classify the severity of TMB infestation in cashew plants. The labeled image dataset of cashew plant images encompasses the images of healthy cashew plants and TMB-infested cashew plants of different levels of severity (mild, moderate, severe, and extreme). This dataset is used to train the model to detect and classify the lesions, using Python, OpenCV, and Torch. Experimental results showed that the proposed approach achieved high performance in detecting and classifying the infestations. The performance of the trained model is assessed using a range of metrics, including precision, recall, and F1-Score. Specifically, the precision is measured as 92.6%, the recall as 90.9%, and the F1-Score as 92.4% for all classes. This model can be used as a tool for early detection and diagnosis of TMB infestation in cashew plants, which will help in the effective management and control of pests. The study results highlight significant enhancements in both accuracy and efficiency compared to conventional severity-level classification methods.

Keywords—cashew plant, Tea Mosquito Bug (TMB), infestation, labelimg, YOLOv5, mean Average Precision (mAP)

Cite: N. P. Vidhya and R. Priya, "Automated Diagnosis of the Severity of TMB Infestation in Cashew Plants Using YOLOv5," Journal of Image and Graphics, Vol. 12, No. 3, pp. 276-282, 2024.

Copyright © 2024 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.