Yolo-Papaya: A Papaya Fruit Disease Detector and Classifier Using CNNs and Convolutional Block Attention Modules

Abstract

Agricultural losses due to post-harvest diseases can reach up to 30% of total production. Detecting diseases in fruits at an early stage is crucial to mitigate losses and ensure the quality and health of fruits. However, this task is challenging due to the different formats, sizes, shapes, and colors that the same disease can present. Convolutional neural networks have been proposed to address this issue, but most studies use self-built datasets with few samples per disease, hindering reproducibility and comparison of techniques. To address these challenges, the authors proposed a novel image dataset comprising 23,158 examples divided into nine classes of papaya fruit diseases, and a robust papaya fruit disease detector called Yolo-Papaya based on the YoloV7 detector with the implementation of a convolutional block attention module (CBAM) attention mechanism. This detector achieved an overall mAP (mean average precision) of 86.2%, with a performance of over 98% in classes such as “healthy fruits” and “Phytophthora blight”. The proposed detector and dataset can be used in practical applications for fruit quality control and are consolidated as a robust benchmark for the task of papaya fruit disease detection. The image dataset and all source code used in this study are available to the academic community on the project page, enabling reproducibility of the study and advancement of research in this domain.