A Cocoa Ripeness Detection and Classification Model Based on Improved YOLOv5s

The present study introduces a novel approach to identifying the maturity of cacao fruits, utilizing YOLOv5s in tandem with the Convolutional Block Attention Module (CBAM). The efficacy of this method was evaluated on two distinct datasets, namely the Cocoa Maturity Dataset TCS 01 and the dataset from PT. Cargill Indonesia. The integration of CBAM into the network is aimed at enhancing the feature representation of the model, leading to an improvement in detection accuracy. The method under consideration demonstrated efficacy in attaining elevated levels of precision while concurrently maintaining a condensed model magnitude, thereby conferring benefits for real-world applications. The results indicate that the suggested approach holds promise for enhancing the cacao industry by increasing the level of cocoa cultivation productivity.