An intelligent grading system for mangosteen based on improved convolutional neural network

This study addresses cognitive challenges in mangosteen production and processing by developing an efficient grading mechanism. A specialized hardware unit was constructed to evaluate mangosteen based on external characteristics, utilizing image preprocessing techniques for color attribute extraction using the RGB model, contour extraction through image segmentation, and diameter measurement via ellipse fitting. We propose a novel convolutional neural network (CNN) model, MobileSeNet, which outperforms MobileNetV2 in average Precision, Recall, and F1-score metrics, achieving a grading accuracy of 98.13 %. Furthermore, MobileSeNet processes images in an average of 76 ms, which is 48 ms faster than MobileNetV2, underscoring its efficiency. Additionally, we developed a user-friendly human-computer interaction interface to enhance usability and minimize cognitive challenges, optimizing user experience and contributing to improved task execution and reduced errors. This comprehensive approach establishes a robust foundation for future advancements in automated grading systems, thereby enhancing productivity in the agricultural sector.