Sweet Potato Quality Detection Dataset

The current agricultural sector faces problems with inconsistent quality detection standards and low detection efficiency, particularly in the quality inspection of agricultural products like sweet potatoes, which often rely on visual inspection by humans, resulting in significant errors. Most existing solutions are based on traditional detection methods and lack efficient, accurate automated detection techniques. This dataset aims to help researchers and developers build machine learning-based object detection models for fast and accurate sweet potato quality detection by providing a large number of annotated sweet potato images. Data is collected using high-resolution cameras in standardized environments to ensure that each image has good visibility. Multiple rounds of annotation and expert review were implemented during the annotation process to ensure high data quality. The data is stored in JPEG format for easy subsequent processing and analysis.