Tomato Quality Grading Dataset

The current agricultural sector faces challenges such as unstable agricultural product quality and diverse market demands, especially in the quality grading of perishable fruits like tomatoes. The existing manual inspection methods are inefficient and error-prone, making it difficult to meet the needs of large-scale production. This dataset aims to assist researchers and developers in building effective automated quality inspection systems by providing high-quality images of tomatoes and their quality grading. It contains 5,000 high-resolution tomato images collected from multiple farms, covering different growth environments and maturity stages. The data collection used professional photography equipment under adequate lighting conditions to ensure clarity and authenticity of images. In terms of quality control, we implemented multiple rounds of annotation, expert review, and consistency checks to ensure the accuracy of each sample’s annotation. The data is stored in JPG format and organized by category, facilitating subsequent machine learning and deep learning applications.