Graded Tomato Image Dataset for Quality Classification under Real-World Conditions

This dataset presents a collection of 1004 tomato images categorized into four quality grades: Grade One, Grade Two, Grade Three, and Rotten, with 251 images per class. The images were collected from local markets in Tangail District under real-world conditions, including variations in lighting, background, and environment. All images were captured from a fixed distance using a smartphone camera to ensure consistency. The dataset is designed to support research in computer vision, image classification, and agricultural quality assessment, and can be used for developing automated tomato grading systems using machine learning and deep learning techniques.