Dataset of Dhaka Street Cleanliness

This dataset contains over 1800 real-world images of roads collected by the group members to enhance machine learning research on road cleanliness classification. The images represent diverse street environments and various levels of cleanliness. The dataset is organized into three folders corresponding to the classes: Clean, Moderate, and Dirty, where each folder contains images of that category. All images were manually labeled using computer software to ensure accurate and consistent annotations. The naming convention follows category-wise serial labels for easy identification. This dataset is intended for image classification tasks to train, validate, and evaluate models that can automatically detect and classify road cleanliness conditions. While the images reflect real-world scenarios, variations in lighting, angle, and image quality may be present.