Kerala Vehicle Colour Classification Dataset
Abstract
Kerala Vehicle Colour Classification Dataset (KVCC) Description This dataset consists of 1,104 high-resolution vehicle images captured from ANPR camera feeds in the Kozhikode district of Kerala, India with support from the Kerala Police Department. The dataset was curated to support research in vehicle attribute recognition under unconstrained environmental conditions, specifically addressing challenges like sunlight glare and varied illumination. Dataset Structure The images are organized into 5 primary color classes: Black Blue Gray Red White The data is split into Training (80%), Validation (10%), and Testing (10%) sets. Naming Convention All images have been renamed using the format: KVCC_[Index].jpg Metadata The included 'metadata.csv' provides a mapping of: Filename: The unique KVCC ID. Label: The ground truth color class. Usage This dataset is intended for academic and research purposes. If you use this dataset, please cite: Arun Natarajan et al.Robust Vehicle Colour and License Plate Recognition in Indian Traffic Conditions: A Hybrid Approach using YOLO and Multi-View Consensus Scoring. Authors Arun Natarajan, Kamble Aditya Dattatray, Thareesh Prabakaran, Rachel Aji Joseph, Abhinav Kurup, Hafeez Muhammed, Shihabudheen K. V., Munavar Fairooz C. National Institute of Technology Calicut, Kozhikode, Kerala, India License: Creative Commons Attribution 4.0 International (CC BY 4.0)
Fields of Study & Subjects
Vehicle License Plate Recognition
Advanced Neural Network Applications
Video Surveillance and Tracking Methods
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 10 February 2026
- Language
- EN
- Document type
- Dataset