Dual license plate recognition and visual features encoding for vehicle identification

This work presents an improved version of a new approach for vehicle identification, which comprises a dual identification system based on license plate recognition and visual encoding. To support this proposal, two new datasets have been created: UC3M-LP for license plate detection and character recognition and UC3M-VRI for vehicle re-identification. The main contributions of this research are the publication of the two open-source datasets and the validation of the dual approach for a reliable vehicle recognition. Precisely, the UC3M-LP dataset is unique, as it fills the gap of European license plates public datasets, becoming the largest of its kind and the first ever for Spanish plates. The proposed dual identification system provides a more robust solution, as it is less sensitive to the variability of image conditions. Performance has been evaluated both on public and the proposed datasets using a multi-network architecture and achieving remarkable results. This strategy opens up new research opportunities in the field of vehicle identification, and the generated datasets may serve as a benchmark for future research. The datasets are publicly available at https://github.com/ramajoballester/UC3M-LP and https://github.com/ramajoballester/UC3M-VRI.