Veri-Car: Towards Open-world Vehicle Information Retrieval
This addresses a practical need for industrial and service sectors requiring automated vehicle information retrieval, though it appears incremental with a hybrid approach.
The paper tackles the problem of extracting vehicle characteristics from images in open-world scenarios where new models constantly emerge, presenting Veri-Car which achieves high precision and accuracy in classifying make, type, model, year, color, and license plate data for both seen and unseen vehicles.
Many industrial and service sectors require tools to extract vehicle characteristics from images. This is a complex task not only by the variety of noise, and large number of classes, but also by the constant introduction of new vehicle models to the market. In this paper, we present Veri-Car, an information retrieval integrated approach designed to help on this task. It leverages supervised learning techniques to accurately identify the make, type, model, year, color, and license plate of cars. The approach also addresses the challenge of handling open-world problems, where new car models and variations frequently emerge, by employing a sophisticated combination of pre-trained models, and a hierarchical multi-similarity loss. Veri-Car demonstrates robust performance, achieving high precision and accuracy in classifying both seen and unseen data. Additionally, it integrates an ensemble license plate detection, and an OCR model to extract license plate numbers with impressive accuracy.