Weighted Edit Distance for Country Code Recognition in License Plates

This paper presents the problem of country code recognition from license plate images. We propose an approach based on character detection and subsequent clustering for country code localization. We further propose three weighted Edit Distance metrics for country of origin prediction from imperfect detections, namely based on character similarity, detection confidence, and relative operation importance. Experimental results show the benefit of proposed approaches on real-world data. The proposed method is lightweight and independent of the underlying object detector, facilitating its application on edge devices.