BLPR achieves 89.6% character-level accuracy on real Bolivian license plates by combining synthetic pretraining, geometric rectification, and confidence-triggered VLM fallback while releasing the first public Bolivian LPDR dataset.
System implementation of multiple license plate detection and correction on wide-angle images using an instance segmentation network model
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
BLPR: Robust License Plate Recognition under Viewpoint and Illumination Variations via Confidence-Driven VLM Fallback
BLPR achieves 89.6% character-level accuracy on real Bolivian license plates by combining synthetic pretraining, geometric rectification, and confidence-triggered VLM fallback while releasing the first public Bolivian LPDR dataset.