Research map / Detection and segmentation / Open-set and few-shot detection
License Plate Detection and Recognition in Unconstrained Scenarios
Sergio Montazzolli Silva, Claudio Rosito Jung
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add synthetic LP data to OCR-NET training (ablation) | ALPR pipeline · AOLP RP | full-LP recognition accuracy (%): 93.29% -> 98.36% | Improved |
| add synthetic LP data to OCR-NET training (ablation) | ALPR pipeline · OpenALPR EU | full-LP recognition accuracy (%): 92.59% -> 93.52% | Improved |
| add synthetic LP data to OCR-NET training (ablation) | ALPR pipeline · OpenALPR BR | full-LP recognition accuracy (%): 88.60% -> 91.23% | Improved |
| add synthetic LP data to OCR-NET training (ablation) | ALPR pipeline · SSIG test | full-LP recognition accuracy (%): 84.58% -> 88.56% | Improved |
| add synthetic LP data to OCR-NET training (ablation) | ALPR pipeline · CD-HARD | full-LP recognition accuracy (%): 73.08% -> 75.00% | Improved |
| add WPOD-NET affine rectification of detected LP (ablation) | ALPR pipeline · AOLP RP | full-LP recognition accuracy (%): 84.61% -> 98.36% | Improved |
| add WPOD-NET affine rectification of detected LP (ablation) | ALPR pipeline · CD-HARD | full-LP recognition accuracy (%): 57.69% -> 75.00% | Improved |
| add WPOD-NET affine rectification of detected LP (ablation) | ALPR pipeline · OpenALPR EU | full-LP recognition accuracy (%): 94.44% -> 93.52% | Hurt |
| add WPOD-NET affine rectification of detected LP (ablation) | ALPR pipeline · OpenALPR BR | full-LP recognition accuracy (%): 90.35% -> 91.23% | No clear effect |
| add WPOD-NET rectification versus OCR on annotated LP boxes (ablation) | ALPR pipeline · AOLP RP | full-LP recognition accuracy (%): 79.21% -> 98.36% | Improved |
| add WPOD-NET rectification versus OCR on annotated LP boxes (ablation) | ALPR pipeline · CD-HARD | full-LP recognition accuracy (%): 53.85% -> 75.00% | Improved |
| use proposed pipeline instead of OpenALPR | ALPR pipeline · CD-HARD | full-LP recognition accuracy (%): 67.31% -> 75.00% | Improved |
Closest papers by meaning
- LSV-LP: Large-Scale Video-Based License Plate Detection and Recognition (TPAMI 2022 · similarity 0.90)
- Efficient License Plate Recognition via Holistic Position Attention (AAAI 2021 · similarity 0.87)
- Towards End-to-End License Plate Detection and Recognition: A Large Dataset and Baseline (ECCV 2018 · similarity 0.86)
- Towards Human-Level License Plate Recognition (ECCV 2018 · similarity 0.86)
- LP-Diff: Towards Improved Restoration of Real-World Degraded License Plate (CVPR 2025 · similarity 0.85)
- Towards Ship License Plate Recognition in the Wild: A Large Benchmark and Strong Baseline (AAAI 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
