Enhancing License Plate Super-Resolution: A Layout-Aware and Character-Driven Approach

Valfride Nascimento, Rayson Laroca, Rafael O. Ribeiro, William Robson Schwartz, David Menotti
8/27/2024
cs.CV

Official code: valfride/lpsr-lacd (23 stars, last commit 2024-10-20).

Abstract

Despite significant advancements in License Plate Recognition (LPR) through deep learning, most improvements rely on high-resolution images with clear characters. This scenario does not reflect real-world conditions where traffic surveillance often captures low-resolution and blurry images. Under these conditions, characters tend to blend with the background or neighboring characters, making accurate LPR challenging. To address this issue, we introduce a novel loss function, Layout and Character Oriented Focal Loss (LCOFL), which considers factors such as resolution, texture, and structural details, as well as the performance of the LPR task itself. We enhance character feature learning using deformable convolutions and shared weights in an attention module and employ a GAN-based training approach with an Optical Character Recognition (OCR) model as the discriminator to guide the super-resolution process. Our experimental results show significant improvements in character reconstruction quality, outperforming two state-of-the-art methods in both quantitative and qualitative measures. Our code is publicly available at https://github.com/valfride/lpsr-lacd

View on arXivView PDF

Code Implementations(1)

valfride/lpsr-lacdOfficial100%

Official code for 'Enhancing License Plate Super-Resolution: A Layout-Aware and Character-Driven Approach' (SIBGRAPI 2024)

233PythonJun 24, 20242 years ago
attention-mechanismlicense-platelicense-plate-recognitionlicense-plate-super-resolutionsuper-resolution+2 more

Similar Papers

Locally-Focused Face Representation for Sketch-to-Image Generation Using Noise-Induced Refinement

82% match2024

AdaSin: Enhancing Hard Sample Metrics with Dual Adaptive Penalty for Face Recognition

82% match2025

A Benchmark for Chinese-English Scene Text Image Super-resolution

82% match1 repo992026

GLYPH-SR: Can We Achieve Both High-Quality Image Super-Resolution and High-Fidelity Text Recovery via VLM-guided Latent Diffusion Model?

82% match2025

Hybrid CNN-ViT Framework for Motion-Blurred Scene Text Restoration

82% match1 repo2025

UTSRMorph: A Unified Transformer and Superresolution Network for Unsupervised Medical Image Registration

81% match1 repo212024

Cite this paper

@article{nascimento2024enhancing,
  title  = {Enhancing License Plate Super-Resolution: A Layout-Aware and Character-Driven Approach},
  author = {Valfride Nascimento and Rayson Laroca and Rafael O. Ribeiro and William Robson Schwartz and David Menotti},
  year   = {2024},
  eprint = {2408.15103},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2408.15103v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2408.15103.svg)](https://codeofpaper.com/paper/2408.15103)

Discussion