Enhancing License Plate Super-Resolution: A Layout-Aware and Character-Driven Approach
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910657690992640 |
|---|---|
| author | Nascimento, Valfride Laroca, Rayson Ribeiro, Rafael O. Schwartz, William Robson Menotti, David |
| author_facet | Nascimento, Valfride Laroca, Rayson Ribeiro, Rafael O. Schwartz, William Robson Menotti, David |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_15103 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing License Plate Super-Resolution: A Layout-Aware and Character-Driven Approach Nascimento, Valfride Laroca, Rayson Ribeiro, Rafael O. Schwartz, William Robson Menotti, David Computer Vision and Pattern Recognition 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 |
| title | Enhancing License Plate Super-Resolution: A Layout-Aware and Character-Driven Approach |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.15103 |