Forensic License Plate Recognition with Compression-Informed Transformers

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Moussa, Denise, Maier, Anatol, Spruck, Andreas, Seiler, Jürgen, Riess, Christian
Formato: Preprint
Publicado: 2022
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914781817995264
author Moussa, Denise
Maier, Anatol
Spruck, Andreas
Seiler, Jürgen
Riess, Christian
author_facet Moussa, Denise
Maier, Anatol
Spruck, Andreas
Seiler, Jürgen
Riess, Christian
contents Forensic license plate recognition (FLPR) remains an open challenge in legal contexts such as criminal investigations, where unreadable license plates (LPs) need to be deciphered from highly compressed and/or low resolution footage, e.g., from surveillance cameras. In this work, we propose a side-informed Transformer architecture that embeds knowledge on the input compression level to improve recognition under strong compression. We show the effectiveness of Transformers for license plate recognition (LPR) on a low-quality real-world dataset. We also provide a synthetic dataset that includes strongly degraded, illegible LP images and analyze the impact of knowledge embedding on it. The network outperforms existing FLPR methods and standard state-of-the art image recognition models while requiring less parameters. For the severest degraded images, we can improve recognition by up to 8.9 percent points.
format Preprint
id arxiv_https___arxiv_org_abs_2207_14686
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Forensic License Plate Recognition with Compression-Informed Transformers
Moussa, Denise
Maier, Anatol
Spruck, Andreas
Seiler, Jürgen
Riess, Christian
Computer Vision and Pattern Recognition
Artificial Intelligence
Forensic license plate recognition (FLPR) remains an open challenge in legal contexts such as criminal investigations, where unreadable license plates (LPs) need to be deciphered from highly compressed and/or low resolution footage, e.g., from surveillance cameras. In this work, we propose a side-informed Transformer architecture that embeds knowledge on the input compression level to improve recognition under strong compression. We show the effectiveness of Transformers for license plate recognition (LPR) on a low-quality real-world dataset. We also provide a synthetic dataset that includes strongly degraded, illegible LP images and analyze the impact of knowledge embedding on it. The network outperforms existing FLPR methods and standard state-of-the art image recognition models while requiring less parameters. For the severest degraded images, we can improve recognition by up to 8.9 percent points.
title Forensic License Plate Recognition with Compression-Informed Transformers
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2207.14686