Detail publikačního výsledku

Geometric Alignment by Deep Learning for Recognition of Challenging License Plates

ŠPAŇHEL, J.; SOCHOR, J.; JURÁNEK, R.; HEROUT, A.

Originální název

Geometric Alignment by Deep Learning for Recognition of Challenging License Plates

Anglický název

Geometric Alignment by Deep Learning for Recognition of Challenging License Plates

Druh

Stať ve sborníku v databázi WoS či Scopus

Originální abstrakt

In this paper, we explore the problem of license
plate recognition in-the-wild (in the meaning of capturing data
in unconstrained conditions, taken from arbitrary viewpoints
and distances). We propose a method for automatic license
plate recognition in-the-wild based on a geometric alignment
of license plates as a preceding step for holistic license plate
recognition. The alignment is done by a Convolutional Neural
Network that estimates control points for rectifying the image
and the following rectification step is formulated so that the
whole alignment and recognition process can be assembled into
one computational graph of a contemporary neural network
framework, such as Tensorflow. The experiments show that the
use of the aligner helps the recognition considerably: the error
rate dropped from 9.6 % to 2.1 % on real-life images of license
plates. The experiments also show that the solution is fast - it
is capable of real-time processing even on an embedded and
low-power platform (Jetson TX2). We collected and annotated
a dataset of license plates called CamCar6k, containing 6,064
images with annotated corner points and ground truth texts.
We make this dataset publicly available.

Anglický abstrakt

In this paper, we explore the problem of license
plate recognition in-the-wild (in the meaning of capturing data
in unconstrained conditions, taken from arbitrary viewpoints
and distances). We propose a method for automatic license
plate recognition in-the-wild based on a geometric alignment
of license plates as a preceding step for holistic license plate
recognition. The alignment is done by a Convolutional Neural
Network that estimates control points for rectifying the image
and the following rectification step is formulated so that the
whole alignment and recognition process can be assembled into
one computational graph of a contemporary neural network
framework, such as Tensorflow. The experiments show that the
use of the aligner helps the recognition considerably: the error
rate dropped from 9.6 % to 2.1 % on real-life images of license
plates. The experiments also show that the solution is fast - it
is capable of real-time processing even on an embedded and
low-power platform (Jetson TX2). We collected and annotated
a dataset of license plates called CamCar6k, containing 6,064
images with annotated corner points and ground truth texts.
We make this dataset publicly available.

Klíčová slova

License Plate Recognition, CNN, License Plate
Dataset, Image Alignment, Intelligent Transportation Systems

Klíčová slova v angličtině

License Plate Recognition, CNN, License Plate
Dataset, Image Alignment, Intelligent Transportation Systems

Autoři

ŠPAŇHEL, J.; SOCHOR, J.; JURÁNEK, R.; HEROUT, A.

Rok RIV

2019

Vydáno

04.11.2018

Nakladatel

IEEE Intelligent Transportation Systems Society

Místo

Lahaina, Maui

ISBN

978-1-72810-321-1

Kniha

2018 21st International Conference on Intelligent Transportation Systems (ITSC)

ISSN

2153-0017

Periodikum

Proceedings

Číslo

21

Stát

Spojené státy americké

Strany od

3524

Strany do

3529

Strany počet

6

URL

https://ieeexplore.ieee.org/document/8569259

BibTex

@inproceedings{BUT155105,
  author="Jakub {Špaňhel} and Jakub {Sochor} and Roman {Juránek} and Adam {Herout}",
  title="Geometric Alignment by Deep Learning for Recognition of Challenging License Plates",
  booktitle="2018 21st International Conference on Intelligent Transportation Systems (ITSC)",
  year="2018",
  journal="Proceedings",
  number="21",
  pages="3524--3529",
  publisher="IEEE Intelligent Transportation Systems Society",
  address="Lahaina, Maui",
  doi="10.1109/ITSC.2018.8569259",
  isbn="978-1-72810-321-1",
  issn="2153-0009",
  url="https://ieeexplore.ieee.org/document/8569259"
}