Conference paper

ŠPAŇHEL Jakub, SOCHOR Jakub, JURÁNEK Roman and HEROUT Adam. Geometric Alignment by Deep Learning for Recognition of Challenging License Plates. In: 2018 21st International Conference on Intelligent Transportation Systems (ITSC). Lahaina, Maui: IEEE Intelligent Transportation Systems Society, 2018, pp. 3524-3529. ISBN 978-1-72810-321-1. Available from: https://ieeexplore.ieee.org/document/8569259
Publication language:english
Original title:Geometric Alignment by Deep Learning for Recognition of Challenging License Plates
Title (cs):Rozpoznání obtížných registračních značek pomocí geometrické zarovnání hlubokým učením
Pages:3524-3529
Proceedings:2018 21st International Conference on Intelligent Transportation Systems (ITSC)
Conference:21st IEEE International Conference on Intelligent Transportation Systems
Place:Lahaina, Maui, US
Year:2018
URL:https://ieeexplore.ieee.org/document/8569259
ISBN:978-1-72810-321-1
DOI:10.1109/ITSC.2018.8569259
Publisher:IEEE Intelligent Transportation Systems Society
Keywords
License Plate Recognition, CNN, License Plate
Dataset, Image Alignment, Intelligent Transportation Systems
Annotation
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.
BibTeX:
@INPROCEEDINGS{
   author = {Jakub {\v{S}}pa{\v{n}}hel and Jakub Sochor and
	Roman Jur{\'{a}}nek and Adam Herout},
   title = {Geometric Alignment by Deep Learning for
	Recognition of Challenging License Plates},
   pages = {3524--3529},
   booktitle = {2018 21st International Conference on Intelligent
	Transportation Systems (ITSC)},
   year = {2018},
   location = {Lahaina, Maui, US},
   publisher = {IEEE Intelligent Transportation Systems Society},
   ISBN = {978-1-72810-321-1},
   doi = {10.1109/ITSC.2018.8569259},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php.en.iso-8859-2?id=11845}
}

Your IPv4 address: 107.20.10.203
Switch to https

DNSSEC [dnssec]