| bibtype |
C -
Conference Paper (international conference)
|
| ARLID |
0525022 |
| utime |
20240103224144.0 |
| mtime |
20200616235959.9 |
| DOI |
10.2352/ISSN.2470-1173.2020.6.IRIACV-052 |
| title
(primary) (eng) |
Perceptual License Plate Super-Resolution with CTC Loss |
| specification |
| page_count |
5 s. |
| media_type |
E |
|
| serial |
| ARLID |
cav_un_epca*0525236 |
| ISSN |
2470-1173 |
| title
|
Electronic Imaging, Intelligent Robotics and Industrial Applications using Computer Vision 2020 |
| publisher |
| place |
Springfield |
| name |
Society for Imaging Science and Technology |
| year |
2020 |
|
|
| keyword |
super resolution |
| keyword |
generative adversial networks |
| keyword |
optical character recognition |
| author
(primary) |
| ARLID |
cav_un_auth*0332672 |
| name1 |
Bílková |
| name2 |
Zuzana |
| institution |
UTIA-B |
| full_dept (cz) |
Zpracování obrazové informace |
| full_dept (eng) |
Department of Image Processing |
| department (cz) |
ZOI |
| department (eng) |
ZOI |
| fullinstit |
Ústav teorie informace a automatizace AV ČR, v. v. i. |
|
| author
|
| ARLID |
cav_un_auth*0322281 |
| name1 |
Hradiš |
| name2 |
M. |
| country |
CZ |
|
| source |
|
| cas_special |
| project |
| project_id |
SVV-2017-260452 |
| agency |
GA MŠk |
| country |
CZ |
| ARLID |
cav_un_auth*0393278 |
|
| project |
| project_id |
1583117 |
| agency |
GA UK |
| country |
CZ |
| ARLID |
cav_un_auth*0393033 |
|
| project |
| project_id |
AP1701 |
| agency |
AV ČR |
| country |
CZ |
| ARLID |
cav_un_auth*0349658 |
|
| abstract
(eng) |
We present a novel method for super-resolution (SR) of license plate images based on an end-to-end convolutional neural networks (CNN) combining generative adversial networks\n(GANs) and optical character recognition (OCR). License plate SR systems play an important role in number of security applications such as improvement of road safety, traffic monitoring or surveillance. The specific task requires not only realistic-looking reconstructed images but it also needs to preserve the text information. Standard CNN SR and GANs fail to accomplish this requirment. The incorporation of the OCR pipeline into the method also allows training of the network without the need of ground truth high resolution data which enables easy training on real data with all the real image degradations including compression. |
| action |
| ARLID |
cav_un_auth*0392692 |
| name |
IS&T International Symposium on Electronic Imaging 2020 |
| dates |
20200126 |
| mrcbC20-s |
20200130 |
| place |
Burlingame, California |
| country |
US |
|
| RIV |
JC |
| FORD0 |
10000 |
| FORD1 |
10200 |
| FORD2 |
10201 |
| reportyear |
2021 |
| num_of_auth |
2 |
| presentation_type |
PR |
| inst_support |
RVO:67985556 |
| permalink |
http://hdl.handle.net/11104/0309418 |
| mrcbC61 |
1 |
| cooperation |
| ARLID |
cav_un_auth*0300003 |
| name |
Vysoké učení technické v Brně, Fakulta informačních technologií |
| institution |
VUT FIT |
|
| confidential |
S |
| article_num |
052 |
| arlyear |
2020 |
| mrcbU14 |
SCOPUS |
| mrcbU24 |
PUBMED |
| mrcbU34 |
WOS |
| mrcbU63 |
cav_un_epca*0525236 Electronic Imaging, Intelligent Robotics and Industrial Applications using Computer Vision 2020 2470-1173 Springfield Society for Imaging Science and Technology 2020 |
|