CNN for license plate motion deblurring

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F16%3APU122835" target="_blank" >RIV/00216305:26230/16:PU122835 - isvavai.cz</a>

Výsledek na webu

<a href="http://ieeexplore.ieee.org/document/7533077/" target="_blank" >http://ieeexplore.ieee.org/document/7533077/</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICIP.2016.7533077" target="_blank" >10.1109/ICIP.2016.7533077</a>

Jazyk výsledku

angličtina

Název v původním jazyce

CNN for license plate motion deblurring

Popis výsledku v původním jazyce

In this work we explore the previously proposed approach of direct blind deconvolution and denoising with convolutional neural networks (CNN) in a situation where the blur kernels are partially constrained. We focus on blurred images from a real-life traffic surveillance system, on which we, for the first time, demonstrate that neural networks trained on artificial data provide superior reconstruction quality on real images compared to traditional blind deconvolution methods. The training data is easy to obtain by blurring sharp photos from a target system with a very rough approximation of the expected blur kernels, thereby allowing custom CNNs to be trained for a specific application (image content and blur range). Additionally, we evaluate the behavior and limits of the CNNs with respect to blur direction range and length.

Název v anglickém jazyce

CNN for license plate motion deblurring

Popis výsledku anglicky

In this work we explore the previously proposed approach of direct blind deconvolution and denoising with convolutional neural networks (CNN) in a situation where the blur kernels are partially constrained. We focus on blurred images from a real-life traffic surveillance system, on which we, for the first time, demonstrate that neural networks trained on artificial data provide superior reconstruction quality on real images compared to traditional blind deconvolution methods. The training data is easy to obtain by blurring sharp photos from a target system with a very rough approximation of the expected blur kernels, thereby allowing custom CNNs to be trained for a specific application (image content and blur range). Additionally, we evaluate the behavior and limits of the CNNs with respect to blur direction range and length.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/7H14002" target="_blank" >7H14002: ALMARVI - Algorithms, Design Methods, and Many-Core Execution Platform for Low-Power Massive Data-Rate Video and Image Processing</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2016

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

IEEE International Conference on Image Processing (ICIP)

ISBN

978-1-4673-9961-6

ISSN

—

e-ISSN

—

Počet stran výsledku

4

Strana od-do

3832-3836

Název nakladatele

IEEE Signal Processing Society

Místo vydání

Phoenix

Místo konání akce

Phoenix

Datum konání akce

25. 9. 2016

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000390782003167