Detail publikace

CNN for license plate motion deblurring

SVOBODA, P. HRADIŠ, M. MARŠÍK, L. ZEMČÍK, P.

Originální název

CNN for license plate motion deblurring

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

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.

Klíčová slova

Convolutional neural network, Motion blur, Image reconstruction, Blind deconvolution, License plate

Autoři

SVOBODA, P.; HRADIŠ, M.; MARŠÍK, L.; ZEMČÍK, P.

Vydáno

25. 9. 2016

Nakladatel

IEEE Signal Processing Society

Místo

Phoenix

ISBN

978-1-4673-9961-6

Kniha

IEEE International Conference on Image Processing (ICIP)

Strany od

3832

Strany do

3836

Strany počet

4

URL

BibTex

@inproceedings{BUT133500,
  author="Pavel {Svoboda} and Michal {Hradiš} and Lukáš {Maršík} and Pavel {Zemčík}",
  title="CNN for license plate motion deblurring",
  booktitle="IEEE International Conference on Image Processing (ICIP)",
  year="2016",
  pages="3832--3836",
  publisher="IEEE Signal Processing Society",
  address="Phoenix",
  doi="10.1109/ICIP.2016.7533077",
  isbn="978-1-4673-9961-6",
  url="http://ieeexplore.ieee.org/document/7533077/"
}