Convolutional Neural Networks for Direct Text Deblurring

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F15%3APU117023" target="_blank" >RIV/00216305:26230/15:PU117023 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/67985556:_____/15:00450667

Výsledek na webu

<a href="http://www.bmva.org/bmvc/2015/papers/paper006/index.html" target="_blank" >http://www.bmva.org/bmvc/2015/papers/paper006/index.html</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.5244/C.29.6" target="_blank" >10.5244/C.29.6</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Convolutional Neural Networks for Direct Text Deblurring

Popis výsledku v původním jazyce

In this work we address the problem of blind deconvolution and denoising. We focus on restoration of text documents and we show that this type of highly structured data can be successfully restored by a convolutional neural network. The networks are trained to reconstruct high-quality images directly from blurry inputs without assuming any specific blur and noise models. We demonstrate the performance of the convolutional networks on a large set of text documents and on a combination of realistic de-focus and camera shake blur kernels. On this artificial data, the convolutional networks significantly outperform existing blind deconvolution methods, including those optimized for text, in terms of image quality and OCR accuracy. In fact, the networks outperform even state-of-the-art non-blind methods for anything but the lowest noise levels. The approach is validated on real photos taken by various devices. Further information including test data and trained networks can be found on the [PROJECT PAGE] (http://www.fit.vutbr.cz/~ihradis/CNN-Deblur/).

Název v anglickém jazyce

Convolutional Neural Networks for Direct Text Deblurring

Popis výsledku anglicky

In this work we address the problem of blind deconvolution and denoising. We focus on restoration of text documents and we show that this type of highly structured data can be successfully restored by a convolutional neural network. The networks are trained to reconstruct high-quality images directly from blurry inputs without assuming any specific blur and noise models. We demonstrate the performance of the convolutional networks on a large set of text documents and on a combination of realistic de-focus and camera shake blur kernels. On this artificial data, the convolutional networks significantly outperform existing blind deconvolution methods, including those optimized for text, in terms of image quality and OCR accuracy. In fact, the networks outperform even state-of-the-art non-blind methods for anything but the lowest noise levels. The approach is validated on real photos taken by various devices. Further information including test data and trained networks can be found on the [PROJECT PAGE] (http://www.fit.vutbr.cz/~ihradis/CNN-Deblur/).

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

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2015

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of BMVC 2015

ISBN

1-901725-53-7

ISSN

—

e-ISSN

—

Počet stran výsledku

13

Strana od-do

1-13

Název nakladatele

The British Machine Vision Association and Society for Pattern Recognition

Místo vydání

Swansea

Místo konání akce

Swansea

Datum konání akce

7. 9. 2015

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—