Detail výsledku
Convolutional Neural Networks for Direct Text Deblurring
Kotera Jan
Zemčík Pavel, prof. Dr. Ing., dr. h. c., UAMT (FEKT), UPGM (FIT)
Šroubek Filip, Ing., Ph.D.,D.Sc.
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.
convolutional neural networks, blind deconvolution, image restoration, deblurring, CNN, neural networks, deep learning
@inproceedings{BUT119880,
author="Michal {Hradiš} and Jan {Kotera} and Pavel {Zemčík} and Filip {Šroubek}",
title="Convolutional Neural Networks for Direct Text Deblurring",
booktitle="Proceedings of BMVC 2015",
year="2015",
pages="1--13",
publisher="The British Machine Vision Association and Society for Pattern Recognition",
address="Swansea",
doi="10.5244/C.29.6",
isbn="1-901725-53-7",
url="http://www.bmva.org/bmvc/2015/papers/paper006/index.html"
}