Convolutional Neural Networks for Direct Text Deblurring

Michal Hradiš, Jan Kotera, Pavel Zemčík and Filip Šroubek

Abstract

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.

Session

Deep Learning

Files

Extended Abstract (PDF, 637K)
Paper (PDF, 3M)
Supplemental Materials (ZIP, 26M)

DOI

10.5244/C.29.6
https://dx.doi.org/10.5244/C.29.6

Citation

Bibtex

@inproceedings{BMVC2015_6,
	title={Convolutional Neural Networks for Direct Text Deblurring},
	author={Michal Hradiš and Jan Kotera and Pavel Zemčík and Filip Šroubek},
	year={2015},
	month={September},
	pages={6.1-6.13},
	articleno={6},
	numpages={13},
	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
	publisher={BMVA Press},
	editor={Xianghua Xie, Mark W. Jones, and Gary K. L. Tam},
	doi={10.5244/C.29.6},
	isbn={1-901725-53-7},
	url={https://dx.doi.org/10.5244/C.29.6}
}