Reading Text in the Wild from Compressed Images
Abstract
Reading text in the wild is gaining attention in the computer vision community. Images captured in the wild are almost always compressed to varying degrees, depending on application context, and this compression introduces artifacts that distort image content into the captured images. In this paper we investigate the impact these compression artifacts have on text localization and recognition in the wild. We also propose a deep Convolutional Neural Network (CNN) that can eliminate text-specific compression artifacts and which leads to an improvement in text recognition. Experimental results on the ICDAR-Challenge4 dataset demonstrate that compression artifacts have a significant impact on text localization and recognition and that our approach yields an improvement in both – especially at high compression rates.
Cite
Text
Galteri et al. "Reading Text in the Wild from Compressed Images." IEEE/CVF International Conference on Computer Vision Workshops, 2017. doi:10.1109/ICCVW.2017.283Markdown
[Galteri et al. "Reading Text in the Wild from Compressed Images." IEEE/CVF International Conference on Computer Vision Workshops, 2017.](https://mlanthology.org/iccvw/2017/galteri2017iccvw-reading/) doi:10.1109/ICCVW.2017.283BibTeX
@inproceedings{galteri2017iccvw-reading,
title = {{Reading Text in the Wild from Compressed Images}},
author = {Galteri, Leonardo and Bazazian, Dena and Seidenari, Lorenzo and Bertini, Marco and Bagdanov, Andrew D. and Nicolaou, Anguelos and Karatzas, Dimosthenis and Del Bimbo, Alberto},
booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
year = {2017},
pages = {2399-2407},
doi = {10.1109/ICCVW.2017.283},
url = {https://mlanthology.org/iccvw/2017/galteri2017iccvw-reading/}
}