PT Unknown AU Leonardo Galteri Dena Bazazian Lorenzo Seidenari Marco Bertini Andrew Bagdanov Anguelos Nicolaou Dimosthenis Karatzas Alberto del Bimbo TI Reading Text in the Wild from Compressed Images BT 1st International workshop on Egocentric Perception, Interaction and Computing PY 2017 DI 10.1109/ICCVW.2017.283 AB 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 artifactsthat 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 significantimpact on text localization and recognition and that our approach yields an improvement in both – especially at high compression rates. ER