The following work presents a new algorithm for character recognition from obfuscated images. The presented method is an example of a potential threat to current postal services. This paper both analyzes the efficiency of the given algorithm and suggests countermeasures to prevent such threats from occurring.
@article{arxiv.2012.11775,
title = {MailLeak: Obfuscation-Robust Character Extraction Using Transfer Learning},
author = {Wei Wang and Emily Sallenback and Zeyu Ning and Hugues Nelson Iradukunda and Wenxi Lu and Qingquan Zhang and Ting Zhu},
journal= {arXiv preprint arXiv:2012.11775},
year = {2020}
}