English

MailLeak: Obfuscation-Robust Character Extraction Using Transfer Learning

Machine Learning 2020-12-23 v1 Cryptography and Security

Abstract

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.

Keywords

Cite

@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}
}
R2 v1 2026-06-23T21:10:48.631Z