MailLeak: Obfuscation-Robust Character Extraction Using Transfer Learning

12/22/2020

∙

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.

READ FULL TEXT

MailLeak: Obfuscation-Robust Character Extraction Using Transfer Learning

Inter- and Intra-domain Knowledge Transfer for Related Tasks in Deep Character Recognition

Character Spotting Using Machine Learning Techniques

AniWho : A Quick and Accurate Way to Classify Anime Character Faces in Images

REZCR: A Zero-shot Character Recognition Method via Radical Extraction

Subword-Delimited Downsampling for Better Character-Level Translation

Meta-Model Structure Selection: Building Polynomial NARX Model for Regression and Classification

Computer Aided Restoration of Handwritten Character Strokes

MailLeak: Obfuscation-Robust Character Extraction Using Transfer Learning

Related Research

Inter- and Intra-domain Knowledge Transfer for Related Tasks in Deep Character Recognition

Character Spotting Using Machine Learning Techniques

AniWho : A Quick and Accurate Way to Classify Anime Character Faces in Images

REZCR: A Zero-shot Character Recognition Method via Radical Extraction

Subword-Delimited Downsampling for Better Character-Level Translation

Meta-Model Structure Selection: Building Polynomial NARX Model for Regression and Classification

Computer Aided Restoration of Handwritten Character Strokes