Competition: Handwriting Recognition of Historical Ciphers

[Paul Ferguson]

"The first step in the decryption process is the transcription of these manuscripts, which is not easy due to the high variation of hand-writing styles and cipher alphabets, and in addition, the often few number of pages. Although different strategies can be considered to deal with the insufficient amount of training data (e.g. few-shot learning, self-supervised learning) the performance of HTR models is still far from satisfactory. Thus, we believe that a competition with a large number of symbol sets and scribes can boost the research of HTR in low resource scenarios. Indeed, the recognition of ciphers is an example of such a low-resource scenario with a high historical interest. Thousands of enciphered historical manuscripts are buried in libraries and archives. So, transcribing and decrypting the information contained in these special sources is important to the understanding of our cultural heritage, since it helps to shed new light on and even to (re-)interpret our history."

https://rrc.cvc.uab.es/?ch=27