ICDAR 2019 Historical Document Reading Challenge on Large Structured Chinese Family Records
This addresses the problem of automated reading and analysis of historical documents for researchers and archivists, but it is incremental as it sets up a new benchmark rather than proposing a novel method.
The paper introduced a competition focused on recognizing and analyzing the layout, textlines, and characters in a large collection of over 20,000 pages of historical Chinese family records, aiming to advance document reading techniques.
We propose a Historical Document Reading Challenge on Large Chinese Structured Family Records, in short ICDAR2019 HDRC CHINESE. The objective of the proposed competition is to recognize and analyze the layout, and finally detect and recognize the textlines and characters of the large historical document collection containing more than 20 000 pages kindly provided by FamilySearch.