CONF vinciarelli:icpr-1:2006/IDIAP Cursive Character Challenge: a New Database for Machine Learning and Pattern Recognition Camastra, Francesco Spinetti, Marco Vinciarelli, Alessandro EXTERNAL http://publications.idiap.ch/attachments/papers/2006/vinciarelli-icpr-1-2006.pdf PUBLIC http://publications.idiap.ch/index.php/publications/showcite/vinciarelli:rr05-79 Related documents Proceedings of International Conference on Pattern Recognition (ICPR) 2006 913-916 IDIAP-RR 05-79 Cursive character recognition is a challenging task due to high variability and intrinsic ambiguity of cursive letters. This paper presents \emph{C-Cube} (Cursive Character Challenge,',','), a new public-domain cursive character database. \emph{C-Cube} contains 57293 cursive characters manually extracted from cursive handwritten words, including both upper and lower case versions of each letter. The database can be downoloaded from the web and it provides predefined experimental protocols in order to compare rigorously the results obtained by different researchers. REPORT vinciarelli:rr05-79/IDIAP Cursive Character Challenge: a New Database for Machine Learning and Pattern Recognition Camastra, Francesco Spinetti, Marco Vinciarelli, Alessandro EXTERNAL http://publications.idiap.ch/attachments/reports/2005/vinciarelli-idiap-rr-05-79.pdf PUBLIC Idiap-RR-79-2005 2005 IDIAP Published in Proceedings of International {C}onference on {P}attern {R}ecognition 2006 Cursive character recognition is a challenging task due to high variability and intrinsic ambiguity of cursive letters. This paper presents \emph{C-Cube} (Cursive Character Challenge,',','), a new public-domain cursive character database. \emph{C-Cube} contains 57293 cursive characters manually extracted from cursive handwritten words, including both upper and lower case versions of each letter. The database can be downoloaded from the web and it provides predefined experimental protocols in order to compare rigorously the results obtained by different researchers.