CONF chen-das00/IDIAP Multiple Hypotheses Video OCR Chen, Datong Luettin, Juergen EXTERNAL https://publications.idiap.ch/attachments/reports/2000/rr-00-28.pdf PUBLIC https://publications.idiap.ch/index.php/publications/showcite/chen-rr-00-28 Related documents Proceedings of the 4th International Workshop on Document Analysis System 2000 Rio de Janeiro, Brazil December 2000 Published in Proceedings of the 4th International Workshop on Document Analysis System, In this paper, we present a method to improve video OCR with multiple character hypotheses. The text regions in video need to be binarized before work as the input of current OCR system. Tranditional binarization do not use any structural information about the text. Based on a certain statistic model, we define a binarization method, which is called observation function, that should satisfy a certain condition. We then present a method to construct an observation function by computing binarization results according to multiple hypotheses of characters obtained by an OCR system. REPORT chen-rr-00-28/IDIAP Multiple Hypotheses Video OCR Chen, Datong Luettin, Juergen EXTERNAL https://publications.idiap.ch/attachments/reports/2000/rr-00-28.pdf PUBLIC Idiap-RR-28-2000 2000 IDIAP December 2000 Published in Proceedings of the 4th International Workshop on Document Analysis System, 2000 In this paper, we present a method to improve video OCR with multiple character hypotheses. The text regions in video need to be binarized before work as the input of current OCR system. Tranditional binarization do not use any structural information about the text. Based on a certain statistic model, we define a binarization method, which is called observation function, that should satisfy a certain condition. We then present a method to construct an observation function by computing binarization results according to multiple hypotheses of characters obtained by an OCR system..