Computer Assisted Transcription of Handwritten Text Images

To date, automatic handwring recognition systems are far from being perfect and heavy human intervention is often required to check and correct the results of such systems. In order to achieve correct transcriptions, human knowledge can be integrated into the transcription process, following an Interactive Predictive paradigm. We have recently proposed Mouse Actions as a significant feedback information source for the underlying interactive system to improve the poductivity of the human transcriptor. In this paper we review this way to interact with the system and report comparative results using the publicly available IAMDB dataset.

• Type: Conference
• Year: 2007
• Where: ICDAR
• Authors: Alejandro Hector Toselli, Verónica Romero, Luis Rodríguez, Enrique Vidal
• Keywords: Automatic Handwring Recognition, Document Analysis, Heavy Human Intervention, ICDAR 2007, Interactive Predictive Paradigm