What is GiDoc ?

GiDoc stands for Gimp-based Interactive DOCument transcription. It is a computer-assisted transcription prototype developed within the iDoc (Interactive Analysis, Transcription and Translation of Old Text Documents) research project. It follows an interactive-predictive paradigm in which both, the system is guided by the human supervisor, and the supervisor is assisted by the system to complete the transcription task as efficiently as possible. This paradigm is followed at all different recognition levels, and thus GiDoc provides integrated support for interactive-predictive page layout analysis, text line detection and handwritten text transcription.

GiDoc has been built on top of the well-known GNU Image Manipulation Program (Gimp ). Apart from its high-end user interface, GIMP gives us for free many desired prototype features such as a large collection of image conversion drivers and low-level processing routines, an scripting language to automate repetitive tasks, an API for installation of user-defined plug-ins, etc. Indeed, the prototype is implemented as a set of GIMP plug-ins.



giDoc Team