We are very enthusiastic about our ongoing work on tranScriptorium and thought it was time to share this with you.
tranScriptorium is one of the Specific Targeted Research Projects (STReP) of the Seventh Framework Programme (FP7) created by the European Commission – Research and Innovation.
Digital libraries work and published huge amounts of handwritten historical documents. For typical handwritten text images of historical documents currently available text image recognition technologies are not efficient. Traditional Optical Character Recognition (OCR) is simply not usable since characters cannot be isolated automatically in these images. Therefore, holistic, segmentation-free Handwritten Text Recognition (HTR) techniques are needed. Current HTR approaches still lack the required accuracy, mainly due to poor quality, degradations and writing style variability of historical document images.
Hence tranScriptorium aims to develop innovative, efficient and cost-effective solutions for the indexing, search and full transcription of historical handwritten document images, using modern, holistic HTR technology.
The project will turn HTR into a mature technology by addressing the following objectives:
- Enhancing HTR technology for efficient transcription
- Bringing the HTR technology to users: individual researchers with experience in handwritten documents transcription and volunteers who collaborate in large transcription projects.
- Integrating the HTR results in public web portals: the outcomes of the tranScriptorium tools will be attached to the published handwritten document images.
The project will have an important impact to transcribers for whom HTR technology is not well known, as well as to new non-specialist users accessing the possibility to transcribe complex historical documents. Projects like Transcribe Bentham can certainly make good use of this technology. Also great impact is expected for the content provision of cultural heritage digital collections. tranScriptorium might even help locate sunken ships once the information stored in the General Archive of the Indies were processed!
The tranScriptorium project runs from 1 January 2013 to 31 December 2015.