Flexible OCR module for Goobi and other tools
Antiqua or fracture? German or English? Spanish, or Italian … ?
Every option covered. Our OCR service gives you fully automated text recognition management, even for a large number of pages, and delivers the required output for all types of material and in any format you can think of.
In 2010 we introduced an OCR module that can launch a fully automatic text recognition program directly from Goobi. Since then, over the course of many digitisation projects, we have amassed considerable experience in the field of OCR processing. During this period, we have operated and provided our OCR services using a range of engines such as a Recognition Server, Tesseract Server and more recently our own implementation based on an OCR SDK.
intranda’s OCR Service is implemented as a generic web service. It can be integrated into your Goobi workflow as a fully automatic step. What’s more, the service can also be requested from any other software application completely independently of Goobi. The only software you need to have installed is JAVA.
The intranda OCR Service has been developed in close collaboration with Germany’s Common Library Network (GBV) and the University Library of Southampton. Individual OCR jobs are processed according to a set of definable priorities. The current status of each OCR job can be viewed and controlled via a web interface. With regard to output formats, our OCR Service covers the full range of common formats and languages supported.
How would you like to generate additional value from your digitised material? Whether you wish to conduct a full-text search or a semantic analysis, you will need a text recognition system. With our OCR service you can be sure of the best recognition rates and an unbeatable price per page.
The market leader in text recognition provides a wide range of options. Our OCR service gives you fully automated text recognition management, even for a large number of pages, and delivers the required output for all types of material and in any format you can think of. Why compromise?
The OCR service is not only intended for digitisation projects. It can be incorporated fully into your day-to-day routine – however you work. It can be integrated into workflow tools such as Goobi but can also be controlled from any other application. A simple command line instruction is all that is needed to send a request to our web service. We can also install the module on your own system and link it to our our OCR servers.
intranda OCR Service
System requirements
| Operating system: | Linux, Windows, Mac OSX |
| RAM: | 2 GB |
| CPU: | 1 core |
| Hard disk: | 200 MB for the application plus storage space for digitised material |
Get the software
| Documentation: | Download the intranda TaskManager manual here |
| Installation: | On request |
Comments are closed.