ArborScript ES™ converts paper documents or document images into computer readable form, indexes the content, and puts the results into databases. As it "mines" these databases for important key words, phrases, and content, the system automatically retrieves documents containing the relevant information sought by the user. ArborScript renders text, retrieves the images of the original documents, and highlights the areas of interest. The unique properties of ArborScript include its ability to:
- Handle documents that may be of very poor image quality due to artifacts from faxing, copying, scanning, or paper mishandling
- Recognize Middle Eastern languages, including Arabic, Farsi (Persian), Dari, and Pashto
- Allow customers to locate document images based on key words, phrases, and context criteria
- Sort results by search relevance and OCR confidence factors
- Use open standard communication protocols for integration with third-party products
