CLiDE for Chemical Literature Data Extraction

SimBioSys Inc. is pleased to announce CLiDE and CLiDE Lite v 2.0.

CLiDE, an acronym for Chemical Literature Data Extraction, is a document image processing software, which extracts content of printed chemistry documents. The aim of CLiDE is to process whole pages from scanned chemical documents and to extract the maximum amount of information from both the text and the graphic regions.

CLiDE is a chemistry intelligent equivalent of an OCR software. Just as an OCR can recognize characters from a scanned images of a printed text, CLiDE can recognize structures, reactions and text from scanned images of printed chemistry literature.

FEATURES & BENEFITS

• Extracts chemical structure and text information from printed/scanned pages and stores the information in various forms (e.g. MOL file, ChemDraw).
• CLiDE also extracts reaction information. Reaction information can be entered into databases automatically. Saves hours of redrawing.
• Extracts generic structure information from graphics and text. CLiDE will expand condensed generic structures so they can be entered into your DB either expanded or condensed.
• CLiDE recognizes and extracts page layout information. Bibliographical information (e.g. title, author etc.) is conveniently extracted automatically thus saving time cataloging and organizing your DB.

CLiDE v2.0 is primarily available on MS Windows 2000/NT 4.0/Me/98/95 platforms.
CLiDE Lite is also available from SciStore.