Overview

CLiDE Batch is a chemistry intelligent equivalent of an Optical Character Recognition (OCR) software tool. Just as an OCR tool can recognize characters from scanned images of printed text, CLiDE Batch can recognize structures which can be exported into computer-readable file formats.

CLiDE Batch saves users hours of redrawing structures from printed material, as it transforms 'structure diagrams' into 'real structures'. CLiDE Batch is a tool for batch processing documents and images, and can be integrated into pipeline and web service environments.

Features

• Is an easy-to-use command-line tool
• Opens documents of the following types:
  • PDF (Portable Document Format)
  • DOC (Word 2003)
  • DOCX (Word 2007 and 2010)
  • HTML (HyperText Markup Language)
• Opens images files of several types, including
  • BMP (Bitmap Image File)
  • GIF (Graphical Interchange Format File)
  • JPEG, JPG, JPE, JIF (JPEG Image File)
  • PBM (Portable Bitmap Image)
  • PGM (Portable Greymap)
  • PNG (Portable Network Graphics)
  • PNM (Portable Any Map Image)
  • PPM (Portable Pixmap Image File)
  • TIFF, TIF (Tagged Image File Format)
  • XBM (X Windows Bitmap)
  • XPM (X Windows Pixmap)
• Extracts structures from structure diagrams
• Attempts to interpret generic structures
• Detects interpretation errors
• Chemical extraction can be done interactively via the user interface
• Provides a set of options to control the recognition process and what information should be saved into the exported files
• Saves structures in the following formats:
  • MDL Molfile
  • MDL SDfile
  • MDL RGfile
  • CDX (ChemDraw)
  • CML (Chemical Markup Language)
  • MRV (ChemAxon Marvin Document)
  • XML (Extensible Markup Language)
• Exported XML files can be opened in CLiDE Professional for reviewing the extracted structures alongside the input document or image

Platforms

Supported operating systems:

• Windows 8, 7, Vista, XP
• Mac OS X
• Linux