TOCR is short for Transym Optical Character Recognition. TOCR Viewer performs accurate optical character recognition that is highly useful for advanced scanning purposes. It makes use of a comprehensive database of images that that enables it to correctly extract and convert data from scanned documents. Tested against internationally recognized ISRI database, the viewer handles TIFF files as well as bitmaps.
The optical recognition engineering of the software is designed to cover scanning tasks that are difficult to decipher, such as the following:
• Broken characters, unusual fonts, and changes in fonts
• Characters that have different orientations or have orientations that cannot be easily detected on a given page
• Stained, creased, smudged, or crumpled pages
• Texts made nearly unreadable by diagrams and multiple annotations
• Foreign character sets and language modifications
• Scanning devices that have inferior recognition capabilities
• Other situations that make scanning difficult, such as spilled ink on the scanner glass
Most OCR applications are focused on speed, often at the expense of correctness. When confronted with optically-challenging scanning assignments like the ones mentioned above, these programs fall short, often after about 30 seconds of processing data. They also require plenty of downtime while carrying out their functions. With TOCR, however, character extraction from scans is done accurately without sacrificing speed.