CuneiForm
OCR system for printed and typewritten texts
| First version: | 1992 | Last version: | 1999 |
| Application: | ||||
| Input, recognition and storage of textual and graphic data into computers | ||||
| Description: | ||||
| CuneiForm is a self-training intelligent OCR system based on an adaptive recognition technology. It recognizes all fonts (of 4-72 points), without preliminary training.The principle "What you scan is what you get" is supported by the system to the full. It recognizes various texts of complex structure, with tables, graphs and images (monochrome, grey or colour). Text segmentation may be automatic, semi-automatic, or manual. The system deals with various text and image file formats and has 16 millions colours and 256 degrees of gray, for image processing. Image printing, image inversion are also possible. Other important features of the system: | ||||
|
||||
| Languages processed: | ||||
| Russian, English, German, French,
Italian, Spanish, Swedish. The system is capable to recognize mixed Russian-English text without decrease in recognition quality. |
||||
| Type of processing: | ||||
| Cognitive adaptive recognition algorithms. Intel MMX(tm) Technology. Contextual correction based on monolingual dictionary (for each language). 32-bit Application supports OLE and Drag&Drop. | ||||
| Hardware/software requirements: | ||||
| RAM > 4 Mb. All types of scanners. MS Windows 3.1, 95/98/NT. OS/2 Warp3. | ||||
| Distribution: | Thousands of sales. The system is marketed as a stand-alone software product and also as a component of scanner (Hewlett-Packard, Seiko Epson, Xerox) release. | |||
| Developer team: | Contact person: | |||
| Cognitive Technologies | Vladimir L. Arlazarov Phone: (+7 095) 135 50 88, 135 55 10 Fax: (+7 095) 135 50 88 E-mail: arl@cgntv.dol.ru |
|||