Automated Capture of Technical Manuals into IETM Format for Electronic Review & Distribution

Cybernet designed an automated process for turning lengthy technical documents from hard copy to HTML files for Internet distribution. In developing this system, Cybernet evaluated existing optical character reading (OCR) technology, analyzed data compression and display strategies for data transmission across networks, and completed a prototype HTML document using the selected OCR translation utility (SGML) and document image retrieval system. Based on these results, a detailed system design, demonstration system, and preliminary cost analysis were developed.


Sensors and Data


Machine Vision
Document Parsing