: The objective of this study was to test the feasibility of Graphix I to scan Cyrillic text. Twenty-seven pages of DOKLADY AKADEMII NAUK SSSR No 3, 1976 supplied by Foreign Technology Division were scanned and digitized. The output from the optical character reader was formatted in accordance with the input requirements to FTD's SYSTRAN system. During the demonstration of Graphix I, the system throughput rate was determined to be 30 characters per second with a rejection rate of 10.3%. This report discussed the procedures used to scan the text, results, enhancements to the system and the cost for a production system.

http://www.dtic.mil/cgi-bin/GetTRDoc?AD=ADA080431&Location=U2&doc=GetTRDoc.pdf

A Feasibility Test of the Graphix I Optical Character Recognition System for the Capture of Printed Cyrillic Text

: The need to design multi-font print readers is becoming critical for the input conversion activities of the Air Force Foreign Technology Division Machine Translation facilities. This effort was to evaluate existing optical character recognition capabilities toward the total requirement of a Russian typeset print reader. In this research four pages of original scientific Russian text were used as the data base. The contractor demonstrated that the scanning and conversion of Russian text by OCR is feasible and potentially economical. The second objective was to identify the problem areas and compile solutions to them. The results of the analysis of scanning the four samples indicate that secondary recognition and increased digital resolution will be most effective in reducing the total error rate. An ultimate total error rate of less than .5% appears achievable. (Author)

David Bantz

Papers

Automatic typeset input techniques evaluation