Application of OCR in Building Bibliographic Databases
Abstract
Bibliographic databases tend to be very verbose and pose a problem to libraries due to the huge amount of data entry involved. In this situation, the two technologies that offer solutions are retro conversion and optical character recognition (OCR). The application of building an intelligent system for automatic identification of bibliographic elements like title, author, publisher, etc is discussed here. This paper also discusses the heuristics in identifying the elements and resolving conflicts that arise 'in situations where more than one bibliographic element satisfy the criteria specified for identifying the various elements. This work is being carried out at the DRTC with the financial assistance of NISSAT.
http://dx.doi.org/10.14429/dbit.17.4.3228
Except where otherwise noted, the Articles on this site are licensed under Creative Commons License: CC Attribution-Noncommercial-No Derivative Works 2.5 India