Retrieving Information from Korean OCR Text Database
Young Moo Lee, Lee Chung Sik, Hahn Sun Hwa, Kim Jin Hyung · The Transactions of the Korea Information Processing Society · 1999
The texts constructed with Optical Character Recognition(OCR) contain more errors than those constructed with keyboard typing. Therefore, in order to retrieve useful information from OCR texts, we need to develop an effective automatic indexing method. In this paer, we investigate automatic indexing methods that can retrieve information effectively from Korean OCR text database with the character-level recognition ratio of 90%. Experimental result shows that 2-gram indexing provides similar retrieval effectiveness of morpheme-based indexing for the Korean OCR text database.