An Automatic Method for Enhancing Character Recognition in Degraded Historical Documents

Automatic optical character recognition is an important research area in document processing. There are several commercial tools for such purpose, which are becoming more efficient every day. There is still a lot to be improved, in the case of historical documents, however, due to the presence of noise and degradation. This paper presents a new approach for enhancing the character recognition in degraded historical documents. The system proposed consists in identifying regions in which there is information loss due to physical document degradation and process the document with possible candidates for the correct text transcription.