Pre-processing of documents for Optical Characters Recognition

Optical Characters Recognition is division of the document image analysis. It applies on the components of document image which known as text and converts image of document into the editable text by computer. Preprocessing of documents is one of the important parts of characters recognition system.This paper studies the procedures and methods of documents preprocessing and also designs a system for preprocessing of English texts. This system has been implemented using MATLAB and some examples of its application on the documents are shown.

کلیدواژه ها:

OCR ، Optical Characters Recognition ، pre-processing ، document analysis