An approach to divide pre-detected Devanagari words from the scene images into characters - Springer

摘要

A methodology to segment the Devanagari words, extracted from the scene images, into characters is presented. Scene images include street signs, shop names, product advertisements, posters on streets, etc. Such words are prone to multiple sources of noise and these make the segmentation very challenging. The problem gets more complicated while developing the text recognition methodologies for different scripts because there is no general solution to this problem and recognizing text in some scripts can be tougher than in others. An indigenous database is created for this purpose. It consists of 130 samples, manually extracted from 200 natural scene images. The results obtained by applying the proposed techniques are encouraging. The average performance is found to be 55.77 %. The execution time for a typical word of size 1169 × 353 is found to be 4.76 s. The database and the results can serve as baseline for the future researchers.