International Journal of Electronics & Informatics (IJEI)
Published by the Center for Natural Sciences & Engineering Research

 

ISSN: 2186-0114

 


Automated Extraction of Text from Images using Morphology Based Approach
Md. Shorif Uddin, Tanzila Rahman, Umme Sayma Busra, and Madeena Sultana
Abstract:
Existing text strings play an important role in understanding a scene image. Scene images differ from document images, which are composed of text characters of various size, shape, direction, and situation along with complicated backgrounds, such as map, picture or painting, etc. Hence, the extraction of texts on scene images is a difficult as well as challenging task. Mathematical morphology based algorithm finds applications to extract texts from scene images. In this paper a modified morphological filter along with an automatic clustering technique is described. Experimental result confirms the superiority of this approach compared to existing morphological method.
Download in PDF