Call For Paper Volume:4 Issue:8 Aug'2017 |

BINARIZATION OF TEXTUAL IMAGES USING A NETWORK FLOW TERMINOLOGY

Publication Date : 06/08/2015



Author(s) :

Swagat Barot , Prof. S. Rama Mohan.


Volume/Issue :
Volume 2
,
Issue 8
(08 - 2015)



Abstract :

The problem of Optical Character Recognition (OCR) needs, as a first prerequisite, a good and powerful algorithm for binarization of scanned text. Most of the available algorithms used for binarization, uses the concept of thresholding. Such algorithms, in spite of being powerful, simple and the one with very small computational cost, are sometimes less efficient in case of scanned text of low quality. This leads to the requirement of other mathematical model for binarization. In this paper, we present a new mathematical model for binarization problem. We transform the problem in to an equivalent optimization problem and attempt to solve it through network flow terminology. Max-flow min- cut theorem given by Ford and Fulkerson plays a very crucial role in the model.


No. of Downloads :

1


Indexing

Web Design MymensinghPremium WordPress ThemesWeb Development

BINARIZATION OF TEXTUAL IMAGES USING A NETWORK FLOW TERMINOLOGY

August 6, 2015