IUP Publications Online
Home About IUP Magazines Journals Books Archives
     
A Guided Tour | Recommend | Links | Subscriber Services | Feedback | Subscribe Online
 
The IUP Journal of Telecommunications
An Entropy-Based Binarization Method to Separate Foreground from Background in Document Image Processing
:
:
:
:
:
:
:
:
:
 
 
 
 
 
 
 

Character recognition is a branch of pattern recognition, where texts or characters are realized from images. Binarization is an important step of character recognition, where foregrounds or texts or characters are separated from backgrounds. The paper proposes a novel entropy-based fuzzy clustering method for text binarization of a gray-level document image. The proposed method considers the spatial information of the gray pixels and the original gray level values for its computations. In order to separate text or document pixels and background pixels in a more realistic way, the proposed method incorporates fuzzy logic-based decision system. The performance of the method has been tested with several images consisting of different Indian languages and the results are evaluated with respect to two existing standard binarization methods.

 
 

Character recognition is one of the most discussed topics in the field of pattern recognition. Characters, that the researchers have considered, can be both printed and handwritten. Character recognition has a wide range of applications to different fields like postal address identification, signature processing, etc. (Mansi and Gordhan, 2013). Because of the variations in the size and type of fonts and the variations in the handwriting styles, the field remains extremely challenging.

There are several steps in the life cycle of character recognition process. They are: digitization, conversion, binarization, feature extraction and finally recognition. Digitization process produces an image into electronic, whereas conversion process converts an image into a suitable format (in our case it is gray-scale) (Jagruti and Mayank, 2014).

 
 

Telecommunications Journal, Binarization methods, Thresholding methods, Fuzzy membership function, K-means clustering method, Evaluation method