IUP Publications Online
Home About IUP Magazines Journals Books Archives
     
Recommend    |    Subscriber Services    |    Feedback    |     Subscribe Online
 
The IUP Journal of Computer Sciences :
Handwriting Recognition Using Haar Transform
:
:
:
:
:
:
:
:
:
 
 
 
 
 
 
 

The objective of the paper is to receive intelligible handwritten input from paper documents and convert it into understandable format. Handwriting recognition involves the automatic conversion of text in a document into letter codes which are usable within computer and text-processing applications (Hanna et al., 1997). The information contained within these documents must first be extracted from the hard copy using optical scanner and then stored in a computerized format, which can be easily understood. The data obtained by this form is regarded as a static representation of handwriting (Read et al., 2002a). This technology is successfully used by businesses which process lots of handwritten documents, like insurance companies.

 
 
 

Handwriting recognition is the ability of a computer to receive and interpret intelligible handwritten input from sources such as paper documents, photographs, touch-screens and other devices. The image of the written text may be sensed “off line” from a piece of paper by optical scanning (optical character recognition) or intelligent word recognition.

Haar transform is the simplest of the wavelet transforms. This transform cross-multiplies a function against the Haar wavelet with various shifts and stretches, like the Fourier transform cross-multiplies a function against a sine wave with two phases and many stretches.

Haar transform is applied to the scanned input, which causes the core information to be extracted from that image. Dilation is applied to the extracted core image which makes any blur image to appear clearly.

In the traditional system, reading the text of old script by human eye is difficult. The text may not be clear or the text is not written properly which cannot be read by humans easily. The cursive writing by humans is also sometimes difficult to understand, so a new system has been proposed in this paper.

 
 
 

Computer Sciences IUP Journal , Optical Character Recognition (OCR), Finite State Machine (FSM), First in First Out (FIFO).