Chain coding and pre processing stages of handwritten character image file.

Suliman, Azizah and Sulaiman, Mohd. Nasir and Othman, Mohamed and Wirza, Rahmita (2010) Chain coding and pre processing stages of handwritten character image file. electronic Journal of Computer Science and Information Technology (eJCSIT), 2 (1). pp. 6-13.

Full text not available from this repository.

Abstract

In this paper detailed descriptions of the algorithms used in the pre-processing and feature extraction phases of an offline handwritten character are discussed. In classifying handwritten characters, the stages prior to the classification phase play a role as major as the classification itself. There are many pre-processing functions and methods that can be used and different research works will use different methods. This paper discusses in detail some of the algorithms used in the pre-processing stages of an offline handwritten character image file. This paper serves as part of the whole research work that aims at recognizing handwritten characters. The whole research presents a hybrid approach of HMM and Fuzzy Logic in the field of handwritten character recognition. Fuzzy Logic is used in the classification phase while HMM is used in the process of extracting features for the preparation of linguistic variables of the fuzzy rules. However, only the preprocessing stages as employed by the research are described here. The pre-processing phase starts from reading in the input file, the process of binarization, reference line estimation and thinning of the character image for further use in the next stage of the feature extraction and recognition process. Each of the pre-processing stages and the chain coding process will be described in detail giving improvised algorithms, and examples of the processes on existing samples from the database shown. Where comparing experiments with other methods is done, the experimental results are given.

Item Type:Article
Keyword:Pre-processing; Feature extraction; Chain-coding; Binarization; Thinning; Handwritten character
Subject:Writing - Identification - Data processing.
Subject:Expert systems (Computer science).
Subject:Optical character recognition.
Faculty or Institute:Faculty of Computer Science and Information Technology
Publisher:eJCSIT
ID Code:13508
Deposited By: Umikalthom Abdullah
Deposited On:29 Mar 2012 01:05
Last Modified:29 Mar 2012 01:05

Repository Staff Only: Edit item detail

Document Download Statistics

This item has been downloaded for since 29 Mar 2012 01:05.

View statistics for "Chain coding and pre processing stages of handwritten character image file."


Universiti Putra Malaysia Institutional Repository

Universiti Putra Malaysia Institutional Repository is an on-line digital archive that serves as a central collection and storage of scientific information and research at the Universiti Putra Malaysia.

Currently, the collections deposited in the IR consists of Master and PhD theses, Master and PhD Project Report, Journal Articles, Journal Bulletins, Conference Papers, UPM News, Newspaper Cuttings, Patents and Inaugural Lectures.

As the policy of the university does not permit users to view thesis in full text, access is only given to the first 24 pages only.