UPM Institutional Repository

Chain coding and pre processing stages of handwritten character image file


Citation

Suliman, Azizah and Sulaiman, Md. Nasir and Othman, Mohamed and O. K. Rahmat, Rahmita Wirza (2010) Chain coding and pre processing stages of handwritten character image file. Electronic Journal of Computer Science and Information Technology, 2 (1). pp. 6-13. ISSN 1985-7721

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.


Download File

[img]
Preview
Text (Abstract)
Chain coding and pre processing stages of handwritten character image file.pdf

Download (35kB) | Preview

Additional Metadata

Item Type: Article
Divisions: Faculty of Computer Science and Information Technology
Publisher: College of Information Technology, Universiti Tenaga Nasional
Keywords: Pre-processing; Feature extraction; Chain-coding; Binarization; Thinning; Handwritten character
Depositing User: Umikalthom Abdullah
Date Deposited: 29 Mar 2012 01:05
Last Modified: 24 Oct 2018 03:21
URI: http://psasir.upm.edu.my/id/eprint/13508
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item