Development of text extraction and recognition prototype using Adaptive Resonance Theory 1 (ART1) neural network / Iffarini Idris

Character recognition system can contribute tremendously towards the advancement of automation process and can be useful in many other applications such as Data Entry, Document Processing and Cheque Verification. In this research, a prototype of text extraction and recognition using Adaptive Resonan...

Full description

Saved in:

Bibliographic Details
Main Author:	Idris, Iffarini
Format:	Thesis
Language:	English
Published:	2008
Subjects:	C (Computer program language) C++ Image processing
Online Access:	https://ir.uitm.edu.my/id/eprint/65767/1/65767.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-uitm-ir.65767
record_format	uketd_dc
spelling	my-uitm-ir.657672022-09-22T09:08:11Z Development of text extraction and recognition prototype using Adaptive Resonance Theory 1 (ART1) neural network / Iffarini Idris 2008 Idris, Iffarini C (Computer program language). C++ Image processing Character recognition system can contribute tremendously towards the advancement of automation process and can be useful in many other applications such as Data Entry, Document Processing and Cheque Verification. In this research, a prototype of text extraction and recognition using Adaptive Resonance Theory 1 (ARTl) was proposed. For this project, several sets of images were collected from magazines and text books. In prototype design, the interface of ARTl and the ARTl neural network architecture were designed. The pre-process part of this prototype was developed using MATLAB and the recognition part was developed using C++. During the pre-processing stage, images were converted to binary image. Then, the title of the document images was extracted using Mathematical Morphological technique and the characters were segmented using labeling technique. After the pre-processing stage, each of the pixels value that represent the character will be the input to the ARTl network for character recognition process. ARTl neural network has proven to give good performance with 65.7 % recognition rate. A comparative study was conducted between ARTl and Backpropagation Neural Network (BPNN) to compare their recognition performances. BPNN is unable to meet the performance goal because of insufficient number of training data. In conclusion, ARTl is better than BPNN when the number of training data is small. 2008 Thesis https://ir.uitm.edu.my/id/eprint/65767/ https://ir.uitm.edu.my/id/eprint/65767/1/65767.pdf text en public degree Universiti Teknologi MARA (UiTM) Faculty of Computer and Mathematical Sciences Ibrahim, Zaidah
institution	Universiti Teknologi MARA
collection	UiTM Institutional Repository
language	English
advisor	Ibrahim, Zaidah
topic	C (Computer program language) C++ Image processing
spellingShingle	C (Computer program language) C++ Image processing Idris, Iffarini Development of text extraction and recognition prototype using Adaptive Resonance Theory 1 (ART1) neural network / Iffarini Idris
description	Character recognition system can contribute tremendously towards the advancement of automation process and can be useful in many other applications such as Data Entry, Document Processing and Cheque Verification. In this research, a prototype of text extraction and recognition using Adaptive Resonance Theory 1 (ARTl) was proposed. For this project, several sets of images were collected from magazines and text books. In prototype design, the interface of ARTl and the ARTl neural network architecture were designed. The pre-process part of this prototype was developed using MATLAB and the recognition part was developed using C++. During the pre-processing stage, images were converted to binary image. Then, the title of the document images was extracted using Mathematical Morphological technique and the characters were segmented using labeling technique. After the pre-processing stage, each of the pixels value that represent the character will be the input to the ARTl network for character recognition process. ARTl neural network has proven to give good performance with 65.7 % recognition rate. A comparative study was conducted between ARTl and Backpropagation Neural Network (BPNN) to compare their recognition performances. BPNN is unable to meet the performance goal because of insufficient number of training data. In conclusion, ARTl is better than BPNN when the number of training data is small.
format	Thesis
qualification_level	Bachelor degree
author	Idris, Iffarini
author_facet	Idris, Iffarini
author_sort	Idris, Iffarini
title	Development of text extraction and recognition prototype using Adaptive Resonance Theory 1 (ART1) neural network / Iffarini Idris
title_short	Development of text extraction and recognition prototype using Adaptive Resonance Theory 1 (ART1) neural network / Iffarini Idris
title_full	Development of text extraction and recognition prototype using Adaptive Resonance Theory 1 (ART1) neural network / Iffarini Idris
title_fullStr	Development of text extraction and recognition prototype using Adaptive Resonance Theory 1 (ART1) neural network / Iffarini Idris
title_full_unstemmed	Development of text extraction and recognition prototype using Adaptive Resonance Theory 1 (ART1) neural network / Iffarini Idris
title_sort	development of text extraction and recognition prototype using adaptive resonance theory 1 (art1) neural network / iffarini idris
granting_institution	Universiti Teknologi MARA (UiTM)
granting_department	Faculty of Computer and Mathematical Sciences
publishDate	2008
url	https://ir.uitm.edu.my/id/eprint/65767/1/65767.pdf
_version_	1783735576974852096

Development of text extraction and recognition prototype using Adaptive Resonance Theory 1 (ART1) neural network / Iffarini Idris

Similar Items