Bounded Box-Zoning Integrated Approach For Children Handwriting Recognition

This study focuses on recognizing handwritten character datasets of children through the integration of image processing and machine learning. The bounding box, one of the best structural feature extraction methods, has demonstrated high performance in the optical character recognition (OCR) pipelin...

Full description

Bibliographic Details
Main Author: Qausbee, Nik Nur Adlin Nik
Format: Thesis
Language:English
Published: 2024
Subjects:
Online Access:http://eprints.usm.my/62282/
http://eprints.usm.my/62282/1/24%20Pages%20from%20NIK%20NUR%20ADLIN%20BINTI%20NIK%20QAUSBEE.pdf
_version_ 1848884939945148416
author Qausbee, Nik Nur Adlin Nik
author_facet Qausbee, Nik Nur Adlin Nik
author_sort Qausbee, Nik Nur Adlin Nik
building USM Institutional Repository
collection Online Access
description This study focuses on recognizing handwritten character datasets of children through the integration of image processing and machine learning. The bounding box, one of the best structural feature extraction methods, has demonstrated high performance in the optical character recognition (OCR) pipeline. However, its implementation in children’s handwriting has shown a decreasing trend in alphabet detection. Similarly, zoning, a powerful technique under statistical feature extraction demonstrated good classification but is limited by having unlimited feature values and is not applicable for characters with high variations, such as children’s handwriting. The objectives of this study are to identify significant English alphabets based on their features, propose a bounded box-zoning integrated approach to improve the OCR pipeline and identify the accuracy of the proposed method. The Minnesota Handwriting Assessment (MHA) was utilized for data collection, involving handwriting samples collected from 90 children aged between 6 to 9 years old. The study then proceeded with image processing steps, including alphabet grouping into ‘small’ and ‘tail’ groups, feature extraction using the proposed hybrid method (bounded box-zoning), and classification using the multi-input neural network method.
first_indexed 2025-11-15T19:14:41Z
format Thesis
id usm-62282
institution Universiti Sains Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T19:14:41Z
publishDate 2024
recordtype eprints
repository_type Digital Repository
spelling usm-622822025-05-23T02:05:31Z http://eprints.usm.my/62282/ Bounded Box-Zoning Integrated Approach For Children Handwriting Recognition Qausbee, Nik Nur Adlin Nik QA75.5-76.95 Electronic computers. Computer science This study focuses on recognizing handwritten character datasets of children through the integration of image processing and machine learning. The bounding box, one of the best structural feature extraction methods, has demonstrated high performance in the optical character recognition (OCR) pipeline. However, its implementation in children’s handwriting has shown a decreasing trend in alphabet detection. Similarly, zoning, a powerful technique under statistical feature extraction demonstrated good classification but is limited by having unlimited feature values and is not applicable for characters with high variations, such as children’s handwriting. The objectives of this study are to identify significant English alphabets based on their features, propose a bounded box-zoning integrated approach to improve the OCR pipeline and identify the accuracy of the proposed method. The Minnesota Handwriting Assessment (MHA) was utilized for data collection, involving handwriting samples collected from 90 children aged between 6 to 9 years old. The study then proceeded with image processing steps, including alphabet grouping into ‘small’ and ‘tail’ groups, feature extraction using the proposed hybrid method (bounded box-zoning), and classification using the multi-input neural network method. 2024-03 Thesis NonPeerReviewed application/pdf en http://eprints.usm.my/62282/1/24%20Pages%20from%20NIK%20NUR%20ADLIN%20BINTI%20NIK%20QAUSBEE.pdf Qausbee, Nik Nur Adlin Nik (2024) Bounded Box-Zoning Integrated Approach For Children Handwriting Recognition. PhD thesis, Perpustakaan Hamzah Sendut.
spellingShingle QA75.5-76.95 Electronic computers. Computer science
Qausbee, Nik Nur Adlin Nik
Bounded Box-Zoning Integrated Approach For Children Handwriting Recognition
title Bounded Box-Zoning Integrated Approach For Children Handwriting Recognition
title_full Bounded Box-Zoning Integrated Approach For Children Handwriting Recognition
title_fullStr Bounded Box-Zoning Integrated Approach For Children Handwriting Recognition
title_full_unstemmed Bounded Box-Zoning Integrated Approach For Children Handwriting Recognition
title_short Bounded Box-Zoning Integrated Approach For Children Handwriting Recognition
title_sort bounded box-zoning integrated approach for children handwriting recognition
topic QA75.5-76.95 Electronic computers. Computer science
url http://eprints.usm.my/62282/
http://eprints.usm.my/62282/1/24%20Pages%20from%20NIK%20NUR%20ADLIN%20BINTI%20NIK%20QAUSBEE.pdf