Hybrid Region Merging For Image Segmentation Using Optimal Global Feature With Global Merging Criterion Approach

Region merging approach is used to reduce over segmented regions produced by region-based image segmentation algorithms. It is performed by merging the over segmented regions progressively to produce the final segmentation as spatially contiguous regions with closed boundaries. Predominantly, region...

全面介紹

Saved in:
書目詳細資料
主要作者: Vadiveloo, Mogana
格式: Thesis
語言:English
出版: 2020
主題:
在線閱讀:http://eprints.usm.my/55616/1/Pages%20from%20THESIS%20by%20MOGANA%20cut.pdf
標簽: 添加標簽
沒有標簽, 成為第一個標記此記錄!
id my-usm-ep.55616
record_format uketd_dc
spelling my-usm-ep.556162022-11-11T02:00:32Z Hybrid Region Merging For Image Segmentation Using Optimal Global Feature With Global Merging Criterion Approach 2020-02 Vadiveloo, Mogana QA75.5-76.95 Electronic computers. Computer science Region merging approach is used to reduce over segmented regions produced by region-based image segmentation algorithms. It is performed by merging the over segmented regions progressively to produce the final segmentation as spatially contiguous regions with closed boundaries. Predominantly, region merging is performed between two neighboring regions solely on a local merging criterion. This may fail most existing region merging approaches to detect large non-homogeneous visual objects that have global semantic similarity but consist of diverse set of over segmented regions. Besides that, improper selection of global feature information by partitional clustering algorithm in turn affects the merging criterion derivation in region merging eventually causing leakages into adjacent visual object regions. Consequently, this thesis aims to solve these two issues by proposing a region merging approach to merge the over segmented regions producing semantic segments of visual objects regions. 2020-02 Thesis http://eprints.usm.my/55616/ http://eprints.usm.my/55616/1/Pages%20from%20THESIS%20by%20MOGANA%20cut.pdf application/pdf en public phd doctoral Universiti Sains Malaysia Pusat Pengajian Sains Komputer (School of Computer Sciences)
institution Universiti Sains Malaysia
collection USM Institutional Repository
language English
topic QA75.5-76.95 Electronic computers
Computer science
spellingShingle QA75.5-76.95 Electronic computers
Computer science
Vadiveloo, Mogana
Hybrid Region Merging For Image Segmentation Using Optimal Global Feature With Global Merging Criterion Approach
description Region merging approach is used to reduce over segmented regions produced by region-based image segmentation algorithms. It is performed by merging the over segmented regions progressively to produce the final segmentation as spatially contiguous regions with closed boundaries. Predominantly, region merging is performed between two neighboring regions solely on a local merging criterion. This may fail most existing region merging approaches to detect large non-homogeneous visual objects that have global semantic similarity but consist of diverse set of over segmented regions. Besides that, improper selection of global feature information by partitional clustering algorithm in turn affects the merging criterion derivation in region merging eventually causing leakages into adjacent visual object regions. Consequently, this thesis aims to solve these two issues by proposing a region merging approach to merge the over segmented regions producing semantic segments of visual objects regions.
format Thesis
qualification_name Doctor of Philosophy (PhD.)
qualification_level Doctorate
author Vadiveloo, Mogana
author_facet Vadiveloo, Mogana
author_sort Vadiveloo, Mogana
title Hybrid Region Merging For Image Segmentation Using Optimal Global Feature With Global Merging Criterion Approach
title_short Hybrid Region Merging For Image Segmentation Using Optimal Global Feature With Global Merging Criterion Approach
title_full Hybrid Region Merging For Image Segmentation Using Optimal Global Feature With Global Merging Criterion Approach
title_fullStr Hybrid Region Merging For Image Segmentation Using Optimal Global Feature With Global Merging Criterion Approach
title_full_unstemmed Hybrid Region Merging For Image Segmentation Using Optimal Global Feature With Global Merging Criterion Approach
title_sort hybrid region merging for image segmentation using optimal global feature with global merging criterion approach
granting_institution Universiti Sains Malaysia
granting_department Pusat Pengajian Sains Komputer (School of Computer Sciences)
publishDate 2020
url http://eprints.usm.my/55616/1/Pages%20from%20THESIS%20by%20MOGANA%20cut.pdf
_version_ 1776101099579637760