UNSUPERVISED SEGMENTATION OF CORAL REEF IMAGES BY USING COLOR AND TEXTURE FEATURES

Segmentation of natural scenes is an essential task in image processing. It finds a place in many image applications such as retrieval, indexing, classification, surveillance and content-based image retrieval. However, there is clear lack of image segmentation techniques in the literature studies re...

Full description

Saved in:

Bibliographic Details
Main Author:	MOHAMMAD SAMEER ALOUN
Format:	Thesis
Language:	English
Online Access:	http://umt-ir.umt.edu.my:8080/jspui/bitstream/123456789/16019/1/Abstract.pdf http://umt-ir.umt.edu.my:8080/jspui/bitstream/123456789/16019/2/Full%20Thesis%20-%20MOHAMMAD%20SAMEER%20ALOUN.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-umt-ir.-16019
record_format	uketd_dc
spelling	my-umt-ir.-160192022-01-19T08:13:45Z UNSUPERVISED SEGMENTATION OF CORAL REEF IMAGES BY USING COLOR AND TEXTURE FEATURES MOHAMMAD SAMEER ALOUN Segmentation of natural scenes is an essential task in image processing. It finds a place in many image applications such as retrieval, indexing, classification, surveillance and content-based image retrieval. However, there is clear lack of image segmentation techniques in the literature studies related to underwater coral reef images segmentation. This thesis presents new methods to automate the segmentation of underwater coral reef images based on image processing techniques with the combination of color-texture features. The unsupervised segmentation of color-texture regions using J-value segmentation (JSEG) algorithm is one of the most popular and robust unsupervised segmentation algorithms. The JSEG algorithm consists of two stages; color quantization and spatial segmentation. However, the major problem of JSEG algorithm is over-segmentation. The unsupervised image segmentation method groups local pixels that are homogeneous in low-level features into non-overlapped larger regions that may potentially correspond to objects or their parts without any training examples. The over-segmentation occurs when many segments map to a single object. This thesis proposed a modified JSEG algorithm to solve the problem of over segmentation when applying it to underwater coral reef images. UNIVERSITI MALAYSIA TERENGGANU 2021-08 Thesis en http://umt-ir.umt.edu.my:8080/handle/123456789/16019 http://umt-ir.umt.edu.my:8080/jspui/bitstream/123456789/16019/1/Abstract.pdf 2711767d3c1829b397422202db858250 http://umt-ir.umt.edu.my:8080/jspui/bitstream/123456789/16019/2/Full%20Thesis%20-%20MOHAMMAD%20SAMEER%20ALOUN.pdf db53767600cbb3365eb4a24e641b1553 http://umt-ir.umt.edu.my:8080/jspui/bitstream/123456789/16019/3/license.txt 8a4605be74aa9ea9d79846c1fba20a33
institution	Universiti Malaysia Terengganu
collection	UMT Repository System
language	English
description	Segmentation of natural scenes is an essential task in image processing. It finds a place in many image applications such as retrieval, indexing, classification, surveillance and content-based image retrieval. However, there is clear lack of image segmentation techniques in the literature studies related to underwater coral reef images segmentation. This thesis presents new methods to automate the segmentation of underwater coral reef images based on image processing techniques with the combination of color-texture features. The unsupervised segmentation of color-texture regions using J-value segmentation (JSEG) algorithm is one of the most popular and robust unsupervised segmentation algorithms. The JSEG algorithm consists of two stages; color quantization and spatial segmentation. However, the major problem of JSEG algorithm is over-segmentation. The unsupervised image segmentation method groups local pixels that are homogeneous in low-level features into non-overlapped larger regions that may potentially correspond to objects or their parts without any training examples. The over-segmentation occurs when many segments map to a single object. This thesis proposed a modified JSEG algorithm to solve the problem of over segmentation when applying it to underwater coral reef images.
format	Thesis
author	MOHAMMAD SAMEER ALOUN
spellingShingle	MOHAMMAD SAMEER ALOUN UNSUPERVISED SEGMENTATION OF CORAL REEF IMAGES BY USING COLOR AND TEXTURE FEATURES
author_facet	MOHAMMAD SAMEER ALOUN
author_sort	MOHAMMAD SAMEER ALOUN
title	UNSUPERVISED SEGMENTATION OF CORAL REEF IMAGES BY USING COLOR AND TEXTURE FEATURES
title_short	UNSUPERVISED SEGMENTATION OF CORAL REEF IMAGES BY USING COLOR AND TEXTURE FEATURES
title_full	UNSUPERVISED SEGMENTATION OF CORAL REEF IMAGES BY USING COLOR AND TEXTURE FEATURES
title_fullStr	UNSUPERVISED SEGMENTATION OF CORAL REEF IMAGES BY USING COLOR AND TEXTURE FEATURES
title_full_unstemmed	UNSUPERVISED SEGMENTATION OF CORAL REEF IMAGES BY USING COLOR AND TEXTURE FEATURES
title_sort	unsupervised segmentation of coral reef images by using color and texture features
granting_institution	UNIVERSITI MALAYSIA TERENGGANU
url	http://umt-ir.umt.edu.my:8080/jspui/bitstream/123456789/16019/1/Abstract.pdf http://umt-ir.umt.edu.my:8080/jspui/bitstream/123456789/16019/2/Full%20Thesis%20-%20MOHAMMAD%20SAMEER%20ALOUN.pdf
_version_	1747835829292630016

UNSUPERVISED SEGMENTATION OF CORAL REEF IMAGES BY USING COLOR AND TEXTURE FEATURES

Similar Items