Show simple item record

dc.contributor.advisorFaichney, Jolon
dc.contributor.authorBeheshti, Maedeh
dc.date.accessioned2018-01-23T02:17:30Z
dc.date.available2018-01-23T02:17:30Z
dc.date.issued2017
dc.identifier.doi10.25904/1912/1465
dc.identifier.urihttp://hdl.handle.net/10072/365378
dc.description.abstractIn our digital era, many attempts in remote sensing, fashion, crime prevention, publishing, medicine, architecture and bio-medicine have resulted in a large number of image data sets. Traditional methods to search and retrieve from these data sets are gradually being replaced by state-of-the-art and modern techniques such as content based image retrieval. Retrieving images through extracting contents as a feature and a similarity measure is one of the most challenging applications of computer vision. Due to the increasing number of images with different varieties and types, the traditional content based image retrieval systems are unable to properly exploit the content information of images for retrieval. Thus, extracting relevant features of images and finding a measure of image similarity that returns appropriate relationships is challenging. Content Based Image Retrieval (CBIR) is one of the open problems which still needs much more research effort to completely replace traditional retrieval systems. Feature extraction based on colour, texture, shape and etc. which has been done locally or globally for an image is one of the main parts of CBIR. Image segmentation, which extracts objects from the background and partitioning an image into several regions, helps facilitate feature extraction based on shapes or region of interest (ROI).
dc.languageEnglish
dc.publisherGriffith University
dc.publisher.placeBrisbane
dc.rights.copyrightThe author owns the copyright in this thesis, unless stated otherwise.
dc.subject.keywordsAutoimmune clustering
dc.subject.keywordsImage data sets
dc.subject.keywordsContent based image retrieval
dc.subject.keywordsImage retrieval
dc.titleSegmentation, Feature Extraction & Autoimmune Clustering for Foreground-background Image Retrieval
dc.typeGriffith thesis
dc.date.embargoEnd2018-12-20
gro.facultyScience, Environment, Engineering and Technology
gro.rights.copyrightThe author owns the copyright in this thesis, unless stated otherwise.
gro.hasfulltextFull Text
dc.contributor.otheradvisorWu, Xin-Wen
gro.identifier.gurtIDgu1500350747649
gro.thesis.degreelevelThesis (PhD Doctorate)
gro.thesis.degreeprogramDoctor of Philosophy (PhD)
gro.departmentSchool of IInformation and Communication Technology
gro.griffith.authorBeheshti, Maedeh


Files in this item

This item appears in the following Collection(s)

Show simple item record