{"id":{"repo_id":"dcu","oai_identifier":"oai:doras.dcu.ie:16630"},"canonical_url":"https://search.dev.ndltd.org/etd/dcu/oai:doras.dcu.ie:16630","repository":{"repo_id":"dcu","name":"Dublin City University","base_url":"http://doras.dcu.ie/cgi/oai2"},"display":{"title":"A framework for automated landmark recognition in community contributed image corpora","abstract":"Any large library of information requires efficient ways to organise it and methods that allow people to access information efficiently and collections of digital images are no exception. Automatically creating high-level semantic tags based on image content is difficult, if not impossible to achieve accurately. In this thesis a framework is presented that allows for the automatic creation of rich and accurate tags for images with landmarks as the main object. This framework uses state of the art computer vision techniques fused with the wide range of contextual information that is available with community contributed imagery. Images are organised into clusters based on image content and spatial data associated with each image. Based on these clusters different types of classifiers are* trained to recognise landmarks contained within the images in each cluster. A novel hybrid approach is proposed combining these classifiers with an hierarchical matching approach to allow near real-time classification and captioning of images containing landmarks.","abstract_html":"Any large library of information requires efficient ways to organise it and methods that allow people to access information efficiently and collections of digital images are no exception. Automatically creating high-level semantic tags based on image content is difficult, if not impossible to achieve accurately. In this thesis a framework is presented that allows for the automatic creation of rich and accurate tags for images with landmarks as the main object. This framework uses state of the art computer vision techniques fused with the wide range of contextual information that is available with community contributed imagery. Images are organised into clusters based on image content and spatial data associated with each image. Based on these clusters different types of classifiers are* trained to recognise landmarks contained within the images in each cluster. A novel hybrid approach is proposed combining these classifiers with an hierarchical matching approach to allow near real-time classification and captioning of images containing landmarks.","abstract_has_math":false,"creators":["Hughes, Mark"],"institution":"Dublin City University","degree_name":"phd","degree_level":"doctoral","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2011,"date_issued":"2011-11","date_published":"2011-11","updated_at":"2026-07-24T02:00:48Z","subjects":["Multimedia systems","Information retrieval","Image processing"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":null,"outbound_label":null,"outbound_source":null},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.sponsor","label":"Sponsor","values":["FP6 STREP TriPOd"]},{"key":"dc:creator","label":"Author","values":["Hughes, Mark"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2011-11"]},{"key":"dc:date.issued","label":"Date","values":["2011-11"]},{"key":"dc:publisher.institution","label":"Dc Publisher Institution","values":["Dublin City University"]},{"key":"dc:relation.isreferencedby","label":"Dc Relation Isreferencedby","values":["https://doras.dcu.ie/16630/"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"dc:type.qualificationlevel","label":"Dc Type Qualificationlevel","values":["doctoral"]},{"key":"dc:type.qualificationname","label":"Dc Type Qualificationname","values":["phd"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Multimedia systems","Information retrieval","Image processing"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://doras.dcu.ie/16630/1/Thesis.pdf"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Any large library of information requires efficient ways to organise it and methods that allow people to access information efficiently and collections of digital images are no exception. Automatically creating high-level semantic tags based on image content is difficult, if not impossible to achieve accurately. In this thesis a framework is presented that allows for the automatic creation of rich and accurate tags for images with landmarks as the main object. This framework uses state of the art computer vision techniques fused with the wide range of contextual information that is available with community contributed imagery. Images are organised into clusters based on image content and spatial data associated with each image. Based on these clusters different types of classifiers are* trained to recognise landmarks contained within the images in each cluster. A novel hybrid approach is proposed combining these classifiers with an hierarchical matching approach to allow near real-time classification and captioning of images containing landmarks."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["A framework for automated landmark recognition in community contributed image corpora"]}]}],"canonical_facts":{"dc:contributor.sponsor":["FP6 STREP TriPOd"],"dc:creator":["Hughes, Mark"],"dc:date":["2011-11"],"dc:date.issued":["2011-11"],"dc:description.abstract":["Any large library of information requires efficient ways to organise it and methods that allow people to access information efficiently and collections of digital images are no exception. Automatically creating high-level semantic tags based on image content is difficult, if not impossible to achieve accurately. In this thesis a framework is presented that allows for the automatic creation of rich and accurate tags for images with landmarks as the main object. This framework uses state of the art computer vision techniques fused with the wide range of contextual information that is available with community contributed imagery. Images are organised into clusters based on image content and spatial data associated with each image. Based on these clusters different types of classifiers are* trained to recognise landmarks contained within the images in each cluster. A novel hybrid approach is proposed combining these classifiers with an hierarchical matching approach to allow near real-time classification and captioning of images containing landmarks."],"dc:format":["application/pdf"],"dc:identifier.uri":["https://doras.dcu.ie/16630/1/Thesis.pdf"],"dc:language":["en"],"dc:publisher.institution":["Dublin City University"],"dc:relation.isreferencedby":["https://doras.dcu.ie/16630/"],"dc:subject":["Multimedia systems","Information retrieval","Image processing"],"dc:title":["A framework for automated landmark recognition in community contributed image corpora"],"dc:type":["Thesis"],"dc:type.qualificationlevel":["doctoral"],"dc:type.qualificationname":["phd"]},"updated_at":"2026-07-24T02:00:48Z"}