{"id":{"repo_id":"usf","oai_identifier":"oai:digitalcommons.usf.edu:etd-1787"},"canonical_url":"https://search.ndltd.org/etd/usf/oai:digitalcommons.usf.edu:etd-1787","repository":{"repo_id":"usf","name":"University of South Florida","base_url":"https://digitalcommons.usf.edu/do/oai/"},"display":{"title":"A Vision-Based Approach For Unsupervised Modeling Of Signs Embedded In Continuous Sentences","abstract":"The common practice in sign language recognition is to first construct individual sign models, in terms of discrete state transitions, mostly represented using Hidden Markov Models, from manually isolated sign samples and then to use them to recognize signs in continuous sentences. In this thesis we use a continuous state space model, where the states are based on purely image-based features, without the use of special gloves. We also present an unsupervised approach to both extract and learn models for continuous basic units of signs, which we term as signemes, from continuous sentences. Given a set of sentences with a common sign, we can automatically learn the model for part of the sign,or signeme, that is least affected by coarticulation effects. We tested our idea using the publicly available Boston SignStreamDataset by building signeme models of 18 signs. We test the quality of the models by considering how well we can localize the sign in a new sentence. We also present the concept of smooth continuous curve based models formed using functional splines and curve registration. We illustrate this idea using 16 signs.","abstract_html":"The common practice in sign language recognition is to first construct individual sign models, in terms of discrete state transitions, mostly represented using Hidden Markov Models, from manually isolated sign samples and then to use them to recognize signs in continuous sentences. In this thesis we use a continuous state space model, where the states are based on purely image-based features, without the use of special gloves. We also present an unsupervised approach to both extract and learn models for continuous basic units of signs, which we term as signemes, from continuous sentences. Given a set of sentences with a common sign, we can automatically learn the model for part of the sign,or signeme, that is least affected by coarticulation effects. We tested our idea using the publicly available Boston SignStreamDataset by building signeme models of 18 signs. We test the quality of the models by considering how well we can localize the sign in a new sentence. We also present the concept of smooth continuous curve based models formed using functional splines and curve registration. We illustrate this idea using 16 signs.","abstract_has_math":false,"creators":["Nayak, Sunita"],"institution":"University of South Florida","degree_name":null,"degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Sudeep Sarkar, Ph.D.","Barbara Loeding, Ph.D.","Rangachar Kasturi, Ph.D."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2005,"date_issued":"2005-07-07T07:00:00Z","date_published":"2005-07-07T07:00:00Z","updated_at":"2026-11-19T08:34:07Z","subjects":["Sign language","Gestures","Space of relational distributions","Learning","Principal component analysis","American Studies","Arts and Humanities"],"languages":["EN-US"],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.usf.edu/etd/788","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.usf.edu/etd/788","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.usf.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.usf.edu%3Aetd-1787","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Sudeep Sarkar, Ph.D.","Barbara Loeding, Ph.D.","Rangachar Kasturi, Ph.D."]},{"key":"dc:creator","label":"Author","values":["Nayak, Sunita"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2005-07-07T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis","M.S.C.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of South Florida"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Sign language","Gestures","Space of relational distributions","Learning","Principal component analysis","American Studies","Arts and Humanities"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["EN-US"]},{"key":"dc:rights.license","label":"Dc Rights License","values":["default"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.usf.edu/etd/788"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["The common practice in sign language recognition is to first construct individual sign models, in terms of discrete state transitions, mostly represented using Hidden Markov Models, from manually isolated sign samples and then to use them to recognize signs in continuous sentences. In this thesis we use a continuous state space model, where the states are based on purely image-based features, without the use of special gloves. We also present an unsupervised approach to both extract and learn models for continuous basic units of signs, which we term as signemes, from continuous sentences. Given a set of sentences with a common sign, we can automatically learn the model for part of the sign,or signeme, that is least affected by coarticulation effects. We tested our idea using the publicly available Boston SignStreamDataset by building signeme models of 18 signs. We test the quality of the models by considering how well we can localize the sign in a new sentence. We also present the concept of smooth continuous curve based models formed using functional splines and curve registration. We illustrate this idea using 16 signs."]},{"key":"dc:title","label":"Title","values":["A Vision-Based Approach For Unsupervised Modeling Of Signs Embedded In Continuous Sentences"]}]}],"canonical_facts":{"dc:contributor":["Sudeep Sarkar, Ph.D.","Barbara Loeding, Ph.D.","Rangachar Kasturi, Ph.D."],"dc:creator":["Nayak, Sunita"],"dc:date":["2005-07-07T07:00:00Z"],"dc:description":["The common practice in sign language recognition is to first construct individual sign models, in terms of discrete state transitions, mostly represented using Hidden Markov Models, from manually isolated sign samples and then to use them to recognize signs in continuous sentences. In this thesis we use a continuous state space model, where the states are based on purely image-based features, without the use of special gloves. We also present an unsupervised approach to both extract and learn models for continuous basic units of signs, which we term as signemes, from continuous sentences. Given a set of sentences with a common sign, we can automatically learn the model for part of the sign,or signeme, that is least affected by coarticulation effects. We tested our idea using the publicly available Boston SignStreamDataset by building signeme models of 18 signs. We test the quality of the models by considering how well we can localize the sign in a new sentence. We also present the concept of smooth continuous curve based models formed using functional splines and curve registration. We illustrate this idea using 16 signs."],"dc:identifier":["https://digitalcommons.usf.edu/etd/788"],"dc:language":["EN-US"],"dc:rights.license":["default"],"dc:subject":["Sign language","Gestures","Space of relational distributions","Learning","Principal component analysis","American Studies","Arts and Humanities"],"dc:title":["A Vision-Based Approach For Unsupervised Modeling Of Signs Embedded In Continuous Sentences"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis","M.S.C.S."],"thesis:institution_name":["University of South Florida"]},"updated_at":"2026-11-19T08:34:07Z"}