{"id":{"repo_id":"greece","oai_identifier":"oai:10442/39701"},"canonical_url":"https://search.ndltd.org/etd/greece/oai:10442/39701","repository":{"repo_id":"greece","name":"Greek National Archive of PhD Theses","base_url":"https://phdtheses.ekt.gr/eadd_oai/request"},"display":{"title":"Τεχνικές μηχανικής όρασης και αναγνώρισης προτύπων για την αλληλεπίδραση ανθρώπου-υπολογιστή","abstract":"The aim of the present thesis was to design pattern recognition and video processing techniques for the development of human-computer interaction applications. We studied the problems of automatic human action recognition and person identification based on actions. We proposed novel action video representation techniques that can exploit enriched visual information coming from multi-camera setups. We proposed novel classification techniques based on discriminant analysis, artificial neural networks and dynamic classification techniques and probabilistic models. Finally, it has been shown that the proposed approaches can be employed for the recognition of human emotions based on facial expressions","abstract_html":"The aim of the present thesis was to design pattern recognition and video processing techniques for the development of human-computer interaction applications. We studied the problems of automatic human action recognition and person identification based on actions. We proposed novel action video representation techniques that can exploit enriched visual information coming from multi-camera setups. We proposed novel classification techniques based on discriminant analysis, artificial neural networks and dynamic classification techniques and probabilistic models. Finally, it has been shown that the proposed approaches can be employed for the recognition of human emotions based on facial expressions","abstract_has_math":false,"creators":["Iosifidis, Alexandros","Ιωσηφίδης, Αλέξανδρος"],"institution":"Aristotle University Of Thessaloniki (AUTH)","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2013,"date_issued":"2013","date_published":"2013","updated_at":"2026-11-18T21:28:31Z","subjects":["Όραση μηχανής","Αναγνώριση προτύπων","Αλληλεπίδραση ανθρώπου - υπολογιστή","Επεξεργασία εικονοσειρών","Computer vision","Pattern recognition","Human-computer interaction","Video processing","Φυσικές Επιστήμες","Επιστήμη Ηλεκτρονικών Υπολογιστών και Πληροφορική","Επιστήμες Μηχανικού και Τεχνολογία","Επιστήμη Ηλεκτρολόγου Μηχανικού, Ηλεκτρονικού Μηχανικού, Μηχανικού Η/Υ","Natural Sciences","Computer and Information Sciences","Engineering and Technology","Electrical Engineering, Electronic Engineering, Information Engineering"],"languages":["gre"],"rights":["BY_NC_ND"],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["10.12681/eadd/39701"],"render_values":[{"text":"10.12681/eadd/39701","href":"https://doi.org/10.12681/eadd/39701","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/10442/hedi/39701","outbound_label":"Handle","outbound_source":"dc:identifier","record_url":"http://hdl.handle.net/10442/hedi/39701","record_label":"Repository record","record_kind":"handle","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://phdtheses.ekt.gr/eadd_oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3A10442%2F39701","prefix":"oai_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Iosifidis, Alexandros","Ιωσηφίδης, Αλέξανδρος"]},{"key":"dc:creator.fathername","label":"Dc Creator Fathername","values":["Iosif"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2013"]},{"key":"dc:publisher","label":"Institution","values":["Aristotle University Of Thessaloniki (AUTH)","Αριστοτέλειο Πανεπιστήμιο Θεσσαλονίκης (ΑΠΘ)"]},{"key":"dc:type","label":"Dc Type","values":["PhD Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Όραση μηχανής","Αναγνώριση προτύπων","Αλληλεπίδραση ανθρώπου - υπολογιστή","Επεξεργασία εικονοσειρών","Computer vision","Pattern recognition","Human-computer interaction","Video processing","Φυσικές Επιστήμες","Επιστήμη Ηλεκτρονικών Υπολογιστών και Πληροφορική","Επιστήμες Μηχανικού και Τεχνολογία","Επιστήμη Ηλεκτρολόγου Μηχανικού, Ηλεκτρονικού Μηχανικού, Μηχανικού Η/Υ","Natural Sciences","Computer and Information Sciences","Engineering and Technology","Electrical Engineering, Electronic Engineering, Information Engineering"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["gre"]},{"key":"dc:rights","label":"Dc Rights","values":["BY_NC_ND"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["10.12681/eadd/39701","http://hdl.handle.net/10442/hedi/39701"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["The aim of the present thesis was to design pattern recognition and video processing techniques for the development of human-computer interaction applications. We studied the problems of automatic human action recognition and person identification based on actions. We proposed novel action video representation techniques that can exploit enriched visual information coming from multi-camera setups. We proposed novel classification techniques based on discriminant analysis, artificial neural networks and dynamic classification techniques and probabilistic models. Finally, it has been shown that the proposed approaches can be employed for the recognition of human emotions based on facial expressions","Σκοπός της διατριβής ήταν ο σχεδιασμός τεχνικών αναγνώρισης προτύπων και επεξεργασίας εικονοσειρών για την ανάπτυξη εφαρμογών αλληλεπίδρασης ανθρώπου-υπολογιστή. Μελετήθηκαν τα προβλήματα της αυτόματης αναγνώρισης ανθρώπινων κινήσεων και ταυτο-ποίησης ατόμων με βάση τον τρόπο εκτέλεσης κινήσεων. Προτάθηκαν πρωτότυπες τεχνικές αναπαράστασης εικονοσειρών κίνησης οι οποίες είναι σε θέση να κάνουν χρήση ενισχυμένης οπτικής πληροφορίας προερχόμενη από συστήματα πολλαπλών καμερών. Προτάθηκαν πρωτό-τυπες τεχνικές ταξινόμησης βασισμένες σε τεχνικές διακριτικής ανάλυσης, τεχνιτών νευρω-νικών δικτύων, δυναμικής ταξινόμησης και πιθανοκρατικών μοντέλων. Τέλος, δείχθηκε ότι οι προτεινόμενες προσεγγίσεις μπορούν να χρησιμοποιηθούν και για την αναγνώριση ανθρώπινων συναισθημάτων με βάση τις εκφράσεις προσώπου."]},{"key":"dc:title","label":"Title","values":["Τεχνικές μηχανικής όρασης και αναγνώρισης προτύπων για την αλληλεπίδραση ανθρώπου-υπολογιστή","Computer vision and pattern recognition techniques for human-computer interaction"]}]}],"canonical_facts":{"dc:creator":["Iosifidis, Alexandros","Ιωσηφίδης, Αλέξανδρος"],"dc:creator.fathername":["Iosif"],"dc:date":["2013"],"dc:description":["The aim of the present thesis was to design pattern recognition and video processing techniques for the development of human-computer interaction applications. We studied the problems of automatic human action recognition and person identification based on actions. We proposed novel action video representation techniques that can exploit enriched visual information coming from multi-camera setups. We proposed novel classification techniques based on discriminant analysis, artificial neural networks and dynamic classification techniques and probabilistic models. Finally, it has been shown that the proposed approaches can be employed for the recognition of human emotions based on facial expressions","Σκοπός της διατριβής ήταν ο σχεδιασμός τεχνικών αναγνώρισης προτύπων και επεξεργασίας εικονοσειρών για την ανάπτυξη εφαρμογών αλληλεπίδρασης ανθρώπου-υπολογιστή. Μελετήθηκαν τα προβλήματα της αυτόματης αναγνώρισης ανθρώπινων κινήσεων και ταυτο-ποίησης ατόμων με βάση τον τρόπο εκτέλεσης κινήσεων. Προτάθηκαν πρωτότυπες τεχνικές αναπαράστασης εικονοσειρών κίνησης οι οποίες είναι σε θέση να κάνουν χρήση ενισχυμένης οπτικής πληροφορίας προερχόμενη από συστήματα πολλαπλών καμερών. Προτάθηκαν πρωτό-τυπες τεχνικές ταξινόμησης βασισμένες σε τεχνικές διακριτικής ανάλυσης, τεχνιτών νευρω-νικών δικτύων, δυναμικής ταξινόμησης και πιθανοκρατικών μοντέλων. Τέλος, δείχθηκε ότι οι προτεινόμενες προσεγγίσεις μπορούν να χρησιμοποιηθούν και για την αναγνώριση ανθρώπινων συναισθημάτων με βάση τις εκφράσεις προσώπου."],"dc:identifier":["10.12681/eadd/39701","http://hdl.handle.net/10442/hedi/39701"],"dc:language":["gre"],"dc:publisher":["Aristotle University Of Thessaloniki (AUTH)","Αριστοτέλειο Πανεπιστήμιο Θεσσαλονίκης (ΑΠΘ)"],"dc:rights":["BY_NC_ND"],"dc:subject":["Όραση μηχανής","Αναγνώριση προτύπων","Αλληλεπίδραση ανθρώπου - υπολογιστή","Επεξεργασία εικονοσειρών","Computer vision","Pattern recognition","Human-computer interaction","Video processing","Φυσικές Επιστήμες","Επιστήμη Ηλεκτρονικών Υπολογιστών και Πληροφορική","Επιστήμες Μηχανικού και Τεχνολογία","Επιστήμη Ηλεκτρολόγου Μηχανικού, Ηλεκτρονικού Μηχανικού, Μηχανικού Η/Υ","Natural Sciences","Computer and Information Sciences","Engineering and Technology","Electrical Engineering, Electronic Engineering, Information Engineering"],"dc:title":["Τεχνικές μηχανικής όρασης και αναγνώρισης προτύπων για την αλληλεπίδραση ανθρώπου-υπολογιστή","Computer vision and pattern recognition techniques for human-computer interaction"],"dc:type":["PhD Thesis"]},"updated_at":"2026-11-18T21:28:31Z"}