{"id":{"repo_id":"unr","oai_identifier":"oai:scholarwolf.unr.edu:11714/10960"},"canonical_url":"https://search.dev.ndltd.org/etd/unr/oai:scholarwolf.unr.edu:11714/10960","repository":{"repo_id":"unr","name":"University of Nevada - Reno","base_url":"https://scholarwolf.unr.edu/server/oai/request"},"display":{"title":"Identity Level Attributes for Explainable Facial Verification","abstract":"Attributes are describable features of faces and are the foundational visual component that humans use to recognize faces. Current state-of-the-art facial recognition methods are end-to-end deep learning systems that are not interpretable by humans. In this thesis, we introduce a new type of facial attribute label representing identity-level prominent features on an existing face image dataset, CarVer, evaluating its performance against another facial attribute dataset, CelebA. Additionally, we expand CarVer with a set of images from internet sources, creating a new dataset we call CarVerX. This thesis analyzes the utility of identity-level prominent features for explainable face verification. We find that our prominent features outperform traditional facial attributes for the task of face verification opening the door for future research along this avenue for explainable face verification.","abstract_html":"Attributes are describable features of faces and are the foundational visual component that humans use to recognize faces. Current state-of-the-art facial recognition methods are end-to-end deep learning systems that are not interpretable by humans. In this thesis, we introduce a new type of facial attribute label representing identity-level prominent features on an existing face image dataset, CarVer, evaluating its performance against another facial attribute dataset, CelebA. Additionally, we expand CarVer with a set of images from internet sources, creating a new dataset we call CarVerX. This thesis analyzes the utility of identity-level prominent features for explainable face verification. We find that our prominent features outperform traditional facial attributes for the task of face verification opening the door for future research along this avenue for explainable face verification.","abstract_has_math":false,"creators":["Flourens, Cooper"],"institution":"University of Nevada, Reno","degree_name":"Master of Science","degree_level":"Master's Degree","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Hand, Emily"],"committee_chairs":[],"committee_members":["Tavakkoli, Alireza","Young, Benjamin"],"year":2024,"date_issued":"2024","date_published":"2024","updated_at":"2026-07-27T21:45:57Z","subjects":["Attributes","Explainability","Face Verification","Interpretability"],"languages":[],"rights":["Creative Commons Attribution-NonCommercial 4.0 International"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://scholarwolf.unr.edu/handle/11714/10960","outbound_label":"Repository record","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Hand, Emily"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Tavakkoli, Alireza","Young, Benjamin"]},{"key":"dc:creator","label":"Author","values":["Flourens, Cooper"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2024-08-22T17:28:30Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2024-08-22T17:28:30Z"]},{"key":"dc:date.issued","label":"Date","values":["2024"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Master's Degree"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Nevada, Reno"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Attributes","Explainability","Face Verification","Interpretability"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["Creative Commons Attribution-NonCommercial 4.0 International"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://scholarwolf.unr.edu/handle/11714/10960"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Attributes are describable features of faces and are the foundational visual component that humans use to recognize faces. Current state-of-the-art facial recognition methods are end-to-end deep learning systems that are not interpretable by humans. In this thesis, we introduce a new type of facial attribute label representing identity-level prominent features on an existing face image dataset, CarVer, evaluating its performance against another facial attribute dataset, CelebA. Additionally, we expand CarVer with a set of images from internet sources, creating a new dataset we call CarVerX. This thesis analyzes the utility of identity-level prominent features for explainable face verification. We find that our prominent features outperform traditional facial attributes for the task of face verification opening the door for future research along this avenue for explainable face verification."]},{"key":"dc:format","label":"Dc Format","values":["PDF"]},{"key":"dc:title","label":"Title","values":["Identity Level Attributes for Explainable Facial Verification"]}]}],"canonical_facts":{"dc:contributor.advisor":["Hand, Emily"],"dc:contributor.committeemember":["Tavakkoli, Alireza","Young, Benjamin"],"dc:creator":["Flourens, Cooper"],"dc:date.accessioned":["2024-08-22T17:28:30Z"],"dc:date.available":["2024-08-22T17:28:30Z"],"dc:date.issued":["2024"],"dc:description.abstract":["Attributes are describable features of faces and are the foundational visual component that humans use to recognize faces. Current state-of-the-art facial recognition methods are end-to-end deep learning systems that are not interpretable by humans. In this thesis, we introduce a new type of facial attribute label representing identity-level prominent features on an existing face image dataset, CarVer, evaluating its performance against another facial attribute dataset, CelebA. Additionally, we expand CarVer with a set of images from internet sources, creating a new dataset we call CarVerX. This thesis analyzes the utility of identity-level prominent features for explainable face verification. We find that our prominent features outperform traditional facial attributes for the task of face verification opening the door for future research along this avenue for explainable face verification."],"dc:format":["PDF"],"dc:identifier.uri":["https://scholarwolf.unr.edu/handle/11714/10960"],"dc:rights":["Creative Commons Attribution-NonCommercial 4.0 International"],"dc:subject":["Attributes","Explainability","Face Verification","Interpretability"],"dc:title":["Identity Level Attributes for Explainable Facial Verification"],"dc:type":["Thesis"],"thesis:degree_level":["Master's Degree"],"thesis:degree_name":["Master of Science"],"thesis:institution_name":["University of Nevada, Reno"]},"updated_at":"2026-07-27T21:45:57Z"}