This research attempts to use a method that can reduce the search time of a system trying to match a user's iris image against those in a very large database. One method to reduce search time is to predict an individual's ethnicity and then only search iris templates belonging to that particular ethnicity in the database. By limiting the search to a small subsection of the database, as opposed to an exhaustive search, this method will cut significant run time from the search process. We propose the use of an adaptive neuro-fuzzy inference system to implement this idea. In addition to the adaptive neuro-fuzzy inference system, we also used the subtractive clustering technique to create membership functions that helped us compare how each iris' texture features were clustered. By combining subtractive clustering with the adaptive neuro-fuzzy inference system, we were able to map each user to a singular value that identified with a specific ethnicity based on their iris characteristic features. This method achieves a classification rate of 80% while maintaining an acceptable search time.
","abstract_html":"<p>This research attempts to use a method that can reduce the search time of a system trying to match a user's iris image against those in a very large database. One method to reduce search time is to predict an individual's ethnicity and then only search iris templates belonging to that particular ethnicity in the database. By limiting the search to a small subsection of the database, as opposed to an exhaustive search, this method will cut significant run time from the search process. We propose the use of an adaptive neuro-fuzzy inference system to implement this idea. In addition to the adaptive neuro-fuzzy inference system, we also used the subtractive clustering technique to create membership functions that helped us compare how each iris' texture features were clustered. By combining subtractive clustering with the adaptive neuro-fuzzy inference system, we were able to map each user to a singular value that identified with a specific ethnicity based on their iris characteristic features. This method achieves a classification rate of 80% while maintaining an acceptable search time.</p>","abstract_has_math":false,"creators":["Tang, Gary L."],"institution":null,"degree_name":"Master of Science in Engineering (M.S.Eng.)","degree_level":"Thesis - Pacific Access Restricted","degree_discipline":"Engineering","degree_department":null,"school":null,"contributors":["Anahita Zarei"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2014,"date_issued":"2014-01-01T08:00:00Z","date_published":"2014-01-01T08:00:00Z","updated_at":"2026-07-24T05:36:09Z","subjects":["Electrical engineering","Applied sciences","Engineering"],"languages":[],"rights":[],"rights_urls":["http://rightsstatements.org/vocab/InC/1.0/"],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["9781303996887"],"render_values":[{"text":"9781303996887","href":null,"code":true}]}]},"links":{"outbound_url":"https://scholarlycommons.pacific.edu/uop_etds/230","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Anahita Zarei"]},{"key":"dc:creator","label":"Author","values":["Tang, Gary L."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2018-06-29T09:06:19Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis - Pacific Access Restricted"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science in Engineering (M.S.Eng.)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Electrical engineering","Applied sciences","Engineering"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["http://rightsstatements.org/vocab/InC/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["9781303996887","https://scholarlycommons.pacific.edu/uop_etds/230"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This research attempts to use a method that can reduce the search time of a system trying to match a user's iris image against those in a very large database. One method to reduce search time is to predict an individual's ethnicity and then only search iris templates belonging to that particular ethnicity in the database. By limiting the search to a small subsection of the database, as opposed to an exhaustive search, this method will cut significant run time from the search process. We propose the use of an adaptive neuro-fuzzy inference system to implement this idea. In addition to the adaptive neuro-fuzzy inference system, we also used the subtractive clustering technique to create membership functions that helped us compare how each iris' texture features were clustered. By combining subtractive clustering with the adaptive neuro-fuzzy inference system, we were able to map each user to a singular value that identified with a specific ethnicity based on their iris characteristic features. This method achieves a classification rate of 80% while maintaining an acceptable search time.
"]},{"key":"dc:source","label":"Dc Source","values":["55"]},{"key":"dc:title","label":"Title","values":["Fuzzy inference systems for iris biometrics to reduce search time in large databases"]}]}],"canonical_facts":{"dc:contributor":["Anahita Zarei"],"dc:creator":["Tang, Gary L."],"dc:date.available":["2018-06-29T09:06:19Z"],"dc:description.abstract":["This research attempts to use a method that can reduce the search time of a system trying to match a user's iris image against those in a very large database. One method to reduce search time is to predict an individual's ethnicity and then only search iris templates belonging to that particular ethnicity in the database. By limiting the search to a small subsection of the database, as opposed to an exhaustive search, this method will cut significant run time from the search process. We propose the use of an adaptive neuro-fuzzy inference system to implement this idea. In addition to the adaptive neuro-fuzzy inference system, we also used the subtractive clustering technique to create membership functions that helped us compare how each iris' texture features were clustered. By combining subtractive clustering with the adaptive neuro-fuzzy inference system, we were able to map each user to a singular value that identified with a specific ethnicity based on their iris characteristic features. This method achieves a classification rate of 80% while maintaining an acceptable search time.
"],"dc:identifier":["9781303996887","https://scholarlycommons.pacific.edu/uop_etds/230"],"dc:rights":["http://rightsstatements.org/vocab/InC/1.0/"],"dc:source":["55"],"dc:subject":["Electrical engineering","Applied sciences","Engineering"],"dc:title":["Fuzzy inference systems for iris biometrics to reduce search time in large databases"],"thesis:degree_discipline":["Engineering"],"thesis:degree_level":["Thesis - Pacific Access Restricted"],"thesis:degree_name":["Master of Science in Engineering (M.S.Eng.)"]},"updated_at":"2026-07-24T05:36:09Z"}