{"id":{"repo_id":"rochester","oai_identifier":"oai:urresearch.rochester.edu:181"},"canonical_url":"https://search.dev.ndltd.org/etd/rochester/oai:urresearch.rochester.edu:181","repository":{"repo_id":"rochester","name":"Rochester University","base_url":"http://urresearch.rochester.edu/oai2.action"},"display":{"title":"Experiments in generic object recognition","abstract":"Thesis (Ph. D.)--University of Rochester. Dept. of Computer Science, 2003.","abstract_html":"Thesis (Ph. D.)--University of Rochester. Dept. of Computer Science, 2003.","abstract_has_math":false,"creators":["Green, Isaac A. (1974 - )","Nelson, Randal C."],"institution":"University of Rochester. Computer Science Department.","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2004,"date_issued":"Wed, 16 Jun 2004 16:30:41","date_published":"Wed, 16 Jun 2004 16:30:41","updated_at":"2026-08-21T22:21:56Z","subjects":["Object recognition","Active recognition","Computer vision"],"languages":["eng"],"rights":["This item is protected by copyright, with all rights reserved."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/1802/285","outbound_label":"Handle","outbound_source":"dc:identifier"},"source_record":{"url":"http://urresearch.rochester.edu/oai2.action?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Aurresearch.rochester.edu%3A181","prefix":"oai_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Green, Isaac A. (1974 - )","Nelson, Randal C."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["Wed, 16 Jun 2004 16:30:41","Year: 2003","Wed, 26 Sep 2012 16:35:14"]},{"key":"dc:publisher","label":"Institution","values":["University of Rochester. Computer Science Department."]},{"key":"dc:type","label":"Dc Type","values":["Technical Report","Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Object recognition","Active recognition","Computer vision"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["This item is protected by copyright, with all rights reserved."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/1802/285"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis (Ph. D.)--University of Rochester. Dept. of Computer Science, 2003.","The task of generic object recognition involves learning to identify members of a class of objects based on a few exemplars from that class. Generic object classes are inherently ill-defined. Objects can be grouped into classes based on varying criteria such as form, function, color, size, etc. In this work, we develop two extensions to a well-studied, 3D view-based, rigid-object recognizer that improve its performance on generic object classes grouped on shape and a related class of objects we call loosely structured objects. The first extension uses clustering on the underlying local context features to discover features that recur within object classes. The modification improves performance for rigid, generic, and loosely structure classes, but it does not reliably discover recurrent features. Further analysis shows most of the performance improvement comes from a side-effect of the clustering algorithm. Namely, features that tend to create noise in the system become marginalized. The second extension takes a principled approach to estimating the quality of each object model feature based on its robustness and commonness. Noisy features get a low quality score and thus contribute less noise to the recognition process. This approach further improves recognition for rigid, generic, and loosely structured object classes over the clustering method. We also develop an active recognition system that achieves better recognition by utilizing additional information available in the active vision setting. The system uses change detection to perform foreground/background segmentation on the scene. This segmentation information is used to command a pan, tilt, zoom camera to acquire a high-resolution image of target regions in the scene. Furthermore, the segmentation information is used to reduce background clutter in these high-resolution target images. Finally, we describe the Memory Assistant application built on top of the active recognition system. This application is designed to assist people with mild to moderate memory loss keep track of important objects in a home environment. A prototype of this system is currently deployed at the Center for Future Health at the University of Rochester Medical Center."]},{"key":"dc:format","label":"Dc Format","values":["Number of Pages:xv, 135 leaves"]},{"key":"dc:title","label":"Title","values":["Experiments in generic object recognition"]}]}],"canonical_facts":{"dc:creator":["Green, Isaac A. (1974 - )","Nelson, Randal C."],"dc:date":["Wed, 16 Jun 2004 16:30:41","Year: 2003","Wed, 26 Sep 2012 16:35:14"],"dc:description":["Thesis (Ph. D.)--University of Rochester. Dept. of Computer Science, 2003.","The task of generic object recognition involves learning to identify members of a class of objects based on a few exemplars from that class. Generic object classes are inherently ill-defined. Objects can be grouped into classes based on varying criteria such as form, function, color, size, etc. In this work, we develop two extensions to a well-studied, 3D view-based, rigid-object recognizer that improve its performance on generic object classes grouped on shape and a related class of objects we call loosely structured objects. The first extension uses clustering on the underlying local context features to discover features that recur within object classes. The modification improves performance for rigid, generic, and loosely structure classes, but it does not reliably discover recurrent features. Further analysis shows most of the performance improvement comes from a side-effect of the clustering algorithm. Namely, features that tend to create noise in the system become marginalized. The second extension takes a principled approach to estimating the quality of each object model feature based on its robustness and commonness. Noisy features get a low quality score and thus contribute less noise to the recognition process. This approach further improves recognition for rigid, generic, and loosely structured object classes over the clustering method. We also develop an active recognition system that achieves better recognition by utilizing additional information available in the active vision setting. The system uses change detection to perform foreground/background segmentation on the scene. This segmentation information is used to command a pan, tilt, zoom camera to acquire a high-resolution image of target regions in the scene. Furthermore, the segmentation information is used to reduce background clutter in these high-resolution target images. Finally, we describe the Memory Assistant application built on top of the active recognition system. This application is designed to assist people with mild to moderate memory loss keep track of important objects in a home environment. A prototype of this system is currently deployed at the Center for Future Health at the University of Rochester Medical Center."],"dc:format":["Number of Pages:xv, 135 leaves"],"dc:identifier":["http://hdl.handle.net/1802/285"],"dc:language":["eng"],"dc:publisher":["University of Rochester. Computer Science Department."],"dc:rights":["This item is protected by copyright, with all rights reserved."],"dc:subject":["Object recognition","Active recognition","Computer vision"],"dc:title":["Experiments in generic object recognition"],"dc:type":["Technical Report","Thesis"]},"updated_at":"2026-08-21T22:21:56Z"}