{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/24270"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/24270","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Hand detection on images based on deformable part models and additional features","abstract":"Hand detection on images has important applications on person activities recognition. This thesis focuses on PASCAL Visual Object Classes (VOC) system for hand detection. VOC has become a popular system for object detection, based on twenty common objects, and has been released with a successful deformable parts model in VOC2007. A hand detection on an image is made when the system gets a bounding box which overlaps with at least 50% of any ground truth bounding box for a hand on the image. The initial average precision of this detector is around 0.215 compared with a state-of-art of 0.104; however, color and frequency features for detected bounding boxes contain important information for re-scoring, and the average precision can be improved to 0.218 with these features. Results show that these features help on getting higher precision for low recall, even though the average precision is similar.","abstract_html":"Hand detection on images has important applications on person activities recognition. This thesis focuses on PASCAL Visual Object Classes (VOC) system for hand detection. VOC has become a popular system for object detection, based on twenty common objects, and has been released with a successful deformable parts model in VOC2007. A hand detection on an image is made when the system gets a bounding box which overlaps with at least 50% of any ground truth bounding box for a hand on the image. The initial average precision of this detector is around 0.215 compared with a state-of-art of 0.104; however, color and frequency features for detected bounding boxes contain important information for re-scoring, and the average precision can be improved to 0.218 with these features. Results show that these features help on getting higher precision for low recall, even though the average precision is similar.","abstract_has_math":false,"creators":["Crisostomo Romero, Pedro Moises"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Forsyth, David A."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2011,"date_issued":"2011-05-25T15:08:06Z","date_published":"2011-05-25T15:08:06Z","updated_at":"2026-07-22T22:25:24Z","subjects":["Hand detection","computer vision","machine learning","deformable models","PASCAL Visual Object Classes (VOC)","frequency features","color features","Pattern Analysis Statistical Modeling and Computational Learning (PASCAL)"],"languages":["en"],"rights":["Copyright 2011 Pedro Crisostomo"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/24270","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Forsyth, David A."]},{"key":"dc:creator","label":"Author","values":["Crisostomo Romero, Pedro Moises"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2011-05-25T15:08:06Z","2011-05"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Hand detection","computer vision","machine learning","deformable models","PASCAL Visual Object Classes (VOC)","frequency features","color features","Pattern Analysis Statistical Modeling and Computational Learning (PASCAL)"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2011 Pedro Crisostomo"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/24270"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Hand detection on images has important applications on person activities recognition. This thesis focuses on PASCAL Visual Object Classes (VOC) system for hand detection. VOC has become a popular system for object detection, based on twenty common objects, and has been released with a successful deformable parts model in VOC2007. A hand detection on an image is made when the system gets a bounding box which overlaps with at least 50% of any ground truth bounding box for a hand on the image. The initial average precision of this detector is around 0.215 compared with a state-of-art of 0.104; however, color and frequency features for detected bounding boxes contain important information for re-scoring, and the average precision can be improved to 0.218 with these features. Results show that these features help on getting higher precision for low recall, even though the average precision is similar.","Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2011-04-26T19:11:34Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 1 CrisostomoRomero-PedroMoises.pdf: 1228676 bytes, checksum: f301bb42713ef76c3f6ad6f88b9090cc (MD5)","Made available in DSpace on 2011-05-25T15:08:06Z (GMT). No. of bitstreams: 2 CrisostomoRomero-PedroMoises.pdf: 1228676 bytes, checksum: f301bb42713ef76c3f6ad6f88b9090cc (MD5) license.txt: 4066 bytes, checksum: 78db02e3e1e0c8a4ed45b9f7c622ed89 (MD5)"]},{"key":"dc:title","label":"Title","values":["Hand detection on images based on deformable part models and additional features"]}]}],"canonical_facts":{"dc:contributor":["Forsyth, David A."],"dc:creator":["Crisostomo Romero, Pedro Moises"],"dc:date":["2011-05-25T15:08:06Z","2011-05"],"dc:description":["Hand detection on images has important applications on person activities recognition. This thesis focuses on PASCAL Visual Object Classes (VOC) system for hand detection. VOC has become a popular system for object detection, based on twenty common objects, and has been released with a successful deformable parts model in VOC2007. A hand detection on an image is made when the system gets a bounding box which overlaps with at least 50% of any ground truth bounding box for a hand on the image. The initial average precision of this detector is around 0.215 compared with a state-of-art of 0.104; however, color and frequency features for detected bounding boxes contain important information for re-scoring, and the average precision can be improved to 0.218 with these features. Results show that these features help on getting higher precision for low recall, even though the average precision is similar.","Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2011-04-26T19:11:34Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 1 CrisostomoRomero-PedroMoises.pdf: 1228676 bytes, checksum: f301bb42713ef76c3f6ad6f88b9090cc (MD5)","Made available in DSpace on 2011-05-25T15:08:06Z (GMT). No. of bitstreams: 2 CrisostomoRomero-PedroMoises.pdf: 1228676 bytes, checksum: f301bb42713ef76c3f6ad6f88b9090cc (MD5) license.txt: 4066 bytes, checksum: 78db02e3e1e0c8a4ed45b9f7c622ed89 (MD5)"],"dc:identifier":["http://hdl.handle.net/2142/24270"],"dc:language":["en"],"dc:rights":["Copyright 2011 Pedro Crisostomo"],"dc:subject":["Hand detection","computer vision","machine learning","deformable models","PASCAL Visual Object Classes (VOC)","frequency features","color features","Pattern Analysis Statistical Modeling and Computational Learning (PASCAL)"],"dc:title":["Hand detection on images based on deformable part models and additional features"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:24Z"}