{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/29657"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/29657","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Fast and robust face recognition via parallelized L1 minimization","abstract":"Many classic and contemporary face recognition algorithms work well on public data sets, but degrade sharply when they are used in a real recognition system. A major cause of this is the difficulty of simultaneously handling variations in illumination, image misalignment, and occlusion in the test image; while in some applications the gallery images can be well controlled, the test images are only loosely controlled. This thesis describes a conceptually simple but computationally intense face recognition system that achieves a high degree of robustness and stability to illumination variation, image misalignment, and partial occlusion, along with optimized parallel implementations. First, well registered training images taken under many illumination directions are captured using a novel projector-based acquisition system. The recognition system then uses tools from sparse representation to align a test face image to a set of frontal training images. To better handle severe occlusions, an extension to the algorithm is described that makes use of the knowledge that occluded pixels tend to be spatially correlated. Due to the use of multiple face images as features and the non-smooth nature of the optimization problems, these techniques have far greater computational requirements than techniques that extract low-dimensional features. Several custom L1 solvers are presented that achieve faster convergence on face data than general solvers. Optimized implementations for modern parallel computing architectures are investigated in order to build a system capable of performing highly accurate and robust recognition while remaining fast enough for use in access control systems. Optimized parallel implementations for contemporary CPU and GPU hardware are demonstrated to achieve near real-time face recognition for access control applications with hundreds of gallery users.","abstract_html":"Many classic and contemporary face recognition algorithms work well on public data sets, but degrade sharply when they are used in a real recognition system. A major cause of this is the difficulty of simultaneously handling variations in illumination, image misalignment, and occlusion in the test image; while in some applications the gallery images can be well controlled, the test images are only loosely controlled. This thesis describes a conceptually simple but computationally intense face recognition system that achieves a high degree of robustness and stability to illumination variation, image misalignment, and partial occlusion, along with optimized parallel implementations. First, well registered training images taken under many illumination directions are captured using a novel projector-based acquisition system. The recognition system then uses tools from sparse representation to align a test face image to a set of frontal training images. To better handle severe occlusions, an extension to the algorithm is described that makes use of the knowledge that occluded pixels tend to be spatially correlated. Due to the use of multiple face images as features and the non-smooth nature of the optimization problems, these techniques have far greater computational requirements than techniques that extract low-dimensional features. Several custom L1 solvers are presented that achieve faster convergence on face data than general solvers. Optimized implementations for modern parallel computing architectures are investigated in order to build a system capable of performing highly accurate and robust recognition while remaining fast enough for use in access control systems. Optimized parallel implementations for contemporary CPU and GPU hardware are demonstrated to achieve near real-time face recognition for access control applications with hundreds of gallery users.","abstract_has_math":false,"creators":["Wagner, Andrew"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Ma, Yi","Huang, Thomas S.","Ahuja, Narendra","Patel, Sanjay J."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2012,"date_issued":"2012-02-06T20:09:17Z","date_published":"2012-02-06T20:09:17Z","updated_at":"2026-07-22T22:25:27Z","subjects":["Face Recognition","Sparse Representation","Parallel Programming","L1 Minimization"],"languages":["en"],"rights":["Copyright 2011 Andrew Wagner, Creative Commons"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/29657","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Ma, Yi","Huang, Thomas S.","Ahuja, Narendra","Patel, Sanjay J."]},{"key":"dc:creator","label":"Author","values":["Wagner, Andrew"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2012-02-06T20:09:17Z","2011-12"]},{"key":"dc:type","label":"Dc Type","values":["Dissertation / Thesis","text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engr"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"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":["Face Recognition","Sparse Representation","Parallel Programming","L1 Minimization"]}]},{"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 Andrew Wagner, Creative Commons"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/29657"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Many classic and contemporary face recognition algorithms work well on public data sets, but degrade sharply when they are used in a real recognition system. A major cause of this is the difficulty of simultaneously handling variations in illumination, image misalignment, and occlusion in the test image; while in some applications the gallery images can be well controlled, the test images are only loosely controlled. This thesis describes a conceptually simple but computationally intense face recognition system that achieves a high degree of robustness and stability to illumination variation, image misalignment, and partial occlusion, along with optimized parallel implementations. First, well registered training images taken under many illumination directions are captured using a novel projector-based acquisition system. The recognition system then uses tools from sparse representation to align a test face image to a set of frontal training images. To better handle severe occlusions, an extension to the algorithm is described that makes use of the knowledge that occluded pixels tend to be spatially correlated. Due to the use of multiple face images as features and the non-smooth nature of the optimization problems, these techniques have far greater computational requirements than techniques that extract low-dimensional features. Several custom L1 solvers are presented that achieve faster convergence on face data than general solvers. Optimized implementations for modern parallel computing architectures are investigated in order to build a system capable of performing highly accurate and robust recognition while remaining fast enough for use in access control systems. Optimized parallel implementations for contemporary CPU and GPU hardware are demonstrated to achieve near real-time face recognition for access control applications with hundreds of gallery users.","Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2011-12-01T15:41:04Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 2 Wagner_Andrew.zip: 182243316 bytes, checksum: 7b4f7eac3464cc18f52a541ad289c63b (MD5) Wagner_Andrew.pdf: 9697591 bytes, checksum: 59a3d4167921a07109c49c85b8ed9044 (MD5)","Made available in DSpace on 2012-02-06T20:09:17Z (GMT). No. of bitstreams: 3 Wagner_Andrew.pdf: 9697591 bytes, checksum: 59a3d4167921a07109c49c85b8ed9044 (MD5) license.txt: 4062 bytes, checksum: 64d86bb4e14e2ed59c135f65998046a8 (MD5) Wagner_Andrew.zip: 182243316 bytes, checksum: 7b4f7eac3464cc18f52a541ad289c63b (MD5)"]},{"key":"dc:title","label":"Title","values":["Fast and robust face recognition via parallelized L1 minimization"]}]}],"canonical_facts":{"dc:contributor":["Ma, Yi","Huang, Thomas S.","Ahuja, Narendra","Patel, Sanjay J."],"dc:creator":["Wagner, Andrew"],"dc:date":["2012-02-06T20:09:17Z","2011-12"],"dc:description":["Many classic and contemporary face recognition algorithms work well on public data sets, but degrade sharply when they are used in a real recognition system. A major cause of this is the difficulty of simultaneously handling variations in illumination, image misalignment, and occlusion in the test image; while in some applications the gallery images can be well controlled, the test images are only loosely controlled. This thesis describes a conceptually simple but computationally intense face recognition system that achieves a high degree of robustness and stability to illumination variation, image misalignment, and partial occlusion, along with optimized parallel implementations. First, well registered training images taken under many illumination directions are captured using a novel projector-based acquisition system. The recognition system then uses tools from sparse representation to align a test face image to a set of frontal training images. To better handle severe occlusions, an extension to the algorithm is described that makes use of the knowledge that occluded pixels tend to be spatially correlated. Due to the use of multiple face images as features and the non-smooth nature of the optimization problems, these techniques have far greater computational requirements than techniques that extract low-dimensional features. Several custom L1 solvers are presented that achieve faster convergence on face data than general solvers. Optimized implementations for modern parallel computing architectures are investigated in order to build a system capable of performing highly accurate and robust recognition while remaining fast enough for use in access control systems. Optimized parallel implementations for contemporary CPU and GPU hardware are demonstrated to achieve near real-time face recognition for access control applications with hundreds of gallery users.","Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2011-12-01T15:41:04Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 2 Wagner_Andrew.zip: 182243316 bytes, checksum: 7b4f7eac3464cc18f52a541ad289c63b (MD5) Wagner_Andrew.pdf: 9697591 bytes, checksum: 59a3d4167921a07109c49c85b8ed9044 (MD5)","Made available in DSpace on 2012-02-06T20:09:17Z (GMT). No. of bitstreams: 3 Wagner_Andrew.pdf: 9697591 bytes, checksum: 59a3d4167921a07109c49c85b8ed9044 (MD5) license.txt: 4062 bytes, checksum: 64d86bb4e14e2ed59c135f65998046a8 (MD5) Wagner_Andrew.zip: 182243316 bytes, checksum: 7b4f7eac3464cc18f52a541ad289c63b (MD5)"],"dc:identifier":["http://hdl.handle.net/2142/29657"],"dc:language":["en"],"dc:rights":["Copyright 2011 Andrew Wagner, Creative Commons"],"dc:subject":["Face Recognition","Sparse Representation","Parallel Programming","L1 Minimization"],"dc:title":["Fast and robust face recognition via parallelized L1 minimization"],"dc:type":["Dissertation / Thesis","text"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:27Z"}