2026-09-22T16:03:58Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/44478 2023-07-11 col_2142_5131 col_2142_8888 com_2142_5130 com_2142_8887 com_2142_234

Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2013-04-10T20:41:56Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 1 Li_Zhen.pdf: 10718613 bytes, checksum: 33d3a5f6a45d0870d945906fb9961656 (MD5) Made available in DSpace on 2013-05-24T22:17:35Z (GMT). No. of bitstreams: 2 Zhen_Li.pdf: 10718649 bytes, checksum: 022e27c2dc7a64739935895a80d0b04b (MD5) license.txt: 4056 bytes, checksum: f3e6def62ec42029b968a6b7604928e9 (MD5) Restriction data tranferred 2014-07-01T11:36:18-05:00 Original Data Group with Access UIUC Users [automated] Release Date: 2015-05-24 17:18:31 UTC Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system Item marked as restricted to the 'UIUC Users [automated]' Group (id=2) by Seth Robbins (srobbins@illinois.edu) on 2013-05-24T22:19:19Z Item is restricted until 2015-05-24T22:18:31Z U of I Only Restriction Lifted for Item 44451 on 2015-05-24T10:00:54Z. http://hdl.handle.net/2142/44478 en Copyright 2013 Zhen Li Person Verification Efficient Person Search Generative and discriminative models for person verification and efficient search text Huang, Thomas S. Huang, Thomas S. Hasegawa-Johnson, Mark A. Liang, Feng Liang, Zhi-Pei Li, Zhen 2013-05-24T22:17:35Z 2013-05-24T22:17:35Z 2015-05-24T10:00:54Z 2013-05 2013-05-24T22:17:35Z 2013-05 This dissertation studies the person verification problem in modern surveillance and video retrieval systems. The problem is to identify whether a pair of face or human body images is about the same person, even if the person is not seen before. Traditional methods either model the intrapersonal and extrapersonal variations with probabilistic distributions, or look for a distance (or similarity) measure between images (e.g., by metric learning algorithms), and make decisions based on a fixed threshold. We show that the resulting decisions, depending merely on pairwise image differences, are nevertheless insufficient and sub-optimal for the verification problem. In this dissertation, we study both generative and discriminative models for person verification. Both methods consider a joint model of two images in a pair, and provide a decision function of second-order form that generalizes from previous approaches. We also generalize our model to a multi-setting scenario, where environment mismatch, a major challenge in cross-setting person verification, is handled. We evaluate our algorithms on face verification and human body verification problems on a number benchmark datasets, such as Multi-PIE, LFW, CIGIT-AIS, VIPer, VIPeR, and CAVIAR4REID. Our methods outperform not only the classical Bayesian Face Recognition approach, metric learning algorithms (LMNN, ITML, etc.), but also the state-of-the-art in the computer vision community. This dissertation also considers efficient person search, a potential application of person verification in surveillance systems. To this end, we propose a general learning-to-search framework for efficient similarity search in high dimensions. Experimental results show that our approach significantly outperforms the state-of-the-art learning-to-hash methods (such as spectral hashing), as well as state-of-the-art high-dimensional search algorithms (such as LSH and k-means trees). Electrical & Computer Eng 1933 Electrical & Computer Engr 1200 University of Illinois at Urbana-Champaign Dissertation Ph.D. PHD:Electr & Computer Eng-UIUC 10KS1200PHD