1 resultado para Biggs, Leonard Vivian - Pictorial works
em Massachusetts Institute of Technology
Filtro por publicador
- Repository Napier (1)
- AMS Tesi di Dottorato - Alm@DL - Università di Bologna (2)
- AMS Tesi di Laurea - Alm@DL - Università di Bologna (1)
- Andina Digital - Repositorio UASB-Digital - Universidade Andina Simón Bolívar (1)
- Aquatic Commons (4)
- ArchiMeD - Elektronische Publikationen der Universität Mainz - Alemanha (1)
- Archive of European Integration (37)
- Archivo Digital para la Docencia y la Investigación - Repositorio Institucional de la Universidad del País Vasco (2)
- Biblioteca Digital | Sistema Integrado de Documentación | UNCuyo - UNCUYO. UNIVERSIDAD NACIONAL DE CUYO. (2)
- Biblioteca Digital da Produção Intelectual da Universidade de São Paulo (1)
- Biblioteca Digital de Teses e Dissertações Eletrônicas da UERJ (9)
- Biodiversity Heritage Library, United States (111)
- Blue Tiger Commons - Lincoln University - USA (1)
- BORIS: Bern Open Repository and Information System - Berna - Suiça (22)
- Boston University Digital Common (3)
- Brock University, Canada (38)
- Bucknell University Digital Commons - Pensilvania - USA (4)
- Cambridge University Engineering Department Publications Database (9)
- CentAUR: Central Archive University of Reading - UK (36)
- Center for Jewish History Digital Collections (1)
- Central European University - Research Support Scheme (1)
- Chinese Academy of Sciences Institutional Repositories Grid Portal (3)
- Cochin University of Science & Technology (CUSAT), India (16)
- Comissão Econômica para a América Latina e o Caribe (CEPAL) (5)
- CORA - Cork Open Research Archive - University College Cork - Ireland (5)
- CUNY Academic Works (1)
- Dalarna University College Electronic Archive (2)
- Deakin Research Online - Australia (114)
- Department of Computer Science E-Repository - King's College London, Strand, London (1)
- Digital Archives@Colby (6)
- Digital Commons - Michigan Tech (2)
- Digital Commons @ DU | University of Denver Research (11)
- Digital Commons @ Winthrop University (1)
- Digital Commons at Florida International University (1)
- Digital Peer Publishing (6)
- DigitalCommons@The Texas Medical Center (1)
- DigitalCommons@University of Nebraska - Lincoln (7)
- Digitale Sammlungen - Goethe-Universität Frankfurt am Main (14)
- DRUM (Digital Repository at the University of Maryland) (23)
- Gallica, Bibliotheque Numerique - Bibliothèque nationale de France (French National Library) (BnF), France (1)
- Greenwich Academic Literature Archive - UK (2)
- Harvard University (16)
- Helda - Digital Repository of University of Helsinki (3)
- Indian Institute of Science - Bangalore - Índia (5)
- Massachusetts Institute of Technology (1)
- Ministerio de Cultura, Spain (9)
- National Center for Biotechnology Information - NCBI (2)
- Portal de Revistas Científicas Complutenses - Espanha (1)
- Publishing Network for Geoscientific & Environmental Data (4)
- QUB Research Portal - Research Directory and Institutional Repository for Queen's University Belfast (55)
- Queensland University of Technology - ePrints Archive (60)
- Repositório digital da Fundação Getúlio Vargas - FGV (3)
- Repositório Institucional UNESP - Universidade Estadual Paulista "Julio de Mesquita Filho" (14)
- School of Medicine, Washington University, United States (1)
- South Carolina State Documents Depository (5)
- The Scholarly Commons | School of Hotel Administration; Cornell University Research (1)
- Universidad Autónoma de Nuevo León, Mexico (11)
- Universidad del Rosario, Colombia (3)
- Universidad Politécnica de Madrid (7)
- Universidade de Lisboa - Repositório Aberto (3)
- Université de Lausanne, Switzerland (1)
- Université de Montréal, Canada (9)
- University of Michigan (268)
- University of Washington (2)
- USA Library of Congress (4)
- WestminsterResearch - UK (2)
Resumo:
This thesis presents a statistical framework for object recognition. The framework is motivated by the pictorial structure models introduced by Fischler and Elschlager nearly 30 years ago. The basic idea is to model an object by a collection of parts arranged in a deformable configuration. The appearance of each part is modeled separately, and the deformable configuration is represented by spring-like connections between pairs of parts. These models allow for qualitative descriptions of visual appearance, and are suitable for generic recognition problems. The problem of detecting an object in an image and the problem of learning an object model using training examples are naturally formulated under a statistical approach. We present efficient algorithms to solve these problems in our framework. We demonstrate our techniques by training models to represent faces and human bodies. The models are then used to locate the corresponding objects in novel images.