Universidade Federal do Rio de Janeiro COPPE

Instituto Alberto Luiz Coimbra de Pós-Graduação e Pesquisa de Engenharia

Instituto de Matemática

 
Visualizar Meses
Visualizar Meses
Visualizar Flat
Visualizar Flat
Visualizar Semanas
Visualizar Semanas
Visualizar Dias
Visualizar Dias
Categorias
Categorias
Procurar
Procurar

Evento: 'Palestra: Detecting Objects of Variable Shape Structure in Cluttered Images'

Eventos PESC (Palestras, Seminários, etc.)
Palestras, Seminários, etc. do PESC/COPPE/UFRJ.
Data: Thursday, October 18, 2007 At 11:00
Duração: 2 Horas
Contato - Info:
Email:

O Prof. Vassilis Athitsos da Universidade do Texas em Arlington estará visitando a COPPE/UFRJ nesta quinta-feira, dia 18/10. Ele veio ao Rio apresentar um trabalho na IEEE ICCV, que acontece esta semana no Sofitel (detalhes em http://iccv2007.rutgers.edu).

Como parte de sua visita, ele irá proferir uma palestra às 11h na sala H-324B (ver detalhes abaixo). Todos estão convidados a participar.

O Prof. Athitsos tem interesse em conversar sobre trabalhos e tópicos de pesquisa relacionados à sua área de atuação. Em particular, ele gostaria de conversar com alunos que tenham perspectivas de realizar doutorado ou pós-doutorado no exterior. Caso alguém esteja interessado em se reunir com ele (individualmente ou em pequenos grupos), basta enviar uma mensagem ao Daniel R. Figueiredo (daniel@cos.ufrj.br) para agendar um horário na quinta à tarde.


------------------------------------------

TITLE:
Detecting Objects of Variable Shape Structure in Cluttered Images

ABSTRACT:
An important problem in computer vision is detecting objects in the presence of noise, clutter, and occlusions, and registering such shapes with a model. This presentation describes Hidden State Shape Models (HSSMs), a family of models explicitly designed for a large category of object classes where other existing detection methods are not applicable: object classes that exhibit variable shape structure. The term "variable shape structure" is used to characterize object classes in which some shape parts can be repeated an arbitrary number of times, some parts can be optional, and some parts can have several alternative appearances. Examples of such objects include blood vessels in the retina, dendrites, and roadways/waterways in aerial images. HSSMs are a generalization of Hidden Markov Models (HMMs); whereas HMMs can be used to optimally match a sequence of states to a sequence of observations, HSSMs are designed for the more general case where the observations are not ordered. Handling unordered observations allows HSSMs to be optimally matched with features extracted from a cluttered image, in polynomial time. In experiments with real images, HSSMs can detect objects of variable shape structure with high accuracy, even in the presence of large amounts of noise and clutter.

BIO:
Vassilis Athitsos received the BS degree in mathematics from the University of Chicago in 1995, the MS degree in computer science from the University of Chicago in 1997, and the PhD degree in computer science from Boston University in 2006. In 2005-2006 he worked as a researcher at Siemens Corporate Research, developing methods for database-guided medical image analysis. In 2006-2007 he was a postdoctoral research associate at the Computer Science department at Boston University. Since August 2007 he is an assistant professor at the Computer Science and Engineering department at the University of Texas at Arlington. His research interests include computer vision, machine learning, and data mining. His recent work has focused on efficient similarity-based retrieval, gesture recognition, shape modeling and detection, and medical image analysis.


Procurar no Calendário

Powered by ExtCalendar 2

© 2017 PESC/COPPE - Programa de Engenharia de Sistemas e Computação

Cidade Universitária, Centro de Tecnologia, Bloco H, Sala 319
Caixa Postal: 68511 CEP: 21941-972 Fones: +55 21 3938-8672 / +55 21 3938-8673 Fax: +55 21 3938-8676
Rio de Janeiro - RJ - Brasil
Horário de atendimento da Secretaria: 2a. a 6a. de 7:00 às 16:00 horas (exceto feriados escolares)