PPGINF
PÓS-GRADUAÇÃO EM ENGENHARIA DA INFORMAÇÃO
FUNDAÇÃO UNIVERSIDADE FEDERAL DO ABC
Teléfono/Ramal: No informado
E-mail:
ppg.informacao@ufabc.edu.br
http://propg.ufabc.edu.br/ppginfo
Banca de QUALIFICAÇÃO: EDILTON TORRES DE ANDRADE
Uma banca de QUALIFICAÇÃO de MESTRADO foi cadastrada pelo programa.DISCENTE : EDILTON TORRES DE ANDRADE
DATA : 08/08/2019
HORA: 14:00
LOCAL: sala 303, 3º andar, Bloco B, Campus SA da Fundação Universidade Federal do ABC, localizada na Avenida dos Estados, 5001, Santa Terezinha, Santo André, SP
TÍTULO:
Real Objects Recognition Using Synthetic Images for Convolutional Neural Netorks Training
PÁGINAS: 30
GRANDE ÁREA: Engenharias
ÁREA: Engenharia Elétrica
SUBÁREA: Telecomunicações
RESUMO:
The accuracy of Image Recognition using Convolutional Neural Networks is proportional to the number of images used in the network training, so obtaining multiple samples of the same object is a costly task for the application of these networks.
In this work, we evaluated the use of synthetic images generated from 3D Models for training the network.
For that, we used models of dogs of different breeds were manipulating a three-dimensional environment obtained images in different environments and camera positions.
The simulations carried out showed that the synthetic images can be used in an effective way to recognize real objects being an alternative to obtain samples for the training of the Convolutional Neural Networks.
In this work, we evaluated the use of synthetic images generated from 3D Models for training the network.
For that, we used models of dogs of different breeds were manipulating a three-dimensional environment obtained images in different environments and camera positions.
The simulations carried out showed that the synthetic images can be used in an effective way to recognize real objects being an alternative to obtain samples for the training of the Convolutional Neural Networks.
MEMBROS DA BANCA:
Presidente - Interno ao Programa - 2334927 - ANDRE KAZUO TAKAHATA
Membro Titular - Examinador(a) Interno ao Programa - 1964056 - JOAO HENRIQUE RANHEL RIBEIRO
Membro Titular - Examinador(a) Externo ao Programa - 1671396 - IRINEU ANTUNES JUNIOR
Membro Suplente - Examinador(a) Interno ao Programa - 1761107 - RICARDO SUYAMA
Notícia cadastrada em: 07/07/2019 07:26
SIGAA | UFABC - Núcleo de Tecnologia da Informação - ||||| | Copyright © 2006-2024 - UFRN - sigaa-1.ufabc.int.br.sigaa-1-prod