UFS › SIGAA - Sistema Integrado de Gestão de Atividades Acadêmicas São Cristóvão, 22 de Outubro de 2020


Notícias

Banca de DEFESA: ANGELO GARANGAU MENEZES
29/11/2019 12:53


Uma banca de DEFESA de MESTRADO foi cadastrada pelo programa.
DISCENTE: ANGELO GARANGAU MENEZES
DATA: 12/12/2019
HORA: 15:00
LOCAL: Sala de Apresentação de Seminários do Departamento de Computação DCOMP/UFS
TÍTULO: Analysis and evaluation of deep learning based super-resolution algorithms to improve performance in low-resolution face recognition
PALAVRAS-CHAVES: Low-Resolution Face Recognition; Super-Resolution; Deep Learning; Convolutional Neural Networks.
PÁGINAS: 62
GRANDE ÁREA: Ciências Exatas e da Terra
ÁREA: Ciência da Computação
SUBÁREA: Matemática da Computação
ESPECIALIDADE: Modelos Analíticos e de Simulação
RESUMO:

Surveillance scenarios are prone to several problems since they usually involve low-resolution footage, and there is no control of how far the subjects may be from the camera in the first place. This situation is suitable for the application of upsampling (super-resolution) algorithms since they may be able to recover the discriminant properties of the subjects involved.
While general super-resolution approaches were proposed to enhance image quality for human-level perception, biometrics super-resolution methods seek the best "computer perception" version of the image since their focus is on improving automatic recognition performance. Convolutional neural networks and deep learning algorithms, in general, have been applied to computer vision tasks and are now state-of-the-art for several sub-domains, including image classification, restoration, and super-resolution. However, no work has evaluated the effects that the latest proposed super-resolution methods may have upon the accuracy and face verification performance in low-resolution ``in-the-wild'' data.
This project aimed at evaluating and adapting different deep neural network architectures for the task of face super-resolution driven by face recognition performance in real-world low-resolution images. The experimental results in a real-world surveillance and attendance datasets showed that general super-resolution architectures might enhance face verification performance of deep neural networks trained on high-resolution faces. Also, since neural networks are function approximators and can be trained based on specific objective functions, the use of a customized loss function optimized for feature extraction presented promising results for recovering discriminant features in low-resolution face images.


MEMBROS DA BANCA:
Presidente - 1683105 - CARLOS ALBERTO ESTOMBELO MONTESCO
Interno - 1979373 - DANIEL OLIVEIRA DANTAS
Externo ao Programa - 2562054 - CARLOS ALBERTO VILLACORTA CARDOSO

SIGAA | Superintendência de Tecnologia da Informação/UFS | Telefonista/UFS (79)3194-6600 | Copyright © 2009-2020 - UFRN v3.5.16 -r12692-c69972fb69