Banca de QUALIFICAÇÃO: MIGUEL BOZER DA SILVA

Uma banca de QUALIFICAÇÃO de MESTRADO foi cadastrada pelo programa.
DISCENTE : MIGUEL BOZER DA SILVA
DATA : 17/08/2020
HORA: 09:30
LOCAL: Por participação remota
TÍTULO:

Deep Convolutional Networks For Super-Resolution Image Reconstruction

PÁGINAS: 65
GRANDE ÁREA: Engenharias
ÁREA: Engenharia Elétrica
RESUMO:

The need to obtain high-resolution images exists in several areas, such as medicine, astronomy, security, and monitoring. However, not even cameras have the desired high resolution or an external factor can reduce the quality of an image that you want to study. Thus, several studies have emerged in the area of Super Resolution of images, in order to obtain high-resolution images from low-resolution images using software for this task. The most used methods today are based on only a single input image (single image super-resolution (SISR)) and, using deep learning techniques, it is possible to train a network with the objective of obtaining resolution images with characteristics similar to the training set. The proposed method for this work intends to find a network structure neural convolution that is able to take advantage of the results of older methods that do not use convolutional networks to solve this problem. Thus, the objective is to include the results of these methods in the network training phase, in order to verify if this information extra can improve some metrics in the quality of the recovered image, or get some algorithm that has a low x time of execution.

MEMBROS DA BANCA:
Presidente - Interno ao Programa - 1761107 - RICARDO SUYAMA
Membro Titular - Examinador(a) Interno ao Programa - 2334927 - ANDRE KAZUO TAKAHATA
Membro Titular - Examinador(a) Interno ao Programa - 1761105 - MURILO BELLEZONI LOIOLA
Membro Titular - Examinador(a) Externo ao Programa - 1545367 - CELSO SETSUO KURASHIMA
Membro Suplente - Examinador(a) Externo ao Programa - 2356637 - KENJI NOSE FILHO