Generating photorealistic images of people's eyes with strabismus using Deep Convolutional Generative Adversarial Networks
Tipo
Artigo de evento
Data de publicação
2020
Periódico
2nd International Conference on Electrical, Communication and Computer Engineering, ICECCE 2020
Citações (Scopus)
1
Autores
Santos J.
Frango I.
Frango I.
Orientador
Título da Revista
ISSN da Revista
Título de Volume
Membros da banca
Programa
Resumo
© 2020 IEEE.Strabismus is a medical condition that affects about 4% of the world population. In severe cases, strabismus can lead to blindness. Besides affecting the vision, the aesthetic appeal of strabismus can generate sufficient public embarrassment to influence the patient's entire academic, personal and professional development. In most cases the condition can be treated. Studies relating computing and strabismus are still few, we understand that the main reason for this scarcity is the difficulty in acquiring dataset on strabismus. Motivated by this aspect, we propose in this research a generative model for the computational creation of synthetic images of the eye region of people with strabismus using Deep Convolutional Generative Adversarial Networks (DCGAN).
Descrição
Palavras-chave
Assuntos Scopus
Adversarial networks , Aesthetic appeals , Generative model , Medical conditions , Photorealistic images , Professional development , Synthetic images , World population