Facial Makeup Detection using the CMYK Color Model and Convolutional Neural Networks

Página do item simplificado
dc.contributor.authorBertacchi M.G.
dc.contributor.authorSilveira I.F.
dc.date.accessioned2024-03-12T23:52:05Z
dc.date.available2024-03-12T23:52:05Z
dc.date.issued2019
dc.description.abstract© 2019 IEEE.This work presents a facial makeup detection technique using CMYK and Neural Networks. The main goal is to detect facial makeup using the CMYK color model, and analyzing its results by comparing it to the HSV color model, which is widely used in the literature. In the detection process, each image was separated into regions of interest (the eyes and the whole face). Five image databases were chosen, all varying in lighting and environment conditions. In HSV, 91% of accuracy was achieved on the eye region and 92% on the face. In CMYK, the results obtained had 97% of accuracy on the eye region and 95% on the face. Therefore, based on the results achieved, the CMYK color model, even though it is mainly used in Printing, deserves attention in the area of Computer Vision, involving Makeup Detection.
dc.description.firstpage54
dc.description.lastpage60
dc.identifier.doi10.1109/WVC.2019.8876943
dc.identifier.urihttps://dspace.mackenzie.br/handle/10899/35210
dc.relation.ispartofProceedings - 15th Workshop of Computer Vision, WVC 2019
dc.rightsAcesso Restrito
dc.subject.otherlanguageCMYK
dc.subject.otherlanguagecomputer vision
dc.subject.otherlanguageHSV
dc.subject.otherlanguagemakeup detection
dc.subject.otherlanguageneural networks
dc.titleFacial Makeup Detection using the CMYK Color Model and Convolutional Neural Networks
dc.typeArtigo de evento
local.scopus.citations2
local.scopus.eid2-s2.0-85074885921
local.scopus.subjectCMYK
local.scopus.subjectColor modeling
local.scopus.subjectConvolutional neural network
local.scopus.subjectDetection process
local.scopus.subjectEnvironment conditions
local.scopus.subjectHSV color models
local.scopus.subjectImage database
local.scopus.subjectRegions of interest
local.scopus.updated2024-05-01
local.scopus.urlhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85074885921&origin=inward
Arquivos
Coleções
Artigo de evento