Automatic Infant Face Verification via Convolutional Neural Networks

Simple item page
dc.contributor.authorWöhler, Leslieen_US
dc.contributor.authorZhang, Hangjianen_US
dc.contributor.authorAlbuquerque, Georgiaen_US
dc.contributor.authorMagnor, Marcusen_US
dc.contributor.editorBeck, Fabian and Dachsbacher, Carsten and Sadlo, Filipen_US
dc.date.accessioned2018-10-18T09:33:36Z
dc.date.available2018-10-18T09:33:36Z
dc.date.issued2018
dc.description.abstractIn this paper, we investigate how convolutional neural networks (CNN) can learn to solve the verification task for faces of young children. One of the main issues of automatic face verification approaches is how to deal with facial changes resulting from aging. Since the facial shape and features change drastically during early childhood, the recognition of children can be challenging even for human observers. Therefore, we design CNNs that take two infant photographs as input and verify whether they belong to the same child. To specifically train our CNNs to recognize young children, we collect a new infant face dataset including 4,528 face images of 42 subjects in the age range of 0 to 6 years. Our results show an accuracy of up to 85 percent for face verification using our dataset with no overlapping subjects between the training and test data, and 72 percent in the FG-NET dataset for the age range from 0 to 4 years.en_US
dc.description.sectionheadersImage Analysis and Visualization
dc.description.seriesinformationVision, Modeling and Visualization
dc.identifier.doi10.2312/vmv.20181253
dc.identifier.isbn978-3-03868-072-7
dc.identifier.pages55-62
dc.identifier.urihttps://doi.org/10.2312/vmv.20181253
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/vmv20181253
dc.publisherThe Eurographics Associationen_US
dc.subjectI.5.4 [Pattern Recognition]
dc.subjectApplication
dc.subjectComputer Vision
dc.titleAutomatic Infant Face Verification via Convolutional Neural Networksen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
055-062.pdf
Size:
5.8 MB
Format:
Adobe Portable Document Format
Download
Collections
VMV18