Hair counting with deep learning

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

Samenvatting

We present a set of deep learning models aimed at solving the hair counting problem in human skin images. All the models are end-to-end, providing a mapping from the input image to a single scalar corresponding to the number of hair. The list of models corresponds to the most common deep learning architectures that worked over-time in various applications, where some of the networks were adapted to output the hair count. Results show that autoencoder architectures with skip connections work best for such end-to-end counting task, hinting at increased performance when multi-task learning is used. With the results presented, we speculate on the possibility to remove human annotator from the tedious task of manual counting of skin hair.

Originele taal-2Engels
TitelProceedings of the International Conference on Biomedical Innovations and Applications, BIA 2020
RedacteurenValentina Markova, Todor Ganchev
UitgeverijInstitute of Electrical and Electronics Engineers
Pagina's5-9
Aantal pagina's5
ISBN van elektronische versie9781728170732
DOI's
StatusGepubliceerd - 24 sep 2020
Evenement2020 International Conference on Biomedical Innovations and Applications, BIA 2020 - Varna, Bulgarije
Duur: 24 sep 202027 sep 2020

Congres

Congres2020 International Conference on Biomedical Innovations and Applications, BIA 2020
Land/RegioBulgarije
StadVarna
Periode24/09/2027/09/20

Bibliografische nota

Publisher Copyright:
© 2020 IEEE.

Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.

Vingerafdruk

Duik in de onderzoeksthema's van 'Hair counting with deep learning'. Samen vormen ze een unieke vingerafdruk.

Citeer dit