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.
|Title of host publication||Proceedings of the International Conference on Biomedical Innovations and Applications, BIA 2020|
|Editors||Valentina Markova, Todor Ganchev|
|Publisher||Institute of Electrical and Electronics Engineers|
|Number of pages||5|
|Publication status||Published - 24 Sep 2020|
|Event||2020 International Conference on Biomedical Innovations and Applications, BIA 2020 - Varna, Bulgaria|
Duration: 24 Sep 2020 → 27 Sep 2020
|Conference||2020 International Conference on Biomedical Innovations and Applications, BIA 2020|
|Period||24/09/20 → 27/09/20|
Bibliographical notePublisher Copyright:
© 2020 IEEE.
Copyright 2020 Elsevier B.V., All rights reserved.
- computer vision
- deep learning
- object counting