Braid Hairstyle Recognition based on CNNs

Chao Sun, Won-Sook Lee

2017

Abstract

In this paper, we present a novel braid hairstyle recognition system based on Convolutional Neural Networks (CNNs). We first build a hairstyle patch dataset that is composed of braid hairstyle patches and non-braid hairstyle patches (straight hairstyle patches, curly hairstyle patches, and kinky hairstyle patches). Then we train our hairstyle recognition system via transfer learning on a pre-trained CNN model in order to extract the features of different hairstyles. Our hairstyle recognition CNN model achieves the accuracy of 92.7% on image patch dataset. Then the CNN model is used to perform braid hairstyle detection and recognition in full-hair images. The experiment results shows that the patch-level trained CNN model can successfully detect and recognize braid hairstyle in image-level.

Paper Citation

in Harvard Style

Sun C. and Lee W. (2017). Braid Hairstyle Recognition based on CNNs . In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2017) ISBN 978-989-758-225-7, pages 548-555. DOI: 10.5220/0006169805480555

in Bibtex Style

@conference{visapp17,
author={Chao Sun and Won-Sook Lee},
title={Braid Hairstyle Recognition based on CNNs},
booktitle={Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2017)},
year={2017},
pages={548-555},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006169805480555},
isbn={978-989-758-225-7},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2017)
TI - Braid Hairstyle Recognition based on CNNs
SN - 978-989-758-225-7
AU - Sun C.
AU - Lee W.
PY - 2017
SP - 548
EP - 555
DO - 10.5220/0006169805480555