Exploitation of Nasolabial Folds for Happy Smile Recognition on an Image Using ANN

DOI

10.2991/assehr.k.210305.047How to use a DOI?

Keywords

Nasolabial folds, happy smile recognition, backpropagation

Abstract

Nasolabial folds are the wrinkle around the mouth that can be used to mark facial expressions. In this study, nasolabial folds were used to identify happy smile expressions on facial images. The recognition consists of 2 main stages. The first stage for facial area detection is carried out using the viola-jones algorithm, then the second stage for identification of happy smile expressions is performed using artificial neural network (ANN), i.e. the backpropagation algorithm. The processing of feature extraction exploits the calculation of the area of the nasolabial folds in the segmented image. The data of feature extraction is then used as input for the process of training and testing of the backpropagation neural network. The accuracy rate of the system for identifying happy smile expressions on 150 facial images is 92% for training dataset and 82% for testing dataset.

Copyright

© 2021, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Sri Andayani
AU  - Nur H. Waryanto
AU  - Bambang S. H. Marwoto
AU  - Monica M. Hapsari
PY  - 2021
DA  - 2021/03/08
TI  - Exploitation of Nasolabial Folds for Happy Smile Recognition on an Image Using ANN
BT  - Proceedings of the 7th International Conference on Research, Implementation, and Education of Mathematics and Sciences (ICRIEMS 2020)
PB  - Atlantis Press
SP  - 329
EP  - 333
SN  - 2352-5398
UR  - https://doi.org/10.2991/assehr.k.210305.047
DO  - 10.2991/assehr.k.210305.047
ID  - Andayani2021
ER  -