Deep neural network architecture: application for facial expression recognition

Authors

  • MOISES GARCIA VILLANUEVA UNIVERSIDAD MICHOACANA DE SAN NICOLAS DE HIDALGO
  • Salvador Ramírez Zavala UMSNH

Keywords:

Deep Learning, CNN architecture, facial expression recognition, visual classification of sentiment

Abstract

There are great challenges to build a model or architecture in Deep Learning and integrate it into a real-time application. From the collection of large quality data sets (thousands or millions of objects), to have great computing potential for architectural learning processes and finally achieve efficient architectures. The design of a deep neural network requires expertise, human experience and practical work.
This work presents a deep neural network architecture to classify two feelings of facial expression (happy and sad); A set of data is also created that present great changes in: image environments, facial expression, pose, age, ethnicity and others. The evidence presented shows a competitive architecture and indicates an accuracy greater than 90\% with noisy data. Finally, the implementation of a real-time application for facial expression recognition is shown.

Downloads

Download data is not yet available.

Author Biography

Salvador Ramírez Zavala, UMSNH

Profesor e Investigados adscrito a la Facultad de Ingenierı́a Eléctrica de la Universidad Michoacana de San Nicolás de Hidalgo.

Published

2020-05-15

How to Cite

GARCIA VILLANUEVA, M., & Ramírez Zavala, S. (2020). Deep neural network architecture: application for facial expression recognition. IEEE Latin America Transactions, 18(7), 1311–1319. Retrieved from https://latamt.ieeer9.org/index.php/transactions/article/view/2526