Share Email Print
cover

Proceedings Paper

From face identification to emotion recognition
Author(s): Xin Chang; Władysław Skarbek
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This paper aims to explore the practicality of transfer learning regarding to the emotion recognition task. We present superior performance of the transfer learning from the face identification, compared with the solutions of train-from-scratch feed-forward deep neural networks and general transfer learning from object classifications. We illustrate that the better adaptation of source domain can help with the initialization of the network, providing more efficient learning from the target training samples. In such way even network with complex architecture can overcome over-fitting problems thus having better results than other solutions can do having the same amount of training data. We discuss the detailed training strategies to the get best performance of such transfer leaning using fine-tuning mechanisms on the classical VGG-16 architecture network based on the public accessible FER2013 emotion database.

Paper Details

Date Published: 6 November 2019
PDF: 9 pages
Proc. SPIE 11176, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2019, 111760K (6 November 2019); doi: 10.1117/12.2536735
Show Author Affiliations
Xin Chang, Warsaw Univ. of Technology (Poland)
Władysław Skarbek, Warsaw Univ. of Technology (Poland)


Published in SPIE Proceedings Vol. 11176:
Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2019
Ryszard S. Romaniuk; Maciej Linczuk, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray