The impact of pre-processing algorithms in facial expression recognition

4 January 2021 The impact of pre-processing algorithms in facial expression recognition

Daniel Canedo, António J. R. Neves

Proceedings Volume 11605, Thirteenth International Conference on Machine Vision; 116051Q (2021) https://doi.org/10.1117/12.2587865
Event: Thirteenth International Conference on Machine Vision, 2020, Rome, Italy

Abstract

This paper proposes several pre-processing algorithms to improve facial expression recognition based on Convolutional Neural Networks (CNNs) models. The proposed CNN model was trained on the Extended Cohn-Kanade dataset (CK+) after applying the pre-processing stages and achieved competitive results (93.90% recognition accuracy) despite its simple and light architecture. Using this CNN model, a study on the impact of each pre-processing algorithm when extracting facial features is presented. In the end, it is understood that pre-processing algorithms help CNNs to extract the most relevant features for each facial expression more effectively, reducing the overfitting and increasing the recognition accuracy. Attention maps before and after the pre-processing step are shown in order to visualize its impact when the proposed CNN model makes a prediction.

Citation Download Citation

Daniel Canedo and António J. R. Neves "The impact of pre-processing algorithms in facial expression recognition", Proc. SPIE 11605, Thirteenth International Conference on Machine Vision, 116051Q (4 January 2021); https://doi.org/10.1117/12.2587865

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available