Finding Useful Features for Facial Expression Recognition and Intensity Estimation by Neural Network

Facial expression intensity has been proposed to digitize the degree of facial expressions in order to retrieve impressive scenes from lifelog videos. The intensity is calculated based on the correlation of facial features compared to each facial expression. However, the correlation is not determine...

Full description

Saved in:
Bibliographic Details
Published inInternational journal of software innovation Vol. 8; no. 2; pp. 68 - 84
Main Authors Hochin, Teruhisa, Nomiya, Hiroki, Imamura, Naoki
Format Journal Article
LanguageEnglish
Published Mount Pleasant IGI Global 01.04.2020
Subjects
Face recognition
Mathematical analysis
Neural networks
Online AccessGet full text

Cover

More Information
Summary:Facial expression intensity has been proposed to digitize the degree of facial expressions in order to retrieve impressive scenes from lifelog videos. The intensity is calculated based on the correlation of facial features compared to each facial expression. However, the correlation is not determined objectively. It should be determined statistically based on the contribution score of the facial features necessary for expression recognition. Therefore, the proposed method recognizes facial expressions by using a neural network and calculates the contribution score of input toward the output. First, the authors improve some facial features. After that, they verify the score correctly by comparing the accuracy transitions depending on reducing useful and useless features and process the score statistically. As a result, they extract useful facial features from the neural network.
ISSN:2166-7160
2166-7179
DOI:10.4018/IJSI.2020040105