Automatic Motion Feature Extraction with Application to Quantitative Assessment of Facial Paralysis

Author

Shu He ; Soraghan, John J. ; O´Reilly, B.F.

Author_Institution

Strathclyde Univ., Glasgow, UK

Volume

1

fYear

2007

fDate

15-20 April 2007

Abstract

This paper presents a robust, objective, automated and quantitative assessment system for facial paralysis using artificial intelligence analysis of biomedical video data. Facial feature localization and prescribed facial movements detection are discussed. Optical flow is used to obtain the motion features in the relevant facial regions. Radial basis function (RBF) neural network is applied to provide quantitative evaluation of facial paralysis based on the House-Brackmann scale. The results from 197 videos of 87 subjects are encouraging with a mean squared error (MSE) of 0.013 (training) and 0.0169 (testing).

Keywords

artificial intelligence; feature extraction; image motion analysis; mean square error methods; medical image processing; radial basis function networks; House-Brackmann scale; MSE; RBF neural network; artificial intelligence analysis; automatic motion feature extraction; biomedical video data; facial feature localization; facial movements detection; facial paralysis; mean squared error; optical flow; quantitative assessment; radial basis function neural network; Artificial intelligence; Artificial neural networks; Biomedical optical imaging; Face detection; Facial features; Feature extraction; Image motion analysis; Optical computing; Robustness; Testing; Facial Paralysis Measurement; House-Brackmann Scale; Optical Flow; RBF Neural Network;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing, 2007. ICASSP 2007. IEEE International Conference on

Conference_Location

Honolulu, HI

ISSN

1520-6149

Print_ISBN

1-4244-0727-3

Type

conf

DOI

10.1109/ICASSP.2007.366711

Filename

4217111