A similarity-based neural network for facial expression analysis

Authors:
Kenji Suzuki;Hiroshi Yamada;Shuji Hashimoto
Affiliations:
Department of Intelligent Interaction Technologies, University of Tsukuba, Japan;Department of Psychology, Nihon University, Japan;Department of Applied Physics, Waseda University, Japan
Venue:
Pattern Recognition Letters
Year:
2007

Citing 5
Cited 1

A hybrid approach of NN and HMM for facial emotion classification

Pattern Recognition Letters
Comparison Between Geometry-Based and Gabor-Wavelets-Based Facial Expression Recognition Using Multi-Layer Perceptron

FG '98 Proceedings of the 3rd. International Conference on Face & Gesture Recognition
Learning a similarity-based distance measure for image database organization from human partitionings of an image set

WACV '98 Proceedings of the 4th IEEE Workshop on Applications of Computer Vision (WACV'98)
Emotional facial expression model building

Pattern Recognition Letters
A Nonlinear Mapping for Data Structure Analysis

IEEE Transactions on Computers

Example-based video remixing support system

MM '11 Proceedings of the 19th ACM international conference on Multimedia

Quantified Score

Hi-index	0.10

Visualization

Abstract

In this paper, we introduce a novel model for the measuring of human subjective evaluation by using Relevance Learning based on a similarity-based multilayer perceptron. This work aims to achieve a multidimensional perceptual scaling that associates the physical features of a face with its semantic vector in a low-dimensional space. Unlike the conventional multilayer perceptron that learns from a set of an input feature vector and the desired output, the proposed network can obtain a nonlinear mapping between the input feature vectors and the outputs from a pair of objects and their desired relevance (distance). We conducted a facial expression analysis with both a psychological model of line-drawing image of facial expression and a real image set. Regarding the construction of semantic space, the proposed approach not only shows a good performance as compared with the conventional statistical method but is also able to project new data that are not used during the training phase. We will show some experimental results and discuss the obtained mapping function.