True smile recognition system using neural networks

Abstract

Recently, research about man-machine interface has increased. Therefore application to facial expressions is expected from the development of the man-machine interface. An eigenface method is popular in these research fields by using the principal component analysis (PCA). But in PCA, it is not easy to compute eigenvectors with a large matrix when considering the cost of calculation to adapt for time-varying processing.In this paper, in order for PCA to become high-speed, the simple principal component analysis (SPCA) is applied compress the dimensionality of portions that constitute a face. A value of cos0 is calculated using the eigenvector and the gray-scale image vector of each picture pattern. By using Neural Networks (NN), the value of cos0 between true and false (plastic) smiles is clarified and the true smile is discriminated. Finally, in order to show the effectiveness of the proposed face classification metod for true or false smile, computer simulations are done.

Computational Analysis of Smile Weight Distribution across the Face for Accurate Distinction between Genuine and Posed Smiles

“…Based on the 2D principal component analysis combined with Gabor filters and support vector based machine learning they report an 85.9% accuracy in smile classification. Similarly, Nakano et al, [16] utilized principle component analysis along with neural network based machine learning to achieve smile classification rates of up to 90%, though their framework does not explicitly utilize FACS coding.…”

Photogenic Facial Expression Discrimination

“…In the work of Nakano et al (Nakano et al, 2002), Simple Principal Component Analysis (SPCA) were used to extract features from smiles. The value of cos θ, being θ the angle between the eigenvector and the gray scale vector of each image, was calculated and used as input to a MLP.…”