Fuzzy Neural Networks and Fuzzy Integral Approach to Curvature-Based Component Range Facial Recognition

The surface curvatures in the face contain the most important personal features information. In this paper, we develop a method for recognizing 3D face images by combining face component; eyes, cheek, mouth, and nose. For the proposed approach, the first step uses face curvatures which present the facial features for 3D face images, after normalization using the SVD. As a result of this process, we obtain curvature feature for each component range face. Fuzzy neural network, PCA, and Fisherface methods are then applied to each component range face. The reason for adapting PCA and Fisherface method is that the methods maintain the surface attribute for face curvature, even though they can generate reduced image dimension. In the last step, the aggregation of the individual classifiers using the fuzzy integral is explained for each component. The experimental results showed that the proposed approach has outstanding classification performance compared to other methods.