Reconhecimento de Faces 3D Segmentadas em Regiões Triaxiais Utilizando Momentos Espaciais Adaptados e Invariantes à Rotação

Abstract

This work presents a multiple slicing model for 3D images of human face, using the Frontal, Sagittal and Transverse orthogonal planes. The definition of the segments depends on just one key point, the nose tip, which makes it simple and independent of the detection of several key points. For facial recognition, attributes based on adapted 2D spatial moments of Hu and 3D spatial Invariant Rotation Moments are extracted from each segment. Tests with the proposed model using the Bosphorus Database for neutral vs non-neutral ROC I experiment, applying Linear Discriminant Analysis as classifier and more than one sample for training, achieved 98.7% of verification rate with 0.1% of false acceptance rate. By using the Support Vector Machine as classifier the rank1 experiment recognition rates of 99% and 95.4% have been achieved for a neutral vs neutral and for a neutral vs non-neutral, respectively. These results approach the state-of-the-art using Bosphorus Database and even surpasses it when Anger and Disgust expressions are evaluated. In addition, it was also evaluate the generalization of the method using the FRGC v2.0 database and competitive results been achieved, making the technique promising, especially for its simplicity.