3D Gabor-Edge filters applied to face depth images
Ghada Torkhani, Anis Ladgham, Anis Sakly · 2017
This manuscript introduces a novel 3D face authentication system inspired from the advantageous capacities of Gabor-Edge filters. The approach studies 3D face difficulties such as expression variety, different rotations and exposure to illuminations. The proposed systems starts by preprocessing the 3D face images to resolve acquisition problems. Then, a filtering process is performed by implanting our 3D Gabor-Edge technique extended based on the classic 3D Gabor masks. The next step is to achieve the classification of facial features from the edge saliency by the artificial Neural Network Classifier (NNC). The evaluation of the adopted system is achieved by exporting common datasets from GavabDB database. Experimental results are reported to prove the high accuracy rates of our method compared to the recent researches in the same biometric field.