Analysis of Dense Descriptors in 3D Face Recognition

In the past years, a revolution took place in the world of technology and developed rapidly in all areas, covering various aspects of life. One of the hottest topics that researchers work in is computer vision including artificial intelligence. As it has a great importance, it represents the basics for many applications that are currently used in various sectors. The technology of biometric recognition has progressively developed specially in security for identification purposes. Such technology is face recognition, which uses facial information of humans to recognize people. In this paper 3D (three-dimensional) face recognition approach is proposed by using dense descriptors Local Binary Pattern (LBP), Local Ternary Pattern (LTP), and Gabor with Support Vector Machine (SVM). LTP technique which is a variant and extension of LBP. LBP and LTP have been used for feature information extraction individuality and merging with Gabor from the 3D images, and then the SVM technique is employed to classify and recognize the faces according to extracted features. The database that depended in this work is Three-Dimensional Face Recognition Database (Texas 3DFRD). The accuracy obtained from the proposed model was about 94.9% after many attempts the better one is selected.