In this paper, we propose a robust 3D face recognition system which can handle pose as well as occlusions in real world. The system at first takes as input, a 3D range image, simultaneously registers it using ICP(Iterative Closest Point) algorithm. ICP used in this work, registers facial surfaces to a common model by minimizing distances between a probe model and a gallery model. However the performance of ICP relies heavily on the initial conditions. Hence, it is necessary to provide an initial registration, which will be improved iteratively and finally converge to the best alignment possible. Once the faces are registered, the occlusions are automatically extracted by thresholding the depth map values of the 3D image. After the occluded regions are detected, restoration is done by Principal Component Analysis (PCA). The restored images, after the removal of occlusions, are then fed to the recognition system for classification purpose. Features are extracted from the reconstructed non-occluded face images in the form of face normals. The experimental results which were obtained on the occluded facial images from the Bosphorus 3D face database, illustrate that our occlusion compensation scheme has attained a recognition accuracy of 91.30%.

No abstract

No abstract

In this proposed work, a fully automatic 3D Face Recognition system across pose is presented, which works successfully on three modern databases namely the Frav3D, GavabDB and the Bosphorus databases. Poses handled in the system are yaw, pitch and roll varying from O· to ±30° as well as expressions. The feature extraction is by depth face images with variation in depth values of the surface normals and also by KPCA. The system gives high recognition rate of 96.92% in case of GavabDB database, 96.25% in case of Bosphorus face database and 92.25% in case of Frav3D database by surface normals extraction.

No abstract