To search, Click below search items.


All Published Papers Search Service


3D face recognition using 2DPCA


Eng .Amr Rashad, Alaa Hamdy, Mohamed Ali Saleh, Mohamed Eladawy


Vol. 9  No. 12  pp. 149-155


Robustness of face recognition systems are measured by its ability to overcome the problem of changing in facial expression and rotation of individuals’ face images. This paper represents a face recognition system that overcomes the problem of changes in facial expressions in three-dimensional (3D) range images. A local variation detection and restoration method based on the two-dimensional (2D) principal component analysis (PCA) is proposed. The depth map of 3D facial image is first thresholded to discard the back ground information. Then, the detected face shape is normalized to standard size 100x100 pixels and nose point is selected to be the image center. Image depth values are scaled between 0 and 255 and nose tip has the highest value 255 for translation and scaling ?invariant identification. In preprocessing stage, the local variation is minimized by smoothing the face image. The (2D) principle component analysis is applied to the resultant range data for feature extraction and the corresponding principal images are used as the characteristic feature vectors of the subject to find his/her identity in the database of pre-recorded faces. The system performance is tested against the GavabDB facial database. The facial modeling technique presented here is implemented in a PC platform with the software support of Matlab version 7.7. Experimental results show that the proposed method is able to identify subjects with different facial expression in their 3D facial images.


3D Face, 2DPCA