FACE RECOGNITION THROUGH VARIOUS FACIAL EXPRESSIONS

Face recognition is the main task of the problem that the developers solve, and it also attracts ordinary users, since this area is called intervention biometric modality. In this article, we proposed a new method for identification, that is, the detection (recognition) of faces with different emotions of faces. This approach consists of two elements: the first is facial expression recognition and the second is facial recognition. The method reflects two more important steps to improve the quality of face recognition when changing facial expressions. The first step to choose is specially selected characteristics that decide for the formation of the emotions of individuals, applying the approach (method) of mutual information. This action helps to effectively improve the accuracy of the classification offacial expressions, as well as reduce the size of the feature vector. In the second stage, we used the basic component analysis (PCA) to build EigenFaces for each class of facial expressions. Then, face recognition is performed by projecting the face onto the corresponding Eigen Faces facial expression. The PCA technique significantly reduces the dimension of the original spaces, since face recognition is performed in the reduced EigenFaces space. An experimental study was conducted to evaluate the effectiveness of the proposed approach in terms of the accuracy offace recognition and space-time complexity.

1. Neurological and Psychological Mechanisms for Producing Facial Expressions. Psychological Bulletin (American Psychological Association Inc.) (1995).

2. Abbas, A. (2010). Face identification using multiwavelet-based neural network. Ph.D. thesis, University of Baghdad.

3. Ahonen, T., & H. A. P. M. (2004). Face recognition with local binary patterns, the European Conference on Computer Vision.

4. Arandjelovic, O., & S. G. F. J. C. R. D. T. (2005). Face recognition with image sets using manifold density divergence. In: CVPR.

5. Bartlett, M. S., & L. G. F. I. M. R. (2003). Real time face detection and facial expression recognition: Developmentandapplicationto human computer interaction. In: CVPR Workshop on CVPR for HCI.

6. Barton,J. J.,& Z. J. K. J. P. (2003). Perception of global facial geometry in the inversion effect and prosopagnosia. Neuropsychologia.

7. Belhumeur P. N., & H. J. K. D. (1997). Eigenfaces vs. fisherfaces, Recognition using class specif­ic linear projection. J. IEEE Trans (PAMI).

8. Y.-Q. Wang, «An Analysis of Viola-Jones Face Detection Algorithm, » IPOL Journal, 2013.

9. L. Shapiro and D. Stockman, Computer Vision, Bin. Laboratory of Knowledge, 2006.