BIOMETRIC IDENTIFICATION ALGORITHMS IN FACE RECOGNITION AND THEIR ANALYSIS
Keywords:
CNN, facial image recognition systems, 2DPCA, PCA, F-2DPCA, ICA, stream of frames.Abstract
Biometric identification systems are widely used to increase security. Due to its wide user acceptance, accuracy, security and relatively low cost, facial image recognition is the leading method. Although facial image recognition systems have reached a certain level of maturity, some challenging tasks still require more research. The reason for this is to increase information security and improve people's living conditions in the age of globalization. In this master's dissertation, we studied the basics of facial image recognition, mathematical methods of biometric facial recognition, and the algorithm of many methods related to facial biometric recognition. For example: linear discriminant analysis, support vector machine, hybrid approach, face detection with CNN (Cable News Network).
References
1. K. Mikolajczyk and C. Schmid, “A performance evaluation of local descriptors,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, no. 10, pp. 1615–1630, Oct 2005;
2. Qifa Ke and T. Kanade, “Robust l/sub 1/ norm factorization in the presence of
outliers and missing data by alternative convex programming,” in 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR05), vol. 1, June 2005, pp. 739–746 vol. 1;
