Download Now Free registration required
In this paper, the authors proposed a new fast technique of face authentication based on extraction of a simple Statistical features derived from the image of face. Once the feature vector is extracted, they comparing it with the feature vector of face which is authenticated, and they calculated the error rates in the two sets of validation and test for the data base XM2VTS according to the protocol of Lausanne. The experimental results indicate the reliability, feasibility and efficacy of the proposed method. Moreover, compared to PCA, LDA and EFM, the proposed technique is very quicker to compute.
- Format: PDF
- Size: 406.05 KB