Comparative Analysis of Distance Metrics using Face Recognition
Researchers are using various distance metric standards in evaluation of face recognition methods. In past decades, the Eigenfaces and Fisherfaces face recognition methods were generally evaluated using the Euclidean distance (ED) metric that have shown better performance in cooperative environments, but poorly performed in non-cooperative environments. This paper presents a comparative analysis of distance metrics through face recognition methods i.e., Eigenfaces and Fisherfaces in both cooperative environments and non-cooperative environments. The recognition accuracies of these methods is critically evaluated using ED and Bray Curtis Dissimilarity (BCD) metrics in the face recognition under different conditions on publicly available face databases such as ORL and extended Yale B (EYB). The experimental results show significant improvement in recognition accuracies of Eigenfaces and Fisherfaces methods under BCD.
- There are currently no refbacks.
This site has been shifted to https://stmcomputers.stmjournals.com/