|
An Efficient GUI Face Recognition System Based on Dirichlet Laplacian AwarenessKeywords: EigenvaluesFinite difference method , Curve descriptor , Binary image classification , noise Abstract: The eigenvalues of Dirichlet Laplacian used efficiently as a curve descriptor to generate three different sets of features for shape analysis and classification in binary images[5]. For the binary images the generated features are rotation-, translation-, and size-invariant. It was shown that the three sets of features were tolerant of boundary noise and deformation. These features are used to develop a graphical user interface for inquiry of facial images among the database with/without noise. The recognition has been done with a high degree of accuracy and using a relatively small number of features.
|