Kahraman F, Gokmen M, 2002, "Face recognition with the use of principal component analysis based on artificial neural networks" Perception 31 ECVP Abstract Supplement
Face recognition with the use of principal component analysis based on artificial neural networks
F Kahraman, M Gokmen
Face recognition has been a very hot research topic in recent years and face recognition is also a high-level visual problem. The purpose of this study has been the classification of human faces by using multilayer perceptron neural networks. First, we found the feature vectors of faces by using the principal component analysis (PCA) method. PCA is one of the most successful techniques that has been used to recognise faces in images. It is a technique that extracts the orthogonal axes along which a data set varies most by computing the eigenvectors and eigenvalues of the covariance matrix of the data, which is constructed from an image database. When PCA is applied to facial images, these eigenvectors are often called eigenfaces. After obtaining feature vectors, we trained the neural network by using error-back-propagation algorithm and we used these feature vectors as an input for the artificial neural network.
These web-based abstracts are provided for ease of seaching and access, but certain aspects (such as as mathematics) may not appear in their optimum form. For the final published version of this abstract, please see
ECVP 2002 Abstract Supplement (complete) size: 1753 Kb