Eigenface

About: Eigenface is a research topic. Over the lifetime, 2128 publications have been published within this topic receiving 110119 citations.

An Algorithm of Face Recognition Based on the Variation of 2DPCA

Abstract: This paper discusses the symmetry of face, the Characteristic of PCA (Principal Component Analysis) and 2DPCA(2-Dimensional PCA). It is proved that the covariance matrix of 2DPCA is equivalent to the average of the main diagonal of PCA and the covariance of 2DPCA eliminats some covariance information that be useful for recognition. An algorithm of face recognition based on the variation of 2DPCA (V2DPCA) is proposed which make the most useful of the discriminant information of covariance, and use the fewer coefficient to representing a image. Experiments on the ORL and YALE face bases show improvement in both recognition accuracy and recognition time over the original 2DPCA, and is also superior to the traditional eigenfaces, ICA (Independent Component Analysis ) and Kernel eigenfaces in terms of the recognition accuracy.

Face authentication with salient local features and static Bayesian network

Abstract: In this paper, the problem of face authentication using salient facial features together with statistical generative models is adressed. Actually, classical generative models, and Gaussian Mixture Models in particular make strong assumptions on the way observations derived from face images are generated. Indeed, systems proposed so far consider that local observations are independent, which is obviously not the case in a face. Hence, we propose a new generative model based on Bayesian Networks using only salient facial features. We compare it to Gaussian Mixture Models using the same set of observations. Conducted experiments on the BANCA database show that our model is suitable for the face authentication task, since it outperforms not only Gaussian Mixture Models, but also classical appearance-based methods, such as Eigenfaces and Fisherfaces.

Impression transformation of a face based on discriminant analysis on separately coded representations of facial shape and texture

Abstract: This work describes an attempt to develop a real-life application for transforming the appearance of a person's face to give a more favorable impression. Face images are first represented as high-dimensional vectors by separating the shape and texture information, and variations in the appearance of face images are coded by applying principal component analysis to a set of various face images. The relationship between the coded representation and the impression of corresponding images is analyzed, and an impression transfer vector is defined by the Fisher's linear discriminant obtained from a number of training images previously categorized into two opposing classes for a given impression dimension. An image manipulation method for transforming impressions is proposed which shifts the projection of the input image in the parameter space by an arbitrary magnitude of the impression transfer vector. Experimental results for impression transformations of both age and gender dimensions showed that the method proposed for face image manipulation is an effective one.

View-subspace analysis of multi-view face patterns

Abstract: Multi-view face detection and recognition has been a challenging problem. The challenge is due to the fact that the distribution of multi-view faces in a feature space is more dispersed and more complicated than that of frontal faces. This paper presents an investigation into several view-subspace representations of multi-view faces: learning by using independent component analysis (ICA), independent subspace analysis (ISA) and topographic independent component analysis (TICA). It is shown that view-specific basis components can be learned from multi-view face examples in an unsupervised way by using ICA, ISA and TICA; whereas the components learned by using principal component analysis reveal little view-related information. The learned results provide sensible basis for constructing view-subspaces for multi-view faces. Comparative experiments demonstrate distinctive properties of ICA, ISA and TICA results, and the suitability of the results as representations of multi-view faces.

An efficient human face indexing scheme using eigenfaces

Abstract: We propose an efficient indexing structure for searching a human face in a large database. In our method, a set of eigenfaces is computed based on the faces in the database. Each face in the database is then ranked according to its projection onto each of the eigenfaces. A query input will be ranked similarly, and the corresponding nearest faces in the ranked position with respect to each of the eigenfaces are selected from the database. These selected faces will then form a small database, namely a condensed database, for face recognition, instead of considering the original large database. In the experiments, the effect of the number of eigenfaces used on the size of the condensed database is investigated. Experimental results show that the size of the condensed database is 35% of the original large database when 25% of the eigenfaces with the largest eigenvalues are selected. The processing time required to generate the condensed database is less than one second.