Showing papers on "Eigenface published in 1998"

Integrating faces and fingerprints for personal identification

Abstract: An automatic personal identification system based solely on fingerprints or faces is often not able to meet the system performance requirements. We have developed a prototype biometrics system which integrates faces and fingerprints. The system overcomes the limitations of face recognition systems as well as fingerprint verification systems. The integrated prototype system operates in the identification mode with an admissible response time. The identity established by the system is more reliable than the identity established by a face recognition system. In addition, the proposed decision fusion scheme enables performance improvement by integrating multiple cues with different confidence measures. Experimental results demonstrate that our system performs very well. It meets the response time as well as the accuracy requirements.

Beyond eigenfaces: probabilistic matching for face recognition

Abstract: We propose a technique for direct visual matching for face recognition and database search, using a probabilistic measure of similarity which is based on a Bayesian analysis of image differences. Specifically we model lure mutually exclusive classes of variation between facial images: intra-personal (variations in appearance of the same individual, due to different expressions or lighting) and extra-personal (variations in appearance due to a difference in identity). The likelihoods for each respective class are learned from training data using eigenspace density estimation and used to compute similarity based on the a posteriori probability of membership in the intra-personal class, and ultimately used to rank matches in the database. The performance advantage of this probabilistic technique over nearest-neighbor eigenface matching is demonstrated using results front ARPA's 1996 "FERET" face recognition competition, in which this algorithm was found to be the top performer.

Vehicle sound signature recognition by frequency vector principal component analysis

Abstract: The sound (engine, noise, etc.) of a working vehicle provides an important clue, e.g., for surveillance mission robots, to recognize the vehicle type. In this paper, we introduce the "eigenfaces method", originally used in human face recognition, to model the sound frequency distribution features. We show that it can be a simple and reliable acoustic identification method if the training samples can be properly chosen and classified. We treat the frequency spectra of about 200 ms of sound (a "frame") as a vector in a high-dimensional frequency feature space. In this space, we study the vector distribution for each kind of vehicle sound produced under similar working conditions. A collection of typical sound samples is used as the training data set. The mean frequency vector of the training set is first calculated, and subtracted from each vector in the set. To capture the frequency vectors' variation within the training set, we then calculate the eigenvectors of the covariance matrix of the zero-mean-adjusted sample data set. These eigenvectors represent the principal components of the vector distribution: for each such eigenvector, its corresponding eigenvalue indicates its importance in capturing the variation distribution, with the largest eigenvalues accounting for the most variance within this data set. Thus for each set of training data, its mean vector and its moat important eigenvectors together characterize its sound signature. When a new frame (not in the training set) is tested, its spectrum vector is compared against the mean vector; the difference vector is then projected into the principal component directions, and the residual is found. The coefficients of the unknown vector, in the training set eigenvector basis subspace, identify the unknown vehicle noise in terms of the classes represented in the training set. The magnitude of the residual vector measures the extent to which the unknown vehicle sound cannot be well characterized by the vehicle sounds included in the training set.

Enhanced Fisher linear discriminant models for face recognition

Abstract: We introduce two enhanced Fisher linear discriminant (FLD) models (EFM) in order to improve the generalization ability of the standard FLD based classifiers such as Fisherfaces Similar to Fisherfaces, both EFM models apply first principal component analysis (PCA) for dimensionality reduction before proceeding with FLD type of analysis EFM-1 implements the dimensionality reduction with the goal to balance between the need that the selected eigenvalues account for most of the spectral energy of the raw data and the requirement that the eigenvalues of the within-class scatter matrix in the reduced PCA subspace are not too small EFM-2 implements the dimensionality reduction as Fisherfaces do It proceeds with the whitening of the within-class scatter matrix in the reduced PCA subspace and then chooses a small set of features (corresponding to the eigenvectors of the within-class scatter matrix) so that the smaller trailing eigenvalues are not included in further computation of the between-class scatter matrix Experimental data using a large set of faces-1,107 images drawn from 369 subjects and including duplicates acquired at a later time under different illumination-from the FERET database shows that the EFM models outperform the standard FLD based methods

Empirical performance analysis of linear discriminant classifiers

Abstract: In face recognition literature, holistic template matching systems and geometrical local feature based systems have been pursued. In the holistic approach, PCA (Principal Component Analysis) and LDA (Linear Discriminant Analysis) are popular ones. More recently, the combination of PCA and LDA has been proposed as a superior alternative over pure PCA and LDA. In this paper, we illustrate the rationales behind these methods and the pros and cons of applying them to pattern classification task. A theoretical performance analysis of LDA suggests applying LDA over the principal components from the original signal space or the subspace. The improved performance of this combined approach is demonstrated through experiments conducted on both simulated data and real data.

Face recognition based on nearest linear combinations

Abstract: This paper proposes a novel pattern classification approach, called the nearest linear combination (NLC) approach, for eigenface based face recognition. Assume that multiple prototypical vectors are available per class, each vector being a point in an eigenface space. A linear combination of prototypical vectors belonging to a face class is used to define a measure of distance from the query vector to the class, the measure being defined as the Euclidean distance from the query to the linear combination nearest to the query vector (hence NLC). This contrasts to the nearest neighbor (NN) classification where a query vector is compared with each prototypical vector individually. Using a linear combination of prototypical vectors, instead of each of them individually, extends the representational capacity of the prototypes by generalization through interpolation and extrapolation. Experiments show that it leads to better results than existing classification methods.

Face image analysis by unsupervised learning and redundancy reduction

Abstract: In a task such as face recognition, much of the important information may be contained in the high-order relationships among the image pixels. Representations such as "Eigenfaces" (197) and "Holons" (48) are based on Principal component analysis (PCA), which encodes the correlational structure of the input, but does not address high-order statistical dependencies such as relationships among three or more pixels. Independent component analysis (ICA) is a generalization of PCA which encodes the high-order dependencies in the input in addition to the correlations. Representations for face recognition were developed from the independent components of face images. The ICA representations were superior to PCA for recognizing faces across sessions and changes in expression. ICA was compared to more than eight other image analysis methods on a task of recognizing facial expressions in a project to automate the Facial Action Coding System (62). These methods included estimation of optical flow; representations based on the second-order statistics of the full face images such Eigenfaces (47, 197) local feature analysis (156), and linear discriminant analysis (23); and representations based on the outputs of local filters, such as a Gabor wavelet representations (50, 113) and local PCA (153). The ICA and Gabor wavelet representations achieved the best performance of 96% for classifying 12 facial actions. Relationships between the independent component representation and the Gabor representation are discussed. Temporal redundancy contains information for learning invariances. Different views of a face tend to appear in close temporal proximity as the person changes expression, pose, or moves through the environment. The final chapter modeled the development of viewpoint invariant responses to faces from visual experience in a biological system by encoding spatio-temporal dependencies. The simulations combined temporal smoothing of activity signals with Hebbian learning (72) in a network with both feed-forward connections and a recurrent layer that was a generalization of a Hopfield attractor network. Following training on sequences of graylevel images of faces as they changed pose, multiple views of a given face fell into the same basin of attraction, and the system acquired representations of faces that were approximately viewpoint invariant.

Mixtures of local linear subspaces for face recognition

Abstract: Traditional subspace methods for face recognition compute a measure of similarity between images after projecting them onto a fixed linear subspace that is spanned by some principal component vectors (a.k.a. "eigenfaces") of a training set of images. By supposing a parametric Gaussian distribution over the subspace and a symmetric Gaussian noise model for the image given a point in the subspace, we can endow this framework with a probabilistic interpretation so that Bayes-optimal decisions can be made. However, we expect that different image clusters (corresponding, say, to different poses and expressions) will be best represented by different subspaces. In this paper, we study the recognition performance of a mixture of local linear subspaces model that can be fit to training data using the expectation maximization algorithm. The mixture model outperforms a nearest-neighbor classifier that operates in a PCA subspace.

Bayesian Modeling of Facial Similarity

Abstract: In previous work [6, 9, 10], we advanced a new technique for direct visual matching of images for the purposes of face recognition and image retrieval, using a probabilistic measure of similarity based primarily on a Bayesian (MAP) analysis of image differences, leading to a "dual" basis similar to eigenfaces [13]. The performance advantage of this probabilistic matching technique over standard Euclidean nearest-neighbor eigenface matching was recently demonstrated using results from DARPA's 1996 "FERET" face recognition competition, in which this probabilistic matching algorithm was found to be the top performer. We have further developed a simple method of replacing the costly compution of nonlinear (online) Bayesian similarity measures by the relatively inexpensive computation of linear (offline) subspace projections and simple (online) Euclidean norms, thus resulting in a significant computational speed-up for implementation with very large image databases as typically encountered in real-world applications.

Probabilistic reasoning models for face recognition

Abstract: We introduce in this paper two probabilistic reasoning models (PPM-1 and PRM-2) which combine the Principal Component Analysis (PCA) technique and the Bayes classifier and show their feasibility on the face recognition problem. The conditional probability density function for each class is modeled using the within class scatter and the Maximum A Posteriori (MAP) classification rule is implemented in the reduced PCA subspace. Experiments carried out using 1107 facial images corresponding to 369 subjects (with 169 subjects having duplicate images) from the FERET database show that the PRM approach compares favorably against the two well-known methods for face recognition-the Eigenfaces and Fisherfaces.

Face Recognition: A Hybrid Neural Network Approach

Abstract: Faces represent complex, multidimensional, meaningful visual stimuli and developing a computa- tional model for face recognition is difficult (Turk and Pentland, 1991). We present a hybrid neural network solution which compares favorably with other methods. The system combines local image sam- pling, a self-organizing map neural network, and a convolutional neural network. The self-organizing map provides a quantization of the image samples into a topological space where inputs that are nearby in the original space are also nearby in the output space, thereby providing dimensionality reduction and invariance to minor changes in the image sample, and the convolutional neural network provides for partial invariance to translation, rotation, scale, and deformation. The convolutional network extracts successively larger features in a hierarchical set of layers. We present results using the Karhunen-Loe transform in place of the self-organizing map, and a multilayer perceptron in place of the convolu- tional network. The Karhunen-Lo` eve transform performs almost as well (5.3% error versus 3.8%). The multilayer perceptron performs very poorly (40% error versus 3.8%). The method is capable of rapid classification, requires only fast, approximate normalization and preprocessing, and consistently exhibits better classification performance than the eigenfaces approach (Turk and Pentland, 1991) on the database considered as the number of images per person in the training database is varied from 1 to 5. With 5 images per person the proposed method and eigenfaces result in 3.8% and 10.5% error respectively. The recognizer provides a measure of confidence in its output and classification error approaches zero when rejecting as few as 10% of the examples. We use a database of 400 images of 40 individuals which con- tains quite a high degree of variability in expression, pose, and facial details. We analyze computational complexity and discuss how new classes could be added to the trained recognizer.

A unified Bayesian framework for face recognition

Abstract: This paper introduces a Bayesian framework for face recognition which unifies popular methods such as the eigenfaces and Fisherfaces and can generate two novel probabilistic reasoning models (PRM) with enhanced performance. The Bayesian framework first applies principal component analysis (PCA) for dimensionality reduction with the resulting image representation enjoying noise reduction and enhanced generalization abilities for classification tasks. Following data compression, the Bayes classifier which yields the minimum error when the underlying probability density functions (PDF) are known, carries out the recognition in the reduced PCA subspace using the maximum a posteriori (MAP) rule, which is the optimal criterion for classification because it measures class separability. The PRM models are described within this unified Bayesian framework and shown to yield better performance against both the eigenfaces and Fisherfaces methods.

Eigenfaces and eigenvoices: dimensionality reduction for specialized pattern recognition

Abstract: There are hidden analogies between two dissimilar research areas: face recognition and speech recognition. The standard representations for faces and voices misleadingly suggest that they have a high number of degrees of freedom. However, human faces have two eyes, a nose, and a mouth in predictable locations; such constraints ensure that possible images of faces occupy a tiny portion of the space of possible 2D images. Similarly, physical and cultural constraints on acoustic realizations of words uttered by a particular speaker imply that the true number of degrees of freedom for speaker-dependent hidden Markov models (HMMs) is quite small. Face recognition researchers have adopted representations that make explicit the underlying low dimensionality of the task, greatly improving the performance of their systems while reducing computational costs. We argue that speech researchers should use similar techniques to represent variation between speakers, and discuss applications to speaker adaptation, speaker identification and speaker verification.

Design of radial basis function network as classifier in face recognition using eigenfaces

Abstract: In this paper we investigate alternative designs of a radial basis function network acting as classifier in a face recognition system. The inputs to the RBF network are the projections of a face image over the principal components. A database of 250 facial images of 25 persons is used for training and evaluation. Two RBF designs are studied: the forward selection and the Gaussian mixture model. Both designs are also compared to the conventional Euclidean and Mahalanobis classifiers. A set of experiments evaluates the recognition rate of each method as a function of the number of principal components used to characterize the image samples. The results of the experiments indicate that the Gaussian mixture model RBF achieves the best performance while allowing less neurons in the hidden layer. The Gaussian mixture model approach shows also to be less sensitive to the choice of the training set.

A vector based approximation of KLT and its application to face recognition

Abstract: A face recognition scheme is proposed in this paper. The method utilizes a vector based approximation of KLT (VKLT) which eliminates the large memory demands and the singularity of the covariance matrix matters that are the main drawbacks of the “eigenface method” (a face recognition scheme based on KL transform). The reconstruction error of VKLT approaches the one of KLT preserving also its data dependence, which is important for discriminating face images from non-face images. Moreover, the greater advantage of VKLT over KLT is that of keeping intra-class variations small and consequently increasing the robustness of the face recognition system.

Hierarchical linear combinations for face recognition

Abstract: A hierarchical representation consisting of two level linear combinations (LC) is proposed for face recognition. At the first level, a face image is represented as a linear combination (LC) of a set of basis vectors, i.e. eigenfaces. Thereby a face image corresponds to a feature vector (prototype) in the eigenface space. Normally several such prototypes are available for a face class, each representing the face under a particular condition such as in viewpoint, illumination, and so on. We propose to use the second level LC, that of the prototypes belonging to the same face class, to treat the prototypes coherently. The purpose is to improve face recognition under a new condition not captured by the prototypes by using a linear combination of them. A new distance measure called nearest LC (NLC) is proposed as opposed to the NN. Experiments show that our method yields significantly better results than the one level eigenface methods.

Facial Memory Is Kernel Density Estimation (Almost)

Abstract: We compare the ability of three exemplar-based memory models, each using three different face stimulus representations, to account for the probability a human subject responded "old" in an old/new facial memory experiment. The models are 1) the Generalized Context Model, 2) SimSample, a probabilistic sampling model, and 3) MMOM, a novel model related to kernel density estimation that explicitly encodes stimulus distinctiveness. The representations are 1) positions of stimuli in MDS "face space," 2) projections of test faces onto the "eigenfaces" of the study set, and 3) a representation based on response to a grid of Gabor filter jets. Of the 9 model/representation combinations, only the distinctiveness model in MDS space predicts the observed "morph familiarity inversion" effect, in which the subjects' false alarm rate for morphs between similar faces is higher than their hit rate for many of the studied faces. This evidence is consistent with the hypothesis that human memory for faces is a kernel density estimation task, with the caveat that distinctive faces require larger kernels than do typical faces.

Eye detection and face recognition using evolutionary computation

Abstract: This chapter introduces evolutionary computation (EC) and genetic algorithms (GAs) for face recognition tasks. We first address eye detection as a visual routine and show how to implement it using a hybrid approach integrating learning and evolution. The goals of the novel architecture for eye detection are twofold: (i) derivation of the saliency attention map using consensus between navigation routines encoded as finite state automata (FSA) evolved using GAs and (ii) selection of optimal features using GAs and induction of DT (decision trees) for possibly classifying as eyes the most salient locations identified earlier. Experimental results, using 30 face images from the FERET data base show the feasibility of our hybrid approach. We then introduce the Optimal Projection Axes (OPA) method for face recognition. OPA works by searching through all the rotations defined over whitened Principal Component Analysis (PCA) subspaces. Whitening, which does not preserve norms, plays a dual role: (i) counteracts the fact that the Mean Square Error (MSE) principle underlying PCA preferentially weights low frequencies, and (ii) increases the reachable space of solutions to include non-orthogonal bases. As the search space is too large for any systematic search, stochastic and directed (‘greedy’) search is undertaken using again evolution in the form of Genetic Algorithms (GAs). Evolution is driven by a fitness function defined in terms of performance accuracy and class separation (‘scatter index’). Experiments carried out using 1,107 facial images corresponding to 369 subjects (with 169 subjects having duplicated images) from the FERET data base show that OPA yields improved performance over the eigenface and MDF (Most Discriminant Features) methods.

Generalizing capacity of face database for face recognition

Abstract: A face image can be represented by a point in a feature space such as spanned by a number of eigenfaces. In methods based on nearest neighbor classification, the representational capacity of a face database depends on how prototypical face images are chosen to account for possible image variations and also how many prototypical images or their feature points are available. We propose a novel method for generalizing the representational capacity of available face database. Any two feature points of the same class (individual) are generalized by the feature line passing through the points. The feature line covers more of the face space than the feature points and thus expands the capacity of the available database. In the feature line representation, the classification is based on the distance between the feature point of the query image and each of the feature lines of the prototypical images. Experiments are presented using a data set from five databases: the MIT, Cambridge, Bern, Yale and our own. There are 620 images of 124 individuals subject to varying viewpoint, illumination, and expression. The results show that the error rate of the proposed method is about 55%-60% of that of the standard eigenface method of M.A. Turk and A.P. Pentland (1991). They also demonstrate that the recognition result can be used for inferring how the position of the input face relative to the two retrieved faces.

Evolution of optimal projection axes (OPA) for face recognition

Abstract: The paper describes a novel approach called Optimal Projection Axes (OPA) for face recognition. OPA works by searching through all the rotations defined over whitened principal component analysis (PCA) subspaces. Whitening, which does not preserve norms, plays a dual role: (i) counteracts the fact that the mean square error (MSE) principle underlying PCA preferentially weights low frequencies; and (ii) increases the reachable space of solutions to include non orthogonal bases. Better performance from non orthogonal bases over orthogonal ones is expected as they lead to an overcomplete and robust representational space. As the search space is too large for any systematic search, stochastic and directed ("greedy") search is undertaken using evolution in the form of genetic algorithms (GAs). Evolution is driven by a fitness function defined in terms of performance accuracy and class separation (scatter index). Accuracy indicates the extent to which learning has been successful so far while the scatter index gives an indication of the expected fitness on future trials. Experiments carried out using 1107 facial images corresponding to 369 subjects (with 169 subjects having duplicated images) from the FERET database show that OPA yields improved performance over the eigenface and MDF (Most Discriminant Features) methods.

The use of eigenpictures for optical character recognition

Abstract: We show that the ideas behind the eigenface technique can be easily extended to the OCR problem by using multiple image classes In addition, we also describe a modification to the standard Euclidean distance measure used for recognition which gives very good results in this context

Building a representative training set based on eigenimages

Abstract: Adding new images to the training set necessitates a recalculation of the eigenfaces as well as the representation of all the images in the database in terms of the new eigenfaces. We describe an efficient procedure for doing this and give some examples of the performance of the procedure in practice.

3D motion estimation using expansion matching and KL based canonical images

Abstract: This paper describes a novel approach to 3D motion estimation of planar objects based on eigen-normalization, expansion matching (EXM) and a scaled orthographic projection model. Our approach leads to a comprehensive temporal description of all degrees of freedom in 3D (3 rotations and 3 translations). The 3D motion parameters of the objects are approximated by the corresponding affine parameters. The objects in each frame of a video sequence are normalized to a set of canonical images using principal component normalization procedure. The normalization approach here is based on principal components of the intensity weighted spatial values and not on the intensity values as in works such as eigenfaces. The canonical images generated differ only in orientation. Expansion matching (EXM) is then used to find the differences in orientation. Affine transformations between the shapes also are derived. The pose of the shape in 3D space can therefore be estimated. Experiments on video sequences of planar and quasi-planar objects show robust estimation of the real 3D rotations and translations of the objects in motion.

Baby Face Generator

Abstract: The first portion of the project involves implementing an algorithm for detecting human faces and localizing the key facial features. The implementation will build upon several face detection and facial feature extraction algorithms including Turk and Pentland’s work using eigenfaces to locate faces [1], Huang and Chen’s work using active contour models for facial feature extraction [2], and Saber and Tekalp’s work using color, shape, and symmetry-based cost functions for facial detection and feature extraction [3]. Additionally, the input faces’ ethnicities will be classified using eigenimages or fisher images and combined to select the baby’s ethnicity from a predefined database. The second portion of the project involves combining the identified facial features of the two individuals to form a composite image. This algorithm incorporates facial morphing techniques including Beier’s fieldmorphing algorithm [4] to properly weight and combine the input faces. A randomized weighting method will be used for selecting which features from the input images will appear in the output image so that a different baby image is generated each time the program runs. Finally, the composite image will include color correction to increase the natural appearance of the image. The final implementation of the baby face generator will include a user-friendly interface implemented in MATLAB. This project does not require a DROID camera phone.

Face recognition in a heterogeneous population

Abstract: Face recognition technology has many and varied applications, ranging from document verification to crowd surveillance. The use of face recognition technology in access control is, due to its nonintrusive nature, extremely promising. Most face location and segmentation algorithms proposed in the literature have very limited capabilities, with most not able to find a face which is either rotated or scaled. A novel segmentation algorithm which attempts to overcome these restrictions was developed and used in this study. The Eigenface approach (Karhunen-Loeve transform) has been shown to work extremely well when used to extract feature vectors from a face image. It was found to be the most promising of all the published methods and was therefore used. Most face recognition papers in the open literature have generally used Caucasian faces to test their algorithms, no special mention is made of the other population groups. The effect of a heterogeneous population on face recognition is therefore something of an unknown quantity. It is the aim of this paper to investigate the performance of the developed face recognition system, with emphasis on the effect of a heterogeneous population.

Tracking 3D display systems by image processing analysis

Abstract: This paper describes a fast algorithm of the face detection for an autostereoscopic display system allowing the viewing zone to follow the observer's head. This two phases face detection algorithm may real time detect the observer's eye- position such that the observers do not need to wear any artificial instruments to enable a most natural tracing 3D display system. The two phases face detection algorithm correlates the input image and an eigenface first, then send this correlated result through two thresholdings, and a filter to generate a possible face region. Then, the combination of the possible face region and the correlated result generates the face position information. Clustered background and eye-glasses wearing is allowed. This algorithm is also relatively robust on scaling and viewing angle variations.© (1998) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Subject-Based Modular Eigenspace Scheme for Face Recognition

Abstract: Face recognition is an important research area with many potential applications such as biometric security. Among various techniques, eigenface method by principal component analysis (PCA) of face images has been widely used. In traditional eigenface methods, PCA was used to get the eigenvectors of the covariance matrix of a training set of face images and recognition was achieved by applying a template matching scheme with the vectors obtained by projecting new faces along a small number of eigenfaces. In order to avoid the time consuming step of recomputing eigenfaces when new faces are added, we use a set of modules to generate PCA based face representation for each subjects instead of PCA of entire face images. The localized nature of the representation makes the system easy to maintain and tolerant of local facial characteristic changes. Results indicate that the modular scheme yield accurate recognition on the widely used Olivetti Research Laboratory (ORL) face database.