Showing papers on "Facial recognition system published in 1990"

Face recognition system

Abstract: A recognition system for identifying members of an audience, the system including an imaging system which generates an image of the audience; a selector module for selecting a portion of the generated image; a detection means which analyzes the selected image portion to determine whether an image of a person is present; and a recognition module responsive to the detection means for determining whether a detected image of a person identified by the detection means resembles one of a reference set of images of individuals.

EMPATH: Face, Emotion, and Gender Recognition Using Holons

Abstract: The dimensionality of a set of 160 face images of 10 male and 10 female subjects is reduced from 4096 to 40 via an autoencoder network. The extracted features do not correspond to the features used in previous face recognition systems (Kanade, 1973), such as ratios of distances between facial elements. Rather, they are whole-face features we call holons. The holons are given to 1 and 2 layer back propagation networks that are trained to classify the input features for identity, feigned emotional state and gender. The automatically extracted holons provide a sufficient basis for all of the gender discriminations, 99% of the identity discriminations and several of the emotion discriminations among the training set. Network and human judgements of the emotions are compared, and it is found that the networks tend to confuse more distant emotions than humans do.

Matching range images of human faces

Abstract: The problem of matching range images of human faces for the purpose of establishing a correspondence between similar features of two faces is addressed. Distinct facial features correspond to convex regions of the range image of the face, which is obtained by a segmentation of the range image based on the sign of the mean and Gaussian curvature at each point. Each convex region is represented by its extended Gaussian image, a 1-1 mapping between points of the region and points on the unit sphere that have the same normal. Several issues are examined that are associated with the difficult problem of interpolation of the values of the extended Gaussian image and its representation. A similarity measure between two regions is obtained by correlating their extended Gaussian images. To establish the optimal correspondence, a graph matching algorithm is applied. It uses the correlation matrix between convex regions of the two faces and incorporates additional relational constraints that account for the relative spatial locations of the convex regions in the domain of the range image. >

Face recognition using a digital neural network with self-organising capabilities

Abstract: An approach to face recognition using neural networks is presented. All automatic training procedure based on self-organization is defined. This procedure partitions the data into disjoint classes containing recognizable attributes and can be used to replace a human operator in selecting valid data for training purposes. The nodal operation within the neural network was initially based on combinational logic functions and has been developed to take account of the dominance of salient features in the data. Experimental results demonstrate the system's facial recognition capabilities using multiple classes of data. >

Face Recognition without Features.

Abstract: We have developed a near-real-time computer system which can locate and track a subject's head, and then recognize the person by comparing characteristics of the face to those of known individuals. Our approach treats the face recognition problem as an intrinsically twodimensional recognition problem, taking advantage of the fact that faces are are normally upright and thus may be described by a small set of 2-D characteristic views. The system functions by projecting face images onto a feature space that spans the significant variations among known face images. The significant features are known as "eigenfaces", because they are the eigenvectors (principal componmt,s) of the set of faces; they do not necessarily correspontl to features such as eyes, ears, and noses.

Facial recognition for police purposes using computer graphics and neural networks

Abstract: Neural nets provide a viable solution to identifying criminals photographed at the scene of the crime. A program was written in lightspeed Pascal on a Macintosh II personal computer to simulate a WISARD neural network. A target face from the photograph collection was chosen at random and the net was trained to recognise it. The experimental work is outlined.< >

3 – Face Recognition

Abstract: Publisher Summary This chapter discusses the neuroscience of face recognition. The ability to process the visual information conveyed by the human face is an important skill in normal social interactions. The chapter discusses the information-processing model of face recognition developed by Bruce and Young (1986), which incorporates much of the evidence from neuropsychological and normal studies of face processing. This model distinguishes several different components in the complex skill of facial processing. Following the visual analysis of a face, several subprocesses can be conducted in parallel. Matching of faces for sameness or difference across viewpoints—directed visual processing—is distinguished from facial speech analysis—lip reading—and expression analysis. These procedures are distinguished from face recognition. The parallel organization of this model is necessary to encompass the range of dissociations in face-processing skills that are seen in patients. The descriptive model proposed by Bruce and Young has some points of similarity with models of object recognition and reading. The processing involved in visual analysis of faces is separated on the one hand from perceptual processing of unfamiliar faces and on the other from a stage in which the faces of familiar people are represented.