Showing papers on "Facial recognition system published in 1988"

Upside-down faces : a review of the effect of inversion upon face recognition

Abstract: Several studies have found that face recognition is disproportionately impaired by stimulus inversion when compated to recognition of other classes of visual stimuli. This effect has been interpreted as evidence that face recognition benefits from a 'special' process which is not engaged by an inverted face. This paper reviews studies of the effect of inversion on face recognition in recognition memory tasks, matching tasks and upon cerebral hemisphere asymmetries. Evidence is drawn from developmental studies and from studies of brain-injured and normal adult subjects. It is concluded that the evidence that inverted faces are processed differently from upright faces is far from compelling, and therefore the effect of inversion provides little or no evidence of a unique process in face recognition. The inversion effect is interpreted in terms of expertise in face processing and the highly homogeneous nature of faces as a stimulus class.

Intact recognition of facial expression, gender, and age in patients with impaired recognition of face identity

Abstract: We conducted a series of experiments to assess the ability to recognize the meaning of facial expressions, gender, and age in four patients with severe impairments of the recognition of facial identity. In three patients the recognition of face identity could be dissociated from that of facial expression, age, and gender. In one, all forms of face recognition were impaired. Thus, a given lesion may preclude one type of recognition but not another. We conclude that (1) the cognitive demands posed by different forms of recognition are met at different processing levels, and (2) different levels depend on different neural substrates.

Mental rotation of faces

Abstract: The effect of orientation upon face recognition was explored in two experiments, which used a procedure adapted from the mental rotation literature. In the first experiment, a linear increase in the RT of same-different judgments was found as the second of a pair of sequentially presented faces was rotated away from the vertical. Also, it was found that the effect of changing facial expression did not interact with orientation. In the second experiment, a linear relationship between RT and orientation was found in a task involving the recognition of famous faces. This recognition task was found to be more affected by inversion than was an expression classification task. These results are interpreted as evidence against the view that inverted faces are processed in a qualitatively different manner from upright faces, and are also inconsistent with the hypothesis that inversion makes faces difficult to recognize because facial expression cannot be extracted from an inverted face.

Autonomous face recognition machine

Abstract: A machine is disclosed that is capable of locating human faces in video scenes with random content within two minutes, and capable of recognizing the faces that it locates. The machine uses images obtained from a video camera and is insensitive to variations in brightness, scale, focus, and operates without any human intervention or inputs. When a motion detection feature is included, (one of its options), the location and recognition events occur in less than 1 minute. One embodiment of the system uses: a camera, a Micro-Vax computer, an analog-go-digital A/D converter, and a hard copy print out to process video scenes with random content using an original computer program to locate human faces and identify them. In operation, the camera converts the video scenes into an analog electrical signal, which is converted into digital and forwarded to the computer. The computer performs an original pattern recognition algorithm to search for facial components, identify a gestalt face, and compare the gestalt-face's detected facial characteristics with a stored set of facial characteristics of known human faces, to identify the face thereby.

Face recognition from range data by structural analysis

Abstract: A primal approach to the analysis of a human face through its 3-D image is proposed. This analysis is based on local pattern concepts deduced from the intrinsic properties of a surface described by its local curvature characteristics. Some theoretical results about curvature are recalled and then used for the extraction of characteristic geometrical features from the face surface. Recognition can be achieved by using a pattern vector of distances calculated from these features. Experimental results are provided to illustrate the various steps of the approach.

Enhanced Autonomous Face Recognition Machine. Volume 1

Abstract: : This thesis continues work on the Autonomous Face Recognition Machine developed at AFIT in 1985. There were two major changes made to the system. The set of features extracted from the face for use in the recognition process, was changed. A higher dimensioned vector taken from the two-dimensional Discrete Fourier Transform of the face, was used in hope of increasing the separation of templates stored in the data base. Further research is needed to determine whether this change is beneficial to the system. The second change was to the decision rule used in recognition. The decision making portion of the system was replaced by a back propagation neural network. While providing equivalent recognition capability, this change provides a constant recognition time independent of the number of subjects trained into the system. Keywords: Pattern recognition, Image processing, Neural networks, Gesalt transforms.

The Use Of Fuzzy Relations In Pattern Recognition

Abstract: Fuzzy relations, if utilized properly, can improve the recognition process by reducing the search space for each feature and thus increasing the speed of the recognition process. In this paper we describe such a system based on fuzzy relations and show how fuzzy relations improve the overall performance of the Cooperative Fuzzy Expert System for Intelligent Recognition.