scispace - formally typeset
Search or ask a question

Showing papers on "Facial recognition system published in 1989"


Proceedings ArticleDOI
01 Jan 1989
TL;DR: A graph-matching process of object recognition is proposed, applied to face recognition, which amounts to labeled graph matching, with Gabor jets forming labels to nodes and topology determining links.
Abstract: A graph-matching process of object recognition is proposed. It is applied to face recognition. Gray-level images are represented by a resolution hierarchy of local Gabor components, which are all scaled and rotated versions of each other. The components centered on one image point form a Gabor jet. A single jet provides a distortion-insensitive local representation of part of an image. Object recognition is achieved by matching image point jets to jets in stored prototype patterns. For a selected image jet the best matches are determined, under a constraint preserving spatial arrangement. The procedure amounts to labeled graph matching, with Gabor jets forming labels to nodes and topology determining links. A contrast-insensitive similarity measure provides for invariance with respect to lighting conditions. The authors have formulated the matching procedure as an optimization task solved by diffusion of match points. This diffusion is controlled by a potential determined by jet similarity and the topology-preserving constraint. The algorithm implements a neural network architecture. >

112 citations


Proceedings ArticleDOI
27 Nov 1989
TL;DR: Work related to the authentification or recognition of human faces from their range images is described, which involves the similarity of the Gaussian curvature values of the face surface to calculate similarity indices of profiles or surfaces.
Abstract: Work related to the authentification or recognition of human faces from their range images is described. The approach consists of comparing a part of the profile or the surface of two faces. For this purpose, the profile plane of each face is considered as a quasi-symmetry plane and is extracted by an iterative process which involves the similarity of the Gaussian curvature values of the face surface. Then an optimal matching of the two profiles is done, which allows the calculation of similarity indices of profiles or surfaces. Tests for robustness and the authentification or recognition results show the efficiency of the whole procedure. >

104 citations


Proceedings ArticleDOI
23 May 1989
TL;DR: A human face recognition system, which has a feature extraction subsystem and a recognition subsystem, has been built and a two-test method is used to increase the accuracy of the recognition.
Abstract: A human face recognition system, which has a feature extraction subsystem and a recognition subsystem, has been built. An unknown human facial image is captured and digitized by a frame grabber, and features of the digitized image are extracted. The features are stored during the learning phase and are compared with the references in the memory during the recognition phase. A two-test method is used to increase the accuracy of the recognition. The first test eliminates a number of records with large differences in major features. The second test selects the one with minimum differences by calculating the total weighted error. Test results are presented. >

27 citations


Journal ArticleDOI
TL;DR: The elderly subjects exhibited a more liberal response bias than the young subjects, indicating that impaired memory task performance of the aged subjects cannot be attributed to a more conservative test-taking strategy.
Abstract: A facial recognition memory task was administered to 16 young subjects (age range 18-30) and 28 elderly subjects (age range 63-83). A continuous recognition paradigm was used, in which subjects were instructed to identify the repeated faces in an ongoing series of faces presented on a video monitor screen. A signal detection analysis of the data revealed a mild recognition memory deficit in the elderly, due mainly to an increase in false positives during the second half of the test session. This age-specific increase in late-session false alarms may be a result of increased sensitivity of the aged subjects to proactive interference from previously presented faces. Increasing the length of the delay between the initial and repeat presentation of a face decreased recognition accuracy in both groups, but the young subjects were more sensitive to the delay interval effect than the elderly. Multiple presentations of faces produced a comparable improvement in the recognition accuracy of both young and ...

23 citations


Proceedings ArticleDOI
27 Mar 1989
TL;DR: It is shown that all patients demonstrated better face recognition with the enhanced images than with the original, untouched images, which were significantly clearer, sharper, and easier to see.
Abstract: The authors evaluate whether patients demonstrate improved face recognition when viewing enhanced images. Difficulty with face recognition is a frequent, early complaint of many patients with macular disease. Faces can be recognized when low-pass filtered to a large degree or high-pass filtered. To evaluate actual face recognition rather than the ability to discriminate among test faces, the authors tested the patient's ability to recognize celebrities, which is more robust than the recognition of unfamiliar faces. It is shown that all patients demonstrated better face recognition with the enhanced images than with the original, untouched images. Analysis of the difference between the two areas under the receiver operating curves indicated a statistically significant increase in recognition for 8 out of 17 patients. Patients reported that the enhanced images were significantly clearer, sharper, and easier to see. >

4 citations


01 Dec 1989
TL;DR: Fourier coefficients are demonstrated as a reliable feature set for face recognition, using the Autonomous Face Recognition Machine developed at AFIT over the past several years, and the Fourier transform portion of the system was examined and improved.
Abstract: : This thesis demonstrates Fourier coefficients as a reliable feature set for face recognition, using the Autonomous Face Recognition Machine developed at AFIT over the past several years. The Fourier transform portion of the system was examined and improved. The code was made more efficient. Two Fourier transform routines (a fast Fourier transform and a classical Fourier transform) were tested and compared. A voting scheme was incorporated for examining multiple looks at test faces. To further demonstrate performance, the number of faces in the data base was doubled. Recognition scores of up to 87% were achieved, compared to 63% for Sander's process with Fourier coefficients as a feature set and 67% for Lambert's process with a center-of-mass feature set. This thesis includes complete system documentation, to assist those doing further research in this area.

1 citations


Book ChapterDOI
01 Jan 1989

1 citations