M. A. Turk. Interactive-Time Vision: Face Recognition as a Visual Behavior. PhD thesis, Massachusetts Institute of Technology, School of Architecture and Planning, September 1991.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....faces, against which the performance of computer algorithms for human face perception can be compared. In this paper, the results from experiments to determine the limits of human capabilities in face perception are reported. Face perception has been an area of active research in computer vision [2, 3, 4, 5]. Two of the main shortcomings of existing work are: a) they are not specifically targeted for face perception; most deal with identification, and (b) the 2 experiments have been rather modest in terms of number of images and number of subjects. We report the results of systematic and extensive ....

M. A. Turk. Interactive-Time Vision: Face Recognition as a Visual Behavior. PhD thesis, Massachusetts Institute of Technology, School of Architecture and Planning, September 1991.

....pour identifier les visages sont alors obtenues par des calculs de correlation entre les regions. D autres methodes utilisent une analyse en composantes principales realisee a partir de l information pixel, pour rechercher une base de representation permettant de discriminer les visages [1] 2] [15]. Le systeme de reconnaissance de visage, que nous presentons, s inscrit dans le cadre du projet AMIBE, un des projets de recherche du PRC Communication Homme Machine, qui se propose d experimenter une interface multimodale homme machine integrant le son et l image pour un nombre limite ....

M. Turk. Interactive-time vision: face recognition as a visual behavior. PhD thesis, Massachusetts Institute of Technology, September 1991.

....assist in the task of remembering faces, through the use of computer induced flashbacks. In addition to helping the human remember, and therefore recognize, faces, computers are also capable of directly recognizing faces. Previous work by others is based on using a fixed, tethered camera [35] 36][37][38] The kinds of applications for this work might include video surveillance with a fixed camera and people moving through its field of view. The FBI funded FERET project comprises a large database (more than 7000 faces) that can be searched quickly on a workstation class system. Automatic face ....

Matthew A. Turk. Interactive-Time Vision: Face Recognition as a Visual Behavior. PhD dissertation, MIT, Media Arts and Sciences Section. Advisor: A.P. Pentland.

....[13] The pixel approach is a global one that requires few knowledge about face geometry. Some studies are linked to pattern matching: the measures used to identify faces are correlations between template regions. Other methods use principal component analysis applied on pixel s grey level values [12]. The application, described in this paper, is a system similar to an automatic cash machine withdrawal where the user identifies himself by using a credit card with a secret code. It is possible to enhance the security of such a transaction by verifying that the observed face is identical to a ....

M.Turk. Interactive-time vision: face recognition as a visual behavior. PhD thesis, Massachusetts Institute of Technology, September 1991.

....requiring the response of the participants to be both meaningful and timely. As with other perceptual components (e.g. speech recognition and natural language understanding) vision must be reliable and fast, relative to the tasks at hand. These constraints characterize interactive time vision [2] routines, which have the following properties: Fast This is defined by context; some visual events must be handled more rapidly than others. For example, interpreting user motion to control a pointing device needs to be done at a higher rate than interpreting a gesture to signal goodbye . ....

....is positioned close to the monitor, so that looking at the animated character can be approximated by looking at the camera. Given a valid head location, the eyes are located using a local correlation (with eigeneyes ) and then classified as looking straight ahead , left , or right , as in [2]. 5. Integration The routines described in the preceding section are a sample of our ongoing development of visual routines, and a small subset of the routines that may be useful in general interaction with a lifelike character. In this section we briefly describe the control structure that ....

M. Turk, Interactive-Time Vision: Face Recognition as a Visual Behavior, Ph.D. Thesis, MIT Media Lab, Sept. 1991.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC