Viisage Technology, Inc.

I-tek, Inc.

Lau Technologies

Dennis C Ehn

Francis John Cusack, Jr

Thomas M Kuzeja

Jay F Bortolussi

Michael S Saulnier

Denis K Berube

Methods and systems for identifying an individual are provided. The systems and methods make use of principal component analysis and account for intra-individual variation by utilizing a plurality of images obtained from a stream of data representing a plurality of images of the individual. To identify the individual the system and method account for the intra-individual variation in the stream of data to produce a compensated representation of the individual. The system and method and to match the compensated representation a representation from a reference database to identify the individual.

System and method for image recognition using stream data

A method and system are disclosed for producing a reduced-glare image. The method and system use at least two light sources located a selected distance apart from each other. An image acquisition device acquires a first image of an object using illumination from the first light source, but not the second. Then the image acquisition device acquires a second image of the object using illumination from the second light source, but not the first. The two images, having glare at different pixel locations, are then used to form a reduced-glare image.

Systems and methods for forming a reduced-glare image

A system and method for acquiring, processing, and comparing an image with a stored image to determine if a match exists. In particular, the system refines the image data associated with an object based on pre-stored color values, such as flesh tone color. The system includes a storage element for storing flesh tone colors of a plurality of people, and a defining stage for localizing a region of interest in the image. A combination stage combines the unrefined region of interest with one or more pre-stored flesh tone colors to refine the region of interest based on color. This flesh tone color matching ensures that at least a portion of the image corresponding to the unrefined region of interest having flesh tone color is incorporated into the refined region of interest. Hence, the system can localize the head, based on the flesh tone color of the skin of the face in a rapid manner. According to one practice, the refined region of interest is smaller than or about equal to the unrefined region of interest.

Real-time facial recognition and verification system

A technique for reproducing an image in a set of grey scale steps is disclosed including: providing a plurality of superpixels for providing an output representative of an image; providing a set of threshold levels for each pixel in a superpixel, which set is different from each of the sets of threshold levels of the other pixels in that superpixel and different from the set of greyscale steps; identifying the position of a given pixel in a superpixel and designating a particular set of threshold levels corresponding to the position of that given pixel; comparing the output of the given pixel with its particular set of threshold levels; and indicating the greyscale step in the set of greyscale steps in response to the output of the given pixel equal to or in excess of at least one of the threshold levels in the set of threshold levels corresponding to that pixel position.

Growing community of inventors

Newton, MA, United States of America

Dennis C Ehn