Istituto Trentino Di Cultura

Massachusetts Institute of Technology

Instituto Trentino Di Cultura

Roberto Brunelli

Tomaso A Poggio

Luigi Stringa

Ornella Mich

Daniele Falavigna

In a method of storing and retrieving images of people, for example, in photographic archives and for the construction of identikit images, each characteristic (or feature) of the images to be stored is associated with a region the size of which corresponds to the average size of the feature in the images stored. If {F.sub.i }.sub.i=1 . . . , N is a set of images of the feature, where F.sub.i is the image associated with each of the N people in the data base, on the basis of these images, a new set of images {.PHI..sub.j }.sub.j=0, 1, . . . N of the type ##EQU1## is generated, of which a subset {.PHI.}.sub.i=0 . . . K can be used to approximate, encode, compare and construct images of the type in question in an interactive manner. The method is particularly applicable to techniques for searching photographic archives and for the construction of identikit images.

Method of storing and retrieving images of people, for example, in

A memory based computer graphic animation system generates desired images and image sequences from 2-D views. The 2-D views provide sparse data from which intermediate views are generated based on a generalization and interpolation technique of the invention. This technique is called a Hyper Basis function network and provides a smooth mapping between the given set of 2-D views and a resulting image sequence for animating a subject in a desired movement. A multilayer network provides learning of such mappings and is based on Hyper Basis Functions (HBF's). A special case of the HBFs is the radial basis function technique used in a preferred embodiment. The invention generalization/integration technique involves establishing working axes along which different views of the subject are taken. Different points along the working axes define different positions (geometrical and/or graphical) of the subject. For each of these points, control points for defining a view of the subject are either given or calculated by interpolation/generalization of the present invention.

Memory based method and apparatus for computer graphics

An integrated, multisensory recognition (identification and verification) system is described. Acoustic features and visual features are integrated in order to identify people or to verify their identities. The integration of the speaker-identification and visual-features-identification functions improves both performance and reliability in the applications envisaged. Various architectures are described for the implementation both of the integration function and of the speaker-recognition and visual-features-recognition functions.

Growing community of inventors

Trento, Italy

Roberto Brunelli