Mitsubishi Electric Research Laboratories, Inc.

Mitsubishi Electric Research Labs.

Other

Massachusetts Institute of Technology

Baback Moghaddam

Hanspeter Pfister

Jinho Lee

Raghu Machiraju

William T Freeman

Paul A Beardsley

Chia Shen

Alex Paul Pentland

Ryan Scott Bardsley

Neal B Lesh

Henning Biermann

Egon C Pasztor

Ming-Hsuan Yang

Qi Tian

Xiang S Zhou

Dimitris Margaritis

Features are extracted from a test and reference image to generate a test and reference record. Each feature has a location, and orientation, and furthermore, the features of the reference records also have associated weights. The features of the test record are approximately aligned with the features of the reference record. Then, differences between the locations and orientations of the features of the reference record and the features of the test record are measured, and the weights of all features of the reference record that are less than a predetermined difference when compared with the features of the test record are summed to determine a similarity score that the test record matches the reference record.

Method for comparing features extracted from images of fingerprints

A method recognizes a face in an image. A morphable model having shape and pose parameters is fitted to a face in an image to construct a three-dimensional model of the face. Texture is extracted from the face in the image using the three-dimensional model. The shape and texture are projected into a bilinear illumination model to generate illumination bases for the face in the image. The illumination bases for the face in the image are compared to illumination bases of each of a plurality of bilinear illumination models of known faces to identify the face in the image.

Bilinear illumination model for robust face recognition

A method generates a three-dimensional, bi-linear, illumination model for arbitrary faces. A large number of images are acquired of many different faces. For each face, multiple images are acquired with varying poses and varying illumination. A three-mode singular value decomposition is applied to the images to determine parameters of the model. The model can be fit to a probe image of an unknown face. Then, the model can be compared with models of a gallery of images of unknown faces to recognize the face in the probe image.

Method and system for generating bi-linear models for faces

A method determines an optimal set of viewpoints to acquire a 3D shape of a face. A view-sphere is tessellated with a plurality of viewpoint cells. The face is at an approximate center of the view-sphere. Selected viewpoint cells are discarded. The remaining viewpoint cells are clustered to a predetermined number of viewpoint cells according to a silhouette difference metric. The predetermined number of viewpoint cells are searched for a set of optimal viewpoint cells to construct a 3D model of the face.

Method for determining optimal viewpoints for 3D face modeling and face recognition

A method determines a direction of a principal light source in an image. An input image I is acquired of an object illuminated by a principal light source from an unknown direction. The input image includes an array of pixels, and each pixel has an intensity I(x, y). An intensity vector {right arrow over (I)} is constructed from the intensities of the input image. An albedo map &#x3c1; is defined for the object. An albedo vector {right arrow over (&#x3c1;)} is constructed from the albedo map. A shape matrix N is generated for the object. The albedo vector {right arrow over (&#x3c1;)} is multiplied by the shape matrix N to obtain a shape-albedo matrix A. Then, a direction s* to the principal light source is estimated from the intensity vector {right arrow over (I)}, the albedo vector {right arrow over (&#x3c1;)} and the shape-albedo matrix A according to an optimization 

Face relighting for normalization of directional lighting

A method reconstructs or synthesizes heads from 3D models of heads and 2D silhouettes of heads. A 3D statistical model is generated from multiple real human heads. The 3D statistical model includes a model parameter in the form of basis vectors and corresponding coefficients. Multiple 2D silhouettes of a particular head are acquired using a camera for example. The 3D statistical model is fitted to multiple 2D silhouettes to determine a particular value of the model parameter corresponding to the plurality of 2D silhouettes. Then, the 3D statistical model is rendered according to the particular value of the model parameter to reconstruct the particular head.

Constructing heads from 3D models and 2D silhouettes

A method learns a binary classifier for classifying samples into a first class and a second class. First, a set of training samples is acquired. Each training sample is labeled as either belonging to the first class or to the second class. Pairs of dyadic samples are connected by projection vectors such that a first sample of each dyadic pair belonging to the first class and a second sample of each dyadic pair belonging to the second class. A set of hyperplanes are formed so that the hyperplanes have a surface normal to the projection vectors. One hyperplane from the set of hyperplanes is selected that minimizes a weighted classification error. The set of training samples is then weighted according to a classification by the selected hyperplane. The selected hyperplanes are combined into a binary classifier, and the selecting, weighting, and combining are repeated a predetermined number of iterations to obtain a final classifier for classifying test samples into the first and second classes.

Classification with boosted dyadic kernel discriminants

A method classifies images of faces according to gender. Training images of male and female faces are supplied to a vector support machine. A small number of support vectors are determined from the training images. The support vectors identify a hyperplane. After training, a test image is supplied to the support vector machine. The test image is classified according to the gender of the test image with respect to the hyperplane.

Gender classification with support vector machines

A method for visualizing multimedia objects assigns a feature vector to each multimedia object. The feature vector of each multimedia object is reduced to a location vector having a dimensionality of a display device. A cost function is evaluated to determine an optimal location vector for each multimedia object, and each multimedia object is displayed on a display device according to the optimal location vector. The reducing can use principle component analysis. In addition, a relevance score can be determined for each displayed multimedia object, and the multimedia objects can than be visually enhanced according to the relevance score.

Content-based visualization and user-modeling for interactive browsing and retrieval in multimedia databases

A method for representing an image in an image retrieval database first separates and filters images to extract color and texture features. The color and texture features of each image are partitioned into a plurality of blocks. A joint distribution of the color features and a joint distribution of the texture features are estimated for each block. The estimated joint distributions are stored in the database with each image to enable retrieval of the images by comparing the estimated joint distributions.

Method for image retrieval with multiple regions of interest

A system enables multiple users to interact with a picture presentation. The system includes a display surface having a horizontal orientation, preferably circular. A processor is configured to composite an image. The composite image includes a picture display area, an orientation area, and a plurality of control panels. There is one control panel for each of the users. A database, coupled to the processor, stores annotated pictures. Selected annotated pictures are to be composited into the picture display area of the displayed image. The pictures are selected using the control panel. A display device, coupled to the processor, displays the composite image on the display surface, and an input device is used to interact with the control panels, the orientation area, and the annotated pictures to enable the users to concurrently control the compositing of the sequence of images.

Multi-user interactive picture presentation system and method

A method infers a scene from a test image. During a training phase, a plurality of images and corresponding scenes are acquired. Each of the images and corresponding scenes are partitioned respectively into a plurality of image patches and scene patches. Each image patch is represented as an image vector, and each scene patch is represented as a scene vector. The image vectors and scene vectors are modeled as a network. During an inference phase, the test image is acquired. The test image is partitioned into a plurality of test image patches. Each test image patch is represented as a test image vector. Candidate scene vectors corresponding to the test image vectors are located in the network. Compatibility matrices for the candidate scene vectors are determined, and probabilities of the compatibility matrices are propagated in the network until convergence to infer the scene from the test image.

Method for inferring scenes from test images and training data using probability propagation in a markov network

Methods and apparatus for detecting instances of a selected object or object feature in a digitally represented scene utilize analysis of probability densities to determine whether an input image (or portion thereof) represents such an instance. The invention filters images of objects that, although in some ways similar to the object under study, fail to qualify as typical instances of that object. The invention is useful in the detection and recognition of virtually any multifeatured entity such as human faces, features thereof (e.g., eyes), as well as non-rigid and articulated objects such as human hands.

Growing community of inventors

Cambridge, MA, United States of America

Baback Moghaddam