Abstract: A system and method for estimating a set of landmarks for a large image ensemble employs only a small number of manually labeled images from the ensemble and avoids labor-intensive and error-prone object detection, tracking and alignment learning task limitations associated with manual image labeling techniques. A semi-supervised least squares congealing approach is employed to minimize an objective function defined on both labeled and unlabeled images. A shape model is learned on-line to constrain the landmark configuration. A partitioning strategy allows coarse-to-fine landmark estimation.

Abstract: A novel technique for performing video matting, which is built upon a proposed image matting algorithm that is fully automatic is disclosed. The disclosed methods utilize a PCA-based shape model as a prior for guiding the matting process, so that manual interactions required by most existing image matting methods are unnecessary. By applying the image matting algorithm to these foreground windows, on a per frame basis, a fully automated video matting process is attainable. The process of aligning the shape model with the object is simultaneously optimized based on a quadratic cost function.

Abstract: An advertising system is disclosed. In one embodiment, the system includes an advertising station including a display and configured to provide advertising content to potential customers via the display and one or more cameras configured to capture images of the potential customers when proximate to the advertising station. The system may also include a data processing system to analyze the captured images to determine gaze directions and body pose directions for the potential customers, and to determine interest levels of the potential customers in the advertising content based on the determined gaze directions and body pose directions. Various other systems, methods, and articles of manufacture are also disclosed.

Abstract: A method for image alignment is disclosed. In one embodiment, the method includes acquiring a facial image of a person and using a discriminative face alignment model to fit a generic facial mesh to the facial image to facilitate locating of facial features. The discriminative face alignment model may include a generative shape model component and a discriminative appearance model component. Further, the discriminative appearance model component may have been trained to estimate a score function that minimizes the angle between a gradient direction and a vector pointing toward a ground-truth shape parameter. Additional methods, systems, and articles of manufacture are also disclosed.

Abstract: The present invention aims at providing a method for detecting a signal structure from a moving vehicle. The method for detecting signal structure includes capturing an image from a camera mounted on the moving vehicle. The method further includes restricting a search space by predefining candidate regions in the image, extracting a set of features of the image within each candidate region and detecting the signal structure accordingly.

Abstract: A method for face model fitting comprising, receiving a first observed image, receiving a second observed image, and fitting an active appearance model of a third image to the second observed image and the first observed image with an algorithm that includes a first function of a mean-square-error between a warped image of the second observed image and a synthesis of the active appearance model and a second function of a mean-square-error between the warped image of the second observed image and an appearance data of the first observed image.

Abstract: The system and method disclosed herein provides an integrated and automated workflow, sensor, and reasoning system that automatically detects breaches in protocols, appropriately alarms and records these breaches, facilitates staff adoption of protocol adherence, and ultimately enables the study of protocols for care comparative effectiveness. The system provides real-time alerts to medical personnel in the actual processes of care, thereby reducing the number of negative patient events and ultimately improving staff behavior with respect to protocol adherence.

Abstract: There is provided a discriminative framework for image alignment. Image alignment is generally the process of moving and deforming a template to minimize the distance between the template and an image. There are essentially three elements to image alignment, namely template representation, distance metric, and optimization method. For template representation, given a face dataset with ground truth landmarks, a boosting-based classifier is trained that is able to learn the decision boundary between two classes—the warped images from ground truth landmarks (e.g., positive class) and those from perturbed landmarks (e.g., negative class). A set of trained weak classifiers based on Haar-like rectangular features determines a boosted appearance model. A distance metric is a score from the strong classifier, and image alignment is the process of optimizing (e.g., maximizing) the classification score.

Abstract: A method and system for distributed tracking of multiple targets is disclosed. Multiple targets to be tracked by a plurality of trackers are detected in a frame. The motion state variable of each of the plurality of trackers is calculated in the E-step of a variational Expectation-Maximization algorithm. Further, the data association variable of each of the plurality of trackers is calculated in the M-step of the algorithm. Depending on the motion state variable and the data association variable, the multiple targets are tracked.

Abstract: A system and method for performing a facial image restoration is described. The system includes an active appearance model component for fitting an active appearance model to a facial image found in each of a plurality of video frames, a registration component for registering each pixel of each facial image with comparable pixels of each of the other facial images, and a restoration component for producing a restored facial image from the facial images. The method includes fitting an active appearance model to a facial image found in each of a plurality of video frames, registering each pixel of each said facial image with comparable pixels of each of the other facial images, and producing a restored facial image from the facial images.

Abstract: A method of producing an enhanced Active Appearance Model (AAM) by combining images of multiple resolutions is described herein. The method generally includes processing a plurality of images each having image landmarks and each image having an original resolution level. The images are down-sampled into multiple scales of reduced resolution levels. The AAM is trained for each image at each reduced resolution level, thereby creating a multi-resolution AAM. An enhancement technique is then used to refine the image landmarks for training the AAM at the original resolution level. The landmarks for training the AAM at each level of reduced resolution is obtained by scaling the landmarks used at the original resolution level by a ratio in accordance with the multiple scales.

Abstract: Embodiments of the invention include a system and a method for determining whether a person is carrying concealed contraband, such as an improvised explosives device or other weapon. The system includes a people tracking video subsystem, a people tracking decisioning subsystem, a concealed contraband detection aiming subsystem, and a concealed contraband detection decisioning subsystem.

Abstract: A technique for optimizing object recognition is disclosed. The technique includes receiving at least one image of an object and at least one reference image. The technique further includes identifying at least one performance metric corresponding to an object recognition task. The identified performance metric is optimized to generate the corresponding optimized performance metric by determining an optimal subspace based on a determined objective function corresponding to the object recognition task and a difference between the received image and the corresponding reference image. Subsequently, the technique includes comparing the received image with the reference image based on the optimized performance metric for performing the object recognition task.

Abstract: A system and method for estimating a set of landmarks for a large image ensemble employs only a small number of manually labeled images from the ensemble and avoids labor-intensive and error-prone object detection, tracking and alignment learning task limitations associated with manual image labeling techniques. A semi-supervised least squares congealing approach is employed to minimize an objective function defined on both labeled and unlabeled images. A shape model is learned on-line to constrain the landmark configuration. A partitioning strategy allows coarse-to-fine landmark estimation.

Abstract: A method for re-identifying an image is provided. The method comprises obtaining a plurality of images and generating a correspondence map between the plurality of images. The method further comprises defining a plurality of region signatures for one or more regions comprising the plurality of images and comparing the plurality of images based on the correspondence map and the plurality of region signatures to perform image re-identification.

Abstract: A system, method and apparatus for performing a facial approximation is described. The system includes an acquisition subsystem and a facial approximation algorithm. The method includes the steps of acquiring models of known skulls and a model of a questioned skull, comparing the models of the known skulls with the model of the questioned skull, and removing variation in the facial structure of the questioned skull due to skeletal variation between the known skulls and the questioned skull. The apparatus includes a bony structure software component, a bony structure warping software component, and a soft tissue software component.

Abstract: The present invention aims at providing a method for detecting a signal structure from a moving vehicle. The method for detecting signal structure includes capturing an image from a camera mounted on the moving vehicle. The method further includes restricting a search space by predefining candidate regions in the image, extracting a set of features of the image within each candidate region and detecting the signal structure accordingly.

Abstract: Embodiments of the invention include a security checkpoint system that has a camera configured for obtaining a first photographic image of an individual, a photographic image scanner configured for scanning a second photographic image, and a comparator mechanism for comparing the first photographic image with the second photographic image to ascertain whether the second photographic image is of the individual. Other embodiments include a method for automatedly developing security-related characteristics for an individual.

Abstract: A gaze estimation method and system, the method including capturing a video sequence of images with an image capturing system, designating at least one landmark in a head portion of the captured video sequence, fitting a virtual model of the head portion to the actual head portion in the captured video sequence, and determining the gaze estimation.

Abstract: A method for face model fitting comprising, receiving a first observed image, receiving a second observed image, and fitting an active appearance model of a third image to the second observed image and the first observed image with an algorithm that includes a first function of a mean-square-error between a warped image of the second observed image and a synthesis of the active appearance model and a second function of a mean-square-error between the warped image of the second observed image and an appearance data of the first observed image.