Abstract: Systems and methods perform Laplacian Principal Components Analysis (LPCA). In one implementation, an exemplary system receives multidimensional data and reduces dimensionality of the data by locally optimizing a scatter of each local sample of the data. The optimization includes summing weighted distances between low dimensional representations of the data and a mean. The weights of the distances can be determined by a coding length of each local data sample. The system can globally align the locally optimized weighted scatters of the local samples and provide a global projection matrix. The LPCA improves performance of such applications as face recognition and manifold learning.

Abstract: Systems and methods of segmenting images are disclosed herein. The similarity of images in a set of images is compared. A group of images is selected from the set of images. The images in the group of images are selected based on compared similarities among the images. An informative image is selected from the group of images. User-defined semantic information of the informative image is received. The group of images as a graph is modeled as a graph. Each image in the group of images denotes a node in the graph. Edges of the graph denote a foreground relationship between images or a background relationship between images. One or more images in the group of images are automatically segmented by propagating the semantic information of the informative image to images in the group of images having a corresponding graph node that is related to a graph node corresponding to the informative image. Segmentation results can be refined according to user provided image semantics.

Abstract: Digital video effects are described. In one aspect, a foreground object in a video stream is identified. The video stream comprises multiple image frames. The foreground object is modified by rendering a 3-dimensional (3-D) visual feature over the foreground object for presentation to a user in a modified video stream. Pose of the foreground object is tracked in 3-D space across respective ones of the image frames to identify when the foreground object changes position in respective ones of the image frames. Based on this pose tracking, aspect ratio of the 3-D visual feature is adaptively modified and rendered over the foreground object in corresponding image frames for presentation to the user in the modified video stream.

Abstract: Tensor linear Laplacian discrimination for feature extraction is disclosed. One embodiment comprises generating a contextual distance based sample weight and class weight, calculating a within-class scatter using the at least one sample weight and a between-class scatter for multiple classes of data samples in a sample set using the class weight, performing a mode-k matrix unfolding on scatters and generating at least one orthogonal projection matrix.

Abstract: Systems and methods are described for a face annotation framework with partial clustering and interactive labeling. In one implementation, an exemplary system automatically groups some images of a collection of images into clusters, each cluster mainly including images that contain a person's face associated with that cluster. After an initial user-labeling of each cluster with the person's name or other label, in which the user may also delete/label images that do not belong in the cluster, the system iteratively proposes subsequent clusters for the user to label, proposing clusters of images that when labeled, produce a maximum information gain at each iteration and minimize the total number of user interactions for labeling the entire collection of images.

Abstract: This disclosure describes an integrated framework for class-unsupervised object segmentation. The class-unsupervised object segmentation occurs by integrating top-down constraints and bottom-up constraints on object shapes using an algorithm in an integrated manner. The algorithm describes a relationship among object parts and superpixels. This process forms object shapes with object parts and oversegments pixel images into the superpixels, with the algorithm in conjunction with the constraints. This disclosure describes computing a mask map from a hybrid graph, segmenting the image into a foreground object and a background, and displaying the foreground object from the background.

Abstract: Systems and methods for space-time video montage are described. In one aspect, one or more arbitrary space-time volumes representing informative video portion(s) of at least one input video data sequence are identified. A video summary representing a montage of the at least one input video data sequence is generated for presentation to user from the one or more arbitrary space-time volumes.

Abstract: This disclosure describes an integrated framework for class-unsupervised object segmentation. The class-unsupervised object segmentation occurs by integrating top-down constraints and bottom-up constraints on object shapes using an algorithm in an integrated manner. The algorithm describes a relationship among object parts and superpixels. This process forms object shapes with object parts and oversegments pixel images into the superpixels, with the algorithm in conjunction with the constraints. This disclosure describes computing a mask map from a hybrid graph, segmenting the image into a foreground object and a background, and displaying the foreground object from the background.

Abstract: Described is using semi-Riemannian geometry in supervised learning to learn a discriminant subspace for classification, e.g., labeled samples are used to learn the geometry of a semi-Riemannian submanifold. For a given sample, the K nearest classes of that sample are determined, along with the nearest samples that are in other classes, and the nearest samples in that sample's same class. The distances between these samples are computed, and used in computing a metric matrix. The metric matrix is used to compute a projection matrix that corresponds to the discriminant subspace. In online classification, as a new sample is received, it is projected into a feature space by use of the projection matrix and classified accordingly.

Abstract: Exemplary systems and methods use micro-structure modeling of an image for extracting image features. The micro-structure in an image is modeled as a Markov Random Field, and the model parameters are learned from training images. Micro-patterns adaptively designed from the modeled micro-structure capture spatial contexts of the image. In one implementation, a series of micro-patterns based on the modeled micro-structure can be automatically designed for each block of the image, providing improved feature extraction and recognition because of adaptability to various images, various pixel attributes, and various sites within an image.

Abstract: A method for modeling data affinities and data structures. In one implementation, a contextual distance may be calculated between a selected data point in a data sample and a data point in a contextual set of the selected data point. The contextual set may include the selected data point and one or more data points in the neighborhood of the selected data point. The contextual distance may be the difference between the selected data point's contribution to the integrity of the geometric structure of the contextual set and the data point's contribution to the integrity of the geometric structure of the contextual set. The process may be repeated for each data point in the contextual set of the selected data point. The process may be repeated for each selected data point in the data sample. A digraph may be created using a plurality of contextual distances generated by the process.

Abstract: An efficient, effective and at times superior object detection and/or recognition (ODR) function may be built from a set of Bayesian stumps. Bayesian stumps may be constructed for each feature and object class, and the ODR function may be constructed from the subset of Bayesian stumps that minimize Bayesian error for a particular object class. That is, Bayesian error may be utilized as a feature selection measure for the ODR function. Furthermore, Bayesian stumps may be efficiently implemented as lookup tables with entries corresponding to unequal intervals of feature histograms. Interval widths and entry values may be determined so as to minimize Bayesian error, yielding Bayesian stumps that are optimal in this respect.

Abstract: Methods for detecting a salient object in an input image are described. For this, the salient object in an image may be defined using a set of local, regional, and global features including multi-scale contrast, center-surround histogram, and color spatial distribution. These features are optimally combined through conditional random field learning. The learned conditional random field is then used to locate the salient object in the image. The methods can also use image segmentation, where the salient object is separated from the image background.

Abstract: A search includes comparing a query image provided by a user to a plurality of stored images of faces stored in a stored image database, and determining a similarity of the query image to the plurality of stored images. One or more resultant images of faces, selected from among the stored images, are displayed to the user based on the determined similarity of the stored images to the query image provided by the user. The resultant images are displayed based at least in part on one or more facial features.

Abstract: A Poisson-quantization noise model for modeling noise in low-light conditions is described. In one aspect, image information is received. A Poisson-quantization noise model is then generated from a Poisson noise model and a quantization noise model. Poisson-quantization noise is then estimated in the image information using the Poisson-quantization noise model.

Abstract: The present video tracking technique outputs a Maximum A Posterior (MAP) solution for a target object based on two object templates obtained from a start and an end keyframe of a whole state sequence. The technique first minimizes the whole state space of the sequence by generating a sparse set of local two-dimensional modes in each frame of the sequence. The two-dimensional modes are converted into three-dimensional points within a three-dimensional volume. The three-dimensional points are clustered using a spectral clustering technique where each cluster corresponds to a possible trajectory segment of the target object. If there is occlusion in the sequence, occlusion segments are generated so that an optimal trajectory of the target object can be obtained.

Abstract: A flash-based strategy is used to separate foreground information from background information within image information. In this strategy, a first image is taken without the use of flash. A second image is taken of the same subject matter with the use of flash. The foreground information in the flash image is illuminated by the flash to a much greater extent than the background information. Based on this property, the strategy applies processing to extract the foreground information from the background information. The strategy supplements the flash information by also taking into consideration motion information and color information.

Abstract: Systems and methods perform automatic 3D face modeling. In one implementation, a brief video clip of a user's head turning from front to side provides enough input for automatically achieving a model that includes 2D feature matches, 3D head pose, 3D face shape, and facial textures. The video clip of the user may be of poor quality. In a two layer iterative method, the video clip is divided into segments. Flow-based feature estimation and model-based feature refinement are applied recursively to each segment. Then the feature estimation and refinement are iteratively applied across all the segments. The entire modeling method is automatic and the two layer iterative method provides speed and efficiency, especially when sparse bundle adjustment is applied to boost efficiency.

Abstract: A search includes comparing a query image provided by a user to a plurality of stored images of faces stored in a stored image database, and determining a similarity of the query image to the plurality of stored images. One or more resultant images of faces, selected from among the stored images, are displayed to the user based on the determined similarity of the stored images to the query image provided by the user. The resultant images are displayed based at least in part on one or more facial features.

Abstract: Exemplary systems and methods segment a foreground from a background image in a video sequence. In one implementation, a system refines a segmentation boundary between the foreground and the background image by attenuating background contrast while preserving contrast of the segmentation boundary itself, providing an accurate background cut of live video in real time. A substitute background may then be merged with the segmented foreground within the live video. The system can apply an adaptive background color mixture model to improve segmentation of foreground from background under various background changes, such as camera movement, illumination change, and movement of small objects in the background.