Abstract: A system and method to facilitate pattern recognition or matching between patterns are disclosed that is substantially invariant to small transformations. A substantially smooth deformation field is applied to a derivative of a first pattern and a resulting deformation component is added to the first pattern to derive a first deformed pattern. An indication of similarity between the first pattern and a second pattern may be determined by minimizing the distance between the first deformed pattern and the second pattern with respect to deformation coefficients associated with each deformed pattern. The foregoing minimization provides a system (e.g., linear) that may be solved with standard methods.

Abstract: A simplified general model and an associated estimation algorithm is provided for modeling visual data such as a video sequence. Specifically, images or frames in a video sequence are represented as collections of flat moving objects that change their appearance and shape over time, and can occlude each other over time. A statistical generative model is defined for generating such visual data where parameters such as appearance bit maps and noise, shape bit-maps and variability in shape, etc., are known. Further, when unknown, these parameters are estimated from visual data without prior pre-processing by using a maximization algorithm. By parameter estimation and inference in the model, visual data is segmented into components which facilitates sophisticated applications in video or image editing, such as, for example, object removal or insertion, tracking and visual surveillance, video browsing, photo organization, video compositing, etc.

Abstract: The present invention provides a method of constructing recognition models. Under the method, a set of probabilities is estimated for values of a hidden variable. A Fourier transform is determined for the set of probabilities and is used to determine a Fourier transform of an estimated prototype pattern. The inverse Fourier transform is then determined for the Fourier transform of the estimated prototype pattern to form an estimated prototype pattern.

Abstract: A model characterizes an error pattern that is functionally related to first and second patterns and to one or more model parameters, which may be unknown. The error pattern may be derived by deforming one or both of the first and second patterns, such as by applying a generally smooth, non-uniform deformation field. A likelihood for the model that the error pattern is zero, given the second pattern, is determined. If the model parameter(s) is unknown, the likelihood may be used to estimate (or infer) the parameter(s) that tend to maximize the likelihood for a plurality of stored patterns. The estimated parameters may, in turn, be employed to determine the likelihood as a measure of similarity between an observed pattern and the patterns that the model is capable of generating. In addition, the likelihood may be used to classify an observed pattern according to the likelihood that the observed pattern has relative to one or more models.

Abstract: Methods, systems, devices and/or storage media for passwords. An exemplary method tiles an image, associates an index with each tile and optionally determines offsets for select tiles. Further, the tiling optionally relies on probability and/or entropy. An exemplary password system includes an image; a grid associated with the image, the grid composed of polygons; an index associated with each polygon; and an offset associated with each polygon wherein password identification relies on one or more indices and one or more offsets.

Abstract: The present invention is embodied in a system and method for digitally tracking objects in real time. The present invention visually tracks three-dimensional (3-D) objects in dense disparity maps in real time. Tracking of the human body is achieved by digitally segmenting and modeling different body parts using statistical models defined by multiple size parameters, position and orientation. In addition, the present invention is embodied in a system and method for recognizing mutual occlusions of body parts and filling in data for the occluded parts while tracking a human body. The body parts are preferably tracked from frame to frame in image sequences as an articulated structure in which the body parts are connected at the joints instead of as individual objects moving and changing shape and orientation freely.

Abstract: A system and method facilitating object tracking is provided. The invention includes an audio model that receives at least two audio input signals and a video model that receives a video input. The audio model and the video model employ probabilistic generative models which are combined to facilitate object tracking. Expectation maximization can be employed to modify trainable parameters of the audio model and the video model.

Abstract: The present invention relates includes system and a method for automatically generating short segments of video (or video “cliplets”) from a larger source video. A cliplet has the properties that its length is determined prior to generation and that the cliplet ideally is semantically meaningful and contains a single short event or theme. Generally, the cliplet generation method processes a large source video and generates cliplet results for presentation (such as to a user). Specifically, the method processes the source video to determine editing points and then extracts cliplets from the source video based on the editing points. The extracted cliplets can overlap in time. Cliplet results then are presented, such as to a user. The cliplet generation system includes a video cliplet generator that processes a large source video and generates cliplets in accordance with the cliplet generation method.