Abstract: Unsupervised learning of object category from images is carried out by using an automatic image recognition system. A plurality of training images are automatically analyzed using an interest operator which produces an indication of features. Those features are clustered using a vector guantizer. The model is learned from the features using expectation maximization to assess a joint probability of which features are most relevant.

Abstract: A system and method of determining 3D information about a 3D scene using shadows that are cast on the 3D object.

Abstract: A method and system provide the ability to automatically recognize biological particles. An image of biological particles (e.g., airborne pollen or urine) is obtained. One or more parts of the image are detected as containing one or more particles of interest. Feature vector(s) are extracted from each detected part of the image. Non-linearities are applied to each feature vector. Each part of the image is then classified into a category of biological particle based on the one or more feature vectors for each part of the image.

Abstract: A method and apparatus for determining the relevance of images retrieved from a database relative to a specified visual object category. The method comprises transforming a visual object category into a model defining features of the visual object category and a spatial relationship therebetween, storing the model, comparing a set of images identified during the database search with the stored model, calculating a likelihood value relating to each image based on its correspondence with the model, and ranking the images in order of the respective likelihood values. The apparatus comprises a processor for transforming a visual object category into a model defining features of the visual object category and a spatial relationship therebetween.

Abstract: The present invention relates to a system and method for attentional selection. More specifically, the present invention relates to a system and method for the automated selection and isolation of salient regions likely to contain objects, based on bottom-up visual attention, in order to allow unsupervised one-shot learning of multiple objects in cluttered images.

Abstract: A system for processing handwriting that uses an ordinary camera as an image input device. The output of a single camera is used to produce a probability function that indicates the likelihood of whether the pen is touching the paper. The function uses clues including ink on the page and/or shadows. Another embodiment uses both pen up and pen down information to dynamically time warp-fit the information to fit it to a template.

Abstract: The present invention provides a technique for acquiring motion samples, labeling motion samples with labels based on a plurality of parameters, using the motion samples and the labels to learn a function that maps labels to motions generally, and using the function to synthesize arbitrary motions. The synthesized motions may be portrayed through computer graphic images to provide realistic animation. The present invention allows the modeling of labeled motion samples in a manner that can accommodate the synthesis of motion of arbitrary location, speed, and style. The modeling can provide subtle details of the motion through the use of probabilistic sub-modeling incorporated into the modeling process. Motion samples may be labeled according to any relevant parameters. Labels may be used to differentiate between different styles to yield different models, or different styles of a motion may be consolidated into a single baseline model with the labels used to embellish the baseline model.

Abstract: Unsupervised learning of object category from images is carried out by using an automatic image recognition system. A plurality of training images are automatically analyzed using an interest operator which produces an indication of features. Those features are clustered using a vector quantizer. The model is learned from the features using expectation maximization to assess a joint probability of which features are most relevant.

Abstract: A technique for capturing the surface of three-dimensional (“3D”) objects using structured lighting. The movement of shadow across the 3D objects is optically recorded. Variation in brightness on the surface provides a cue for triangulation. By analyzing the variation in brightness of a particular point on the surface, the location of that point is determined based on the movement of the shadow. With known locations for a camera and a light source, the coordinates in space of the point is triangulated. By repeating this process, a collection of coordinates is created. Those coordinates are then used to reconstruct the 3D surface.

Abstract: A system for processing handwriting that uses an ordinary camera as an image input device. The output of a single camera is used to produce a probability function that indicates the likelihood of whether the pen is touching the paper. The function uses clues including ink on the page and/or shadows. Another embodiment uses both pen up and pen down information to dynamically time warp-fit the information to fit it to a template.

Abstract: A system and method of determining 3D information about a 3D scene using shadows that are cast on the 3D object.

Abstract: A technique for capturing the surface of three-dimensional (“3D”) objects using structured lighting. The movement of shadow across the 3D objects is optically recorded. Variation in brightness on the surface provides a cue for triangulation. By analyzing the variation in brightness of a particular point on the surface, the location of that point is determined based on the movement of the shadow. With known locations for a camera and a light source, the coordinates in space of the point is triangulated. By repeating this process, a collection of coordinates is created. Those coordinates are then used to reconstruct the 3D surface.

Abstract: An image processing system uses an FPGA and an external memory to form neighborhoods for image processing. The FPGA is connected to the external memory in a way that reuses address lines, and increases the effective bandwidth of the operation.

Abstract: A technique for capturing the surface of three-dimensional (“3D”) objects using structured lighting. The movement of shadow across the 3D objects is optically recorded. Variation in brightness on the surface provides a cue for triangulation. By analyzing the variation in brightness of a particular point on the surface, the location of that point is determined based on the movement of the shadow. With known locations for a camera and a light source, the coordinates in space of the point is triangulated. By repeating this process, a collection of coordinates is created. Those coordinates are then used to reconstruct the 3D surface.

Abstract: A system for detecting movement of a writing implement relative to a writing surface to determine the path of the writing implement. The writing implement tip is determined within the image and used to form a kernel. The determination is made either manually, by looking for a predetermined pen tip shape, or by looking for a position of maximum motion in the image. That kernel is tracked from frame to frame to define the path of the writing implement. The tracking is accomplished by correlating the kernel to the image: either to the whole image, to a portion of the image near the last position of the kernel, or to a portion of the image predicted by a prediction filter.