Abstract: An iterative method of determining the topical content of a document using a computer. The processing unit of the computer determines the topical content of documents presented to it in machine readable form using information stored in computer memory. That information includes word-clusters, a lexicon, and association strength values. The processing unit beings by generating an observed feature vector for the document being characterized, which indicates which of the words of the lexicon appear in the document. Afterward, the processing unit makes an initial prediction of the topical content of the document in the form of a topic belief vector. The processing unit uses the topic belief vector and the association strength values to predict which words of the lexicon should appear in the document. This prediction is represented via a predicted feature vector.

Abstract: A device for registering component image tiles in a scanning system for transcribing, into electronic form, markings on a two-dimensional surface such as a whiteboard. A registration light pattern is projected onto the surface to be imaged. The pattern projected can be chosen to best suite the specific properties of the camera and imaging environment. The pattern markings are processed using perspective transformations to determine the overlap properties of the image tiles and distortion of each tile image, and the resulting data is used to combine the tiles to produce an undistorted composite image of the whiteboard.

Abstract: A graphical input and display system for creating and manipulating an abstract graphical image by decomposing it into abstract elemental objects and organizing the elemental objects into a set of perceptually coherent composite objects. The system includes an input device for entering the graphical image, such as a mouse or digitizer and electronic stylus, a display, and a function selection system for manipulating the graphical image. The system decomposes the graphical image entered onto the display into abstract elemental objects each consisting of one or more consecutive "on" pixels within the image. The system organizes the elemental objects into composite objects, which are abstract groups of elemental objects, such that each elemental object belongs to one or more composite objects and each composite object contains one or more elemental objects. The elemental and composite objects are linked in a lattice data structure stored in system memory.

Abstract: A device for transcribing, into electronic form, markings drawn on a whiteboard or blackboard. An electronic camera such as an ordinary video camera is mounted on a computer-controlled pan/tilt head in the ceiling or to the side of the board. Images are captured by directing the camera successively at small regions of the board, then processing these snapshots electronically, leading to a complete, undistorted, high-resolution image of the entire board.

Abstract: A graphical imaging system, wherein the rough location, size and shape of objects in the image is summarized by a first characteristic descriptor, representing a parametric "pose" computed for each object. A second characteristic descriptor, i.e. a "gesture matching" function, is provided in order to select the single object, or else the set of objects, that best comports with the user's selection gesture. When most closely matched, these key characteristic descriptors permit simple and natural user gestures to distinguish among a large set of graphic objects that may overlap both spatially. User gestures can be simple slashes passing through the object, or quick, coarse approximations of objects' shapes.