Abstract: The document controlled workflow techniques are provided that can be represented by refinable Petri nets. A document may contain a control code that indicates to the document controlled workflow system to implement specified operations (i.e., functions) at a refinable place. The operations implemented at the refinable place are determined by the control code in the document. An author of the document can customize a document controlled workflow system of the present invention by entering a control code into a document that triggers the implementation of operations customized to that particular document at a refinable place in the document workflow system. The operations specified by a control code in a document can be represented by a refinement network.

Abstract: An automatic reading assistance application for documents available in electronic form. An automatic annotator is provided which finds concepts of interest and keywords. The operation of the annotator is personalizable for a particular user. The annotator is also capable of improving its performance overtime by both automatic and manual feedback. The annotator is usable with any electronic document. Another available feature is a thumbnail image of all or part of a multi-page document wherein a currently displayed section of the document is highlighted in the thumbnail image. Movement of the highlighted area in the thumbnail image is then synchronized with scrolling through the document.

Abstract: One embodiment of the writing instrument described herein comprises a pen-like device containing three accelerometers and three gyroscopes. Data from these sensors are processed via an Euler transform. Prior to using the writing instrument, the user holds the writing instrument in multiple predefined positions and sensor readings are taken. The sensor readings are mapped to the corresponding predefined positions. In addition, the sensor readings are compared to expected sensor readings to compensate for environmental variations such as altitude or temperature as well as for the possible tilt of a writing surface. The sensor readings are interpolated to map sensor readings other than those at the predefined positions to other writing instrument positions. When the user writes with the writing instrument, sensor outputs are used to track the writing instrument to define strokes made by the user.

Abstract: An automatic reading assistance application for documents available in electronic form. An automatic annotator is provided which finds concepts of interest and keywords. The operation of the annotator is personalizable for a particular user. The annotator is also capable of improving its performance overtime by both automatic and manual feedback. The annotator is usable with any electronic document. Another available feature is a thumbnail image of all or part of a multi-page document wherein a currently displayed section of the document is highlighted in the thumbnail image. Movement of the highlighted area in the thumbnail image is then synchronized with scrolling through the document.

Abstract: A method and apparatus to precisely track the position of the writing instrument, specifically the writing end, such as the tip, of a pen. One embodiment of the invention described herein includes a writing instrument containing acceleration sensors and angular velocity sensors. Data from these sensors are processed via an Euler transform to determine the strokes made with the writing instrument. Corrections may be made to improve upon the output of the Euler transform. The data describing the strokes may include graphical representations of the strokes actually made with the writing instrument. Data describing the strokes may be stored or processed to accomplish a variety of tasks such as recording information, faxing a message, recording an appointment, or other such tasks.

Abstract: A method and apparatus for sending a facsimile of a message is disclosed. The present invention provides for recording pen strokes that set forth a message and sending the recorded pen strokes as part of a facsimile.

Abstract: One embodiment of the writing instrument described herein comprises a pen-like device containing three accelerometers and three gyroscopes. Data from these sensors are processed via an Euler transform. Prior to using the writing instrument, the user holds the writing instrument in multiple predefined positions and sensor readings are taken. The sensor readings are mapped to the corresponding predefined positions. In addition, the sensor readings are compared to expected sensor readings to compensate for environmental variations such as altitude or temperature as well as for the possible tilt of a writing surface. The sensor readings are interpolated to map sensor readings other than those at the predefined positions to other writing instrument positions. When the user writes with the writing instrument, sensor outputs are used to track the writing instrument to define strokes made by the user.

Abstract: An apparatus for presenting on-line documents is provided. The device is coupled to and for use with a network providing access to interconnected, on-line documents in response to document requests. The device comprises a cursor control device and at least one position sensor, wherein the position sensor determines a location of the cursor control device. The at least one position sensor is coupled to a display device. The display device displays a cursor that is responsive to the cursor control device. The display device displays on-line documents in response to document requests made via the cursor.

Abstract: A manual entry interactive paper and electronic document handling and process system uses a pen-like instrument (PI) with a writing point for making written entries upon a physical document and sensing the three-dimensional forces exerted on the writing tip as well as the motion associated with the act of writing. The PI is also equipped with a CCD array for reading pre-printed bar codes used for identifying document pages and other application defined areas on the page, as well as for providing optical character recognition data. A communication link between the PI and an associated base unit transfers the transducer data from the PI. The base unit includes a programmable processor, a display, and a communication link receiver. The processor includes programs for written character and word recognition, memory for storage of an electronic version of the physical document and any hand-written additions to the document.

Abstract: Secure financial transactions may be made with insecure facsimile transmissions using encoded customer-specific information that can be readily decoded and confirmed by a merchant. The encoded information is affixed to an order form using, for instance, a label. The encoded information may include a serial number for use in confirming the order. Other information such as a card number (e.g., credit card) and expiration date may also be included.

Abstract: A method and apparatus for encoding color information in monochrome (black and white) documents. The present invention includes a method and apparatus to produce color documents that interprets color information stored on a document containing an image in monochrome and generates an image in color based on the color information.

Abstract: A system for performing recognition having a telephone transmitter, a camera, a data channel and recognition processing logic, in which the camera is directly mounted to and positioned with respect to the telephone housing to obtain video information from a non-direct frontal view of the speaker corresponding to at least one facial feature for use in speechreading. The facial features that may be obtained include the position of the tongue, separation of the teeth and the rounding protrusion of the lips. Using this data, recognition processing logic performs speechreading recognition of the video information.

Abstract: A conversion method and apparatus that allows for converting a hardcopy document into a hyperdocument and vice versa. During hardcopy to hyperdocument conversion, hypertext information stored on the hardcopy document is used to set up links to other documents. During hyperdocument to hardcopy document conversion, hypertext link information is encoded and stored on the hardcopy document.

Abstract: The apparatus for the recognition of speech comprises an acoustic preprocessor, a visual preprocessor, and a speech classifier that operates the acoustic and visual preprocessed data. The acoustic preprocessor comprises a log mel spectrum analyzer that produces an equal mel bandwidth log power spectrum. The visual processor detects the motion of a set of fiducial markers on the speaker's face and extracts a set of normalized distance vectors describing lip and mouth movement. The speech classifier uses a multilevel time-delay neural network operating on the preprocessed acoustic and visual data to form an output probability distribution that indicates the probability of each candidate utterance having been spoken, based on the acoustic and visual data.

Abstract: A messaging system in which a sender is able to receive certification of receipt of messages sent to a receiver that ensures that only the desired recipient gains access to the messages. Also, the messaging system sends between a sender and a receiver both encrypted communications and decryption information used to decipher the encrypted communications.

Abstract: A facsimile transmission system with a first facsimile machine that includes at least a scanner for scanning documents inserted into a document feeder and transmission capabilities for sending a fax and with a second facsimile machine that includes at least reception capabilities for receiving the fax and a printer for printing a hard copy of the received fax, if necessary. The facsimile system may include functionality for securing the facsimile transmission. The facsimile system may include functionality to enable the facsimile transmission to be certified.

Abstract: A facial feature extraction method and apparatus uses the variation in light intensity (gray-scale) of a frontal view of a speaker's face. The sequence of video images are sampled and quantized into a regular array of 150.times.150 pixels that naturally form a coordinate system of scan lines and pixel position along a scan line. Left and right eye areas and a mouth are located by thresholding the pixel gray-scale and finding the centroids of the three areas. The line segment joining the eye area centroids is bisected at right angle to form an axis of symmetry. A straight line through the centroid of the mouth area that is at right angle to the axis of symmetry constitutes the mouth line. Pixels along the mouth line and the axis of symmetry in the vicinity of the mouth area form a horizontal and vertical gray-scale profile, respectively.

Abstract: A document processing system in which a server subsystem stores information corresponding to a document containing human readable and machine readable information and a client subsystem receives the document and interprets the machine readable information. The client subsystem contacts the server to verify validity of information in the document using a communications network that allows information to be exchanged between the server and the client.

Abstract: A compact disc (CD) read sensor apparatus for reading data from a CD track uses multiple laser beams for performing both tracking and reading data. In one embodiment, two laser beams are used to track by controlling the radial position of the two beams that are nominally radially disposed towards opposite edges of the recorded track. A differential signal is used to obtain tracking information and a sum signal is used to produce a read signal. In another embodiment, three laser beams are used corresponding to prior art three beam systems using two beams nominally disposed towards opposite edges for tracking and a center beam for reading. The three beams are combined to form an enhanced read signal with an improved signal-to-noise ratio over that obtained by any one beam.

Abstract: A method and apparatus for designing a multilayer feed forward neural network that produces a design having a minimum number of connecting weights is based on a novel iterative procedure for inverting the full Hessian matrix of the neural network. The inversion of the full Hessian matrix results in a practical strategy for pruning weights of a trained neural network. The error caused by pruning is minimized by a correction that is applied to remaining (un-pruned) weights thus reducing the need for retraining. However, retraining may be applied to the network possibly leading to further the simplification of the network design.