Abstract: The present invention provides techniques for transmitting at least one signal through an element of a classification system. One or more input signals are received at the element. One or more functional components are extracted from the one or more input signals, and one or more membership components are extracted from the one or more input signals. An output signal is generated from the element comprising a functional component and a membership component that correspond to one or more functional components and membership components from one or more input signals.

Abstract: A system and method are provided that allows a speaker to provide real-time annotations to one or more displayed images during a presentation. The speaker inputs the annotations my manually identify a portion of the displayed image using an input mechanism such as a touch screen that is in communication with a presentation monitor and a control system that is controlling the presentation. The identified portions are annotated onto the displayed images using a adaptive color that is selected to provide optimum contrast with the existing colors in the displayed image. In addition to providing adaptive, contrasting colors for the annotations, imperfection such as waviness are removed from the identified portions to created corrected portions that are then annotated onto the presentation image. Annotation is accomplished through computer generated graphics or through the use of a motorized, controllable laser pointer.

Abstract: The present invention provides a method for capturing and storing physiological response attributes measured from a user while different stimuli are presented. Each stimulus may be any multimedia object, for example text, picture, or audio/video. The measured physiological response attributes are paired with the input stimulus, and stored conjointly in one or more databases. The physiological response attributes measure an aspect of the user known as emotional valence, and relate to the emotional state of the user, such as angry or sad. The database of physiological responses attributes of multiple users is first established. Then, when the physiological response attributes of a specific user in the future is examined, the system can suggest which objects in the database best correspond. Moreover, the database can be constructed based on the responses of the individual user for their own utilization, and be updated over the course of its continued use.

Abstract: A system and method for a network to deconvolve mixtures of inputs that have been previously learned. In addition, the network is also able to segment the components of each input object that most contribute to its classification. The network consists of oscillatory units that can comprise amplitude and phase, and that can synchronize their dynamics, so that deconvolution is determined by the amplitude of an output layer, and segmentation by phase similarity between input and output layer units. Moreover, segmentation can be achieved even when there is considerable superposition of the inputs.

Abstract: A method, apparatus and article of manufacture for modifying printing based upon direct on-the-fly media characteristic parameters is disclosed. The present invention on-the-fly directly measures a media characteristic parameter and performs real-time print modification in response thereto. The measured characteristic parameters include paper texture and composition, as well as adhesion and penetration of print. The modification of print in response to these measured parameters may allow a customer to maintain observed print quality with lower-cost materials. Adjustments may include the addition of coating, hot rolling, or adjustment of toner concentration. Measured parameters may include mottle, paper texture, and bleed through.

Abstract: An automatic monitoring and sensing apparatus is provided for detecting an intruder or a person whose presence is undesired for one reason or another. According to one aspect of the invention, a method and apparatus are provided for automatically monitoring an environment for the presence of a person, and the invention issues an alarm when the environment changes while the person is still present. For example, the invention is capable of detecting a person in an unexpected or dangerous location in the environment, such as a baby or small child who has been left alone in an automobile. The invention initiates remedial action to safeguard the person. In another aspect, the inventive method and apparatus automatically monitors an environment that is intended to be kept secure, such as an environment where a computer system is installed, wherein the apparatus initiates a safeguarding action such as a pre-emptive automatic back-up of data in the computer system.

Abstract: An automatic monitoring and sensing apparatus is provided for detecting an intruder or a person whose presence is undesired for one reason or another. According to one aspect of the invention, a method and apparatus are provided for automatically monitoring an environment for the presence of a person, and the invention issues an alarm when the environment changes while the person is still present. For example, the invention is capable of detecting a person in an unexpected or dangerous location in the environment, such as a baby or small child who has been left alone in an automobile. The invention initiates remedial action to safeguard the person. In another aspect, the inventive method and apparatus automatically monitors an environment that is intended to be kept secure, such as an environment where a computer system is installed, wherein the apparatus initiates a safeguarding action such as a pre-emptive automatic back-up of data in the computer system.

Abstract: The present invention provides techniques for transmitting at least one signal through an element of a classification system. One or more input signals are received at the element. One or more functional components are extracted from the one or more input signals, and one or more membership components are extracted from the one or more input signals. An output signal is generated from the element comprising a functional component and a membership component that correspond to one or more functional components and membership components from one or more input signals.

Abstract: Provided is a method, system, and program for managing a multi-page document. A plurality of input files are received including digital representations of multiple pages of a document. The content of each entire page is represented in a first representation format. The entire page content is capable of including content of a first content type and second content type. For each page of the document represented in the input files, a determination is made of regions in the page including content of the second content type. Each determined region in the page is processed to generate the content for each region in a second representation format. The content of the entire page in the first representation format and the content of each region in the second representation format is added to at least one output file. The output file is then stored.

Abstract: A digital imaging system and method uses a two-stage sigma filter to de-screen color images. This filter does not assume any a priori knowledge about the screening process using to produce the halftone image. The two-stage sigma filter may therefore be used to convert color halftone images into continuous-tone images irrespective of the screening process used. The two-stage sigma filter may be constructed, or emulated in software, using an O (N) algorithm which performs smoothing and preserves edge information simultaneously in the Red/Green/Blue color space. This system and method outperforms conventional approaches which, for example, use a Gaussian blur, because it satisfies the dual criteria of completely eliminating halftone screens while preserving edge information. When combined with halftone segmentation techniques, a complete document processing algorithm for gray-scale and color documents is created.

Abstract: The present invention presents halftoning techniques for printers and solves problems related to halftoning so as to render a combination of text and image areas in a pleasing manner. An advantage of this technique is that it gradually switches from text rendering to picture rendering in a manner which is locally adaptive over small regions, (say 3×3 pixels).

Abstract: An automatic monitoring and sensing apparatus is provided for detecting an intruder or a person whose presence is undesired for one reason or another. According to one aspect of the invention, a method and apparatus are provided for automatically monitoring an environment for the presence of a person, and the invention issues an alarm when the environment changes while the person is still present. For example, the invention is capable of detecting a person in an unexpected or dangerous location in the environment, such as a baby or small child who has been left alone in an automobile. The invention initiates remedial action to safeguard the person. In another aspect, the inventive method and apparatus automatically monitors an environment that is intended to be kept secure, such as an environment where a computer system is installed, wherein the apparatus initiates a safeguarding action such as a pre-emptive automatic back-up of data in the computer system.

Abstract: A system, method, and computer program product for configuring a network abstraction for simulation. Relationships between network models in the network abstraction are described in a network specification. A simulation infrastructure is adapted to configure the relationships between network models specified in the network specification. The simulation infrastructure is designed to acquire the network specification during run-time, access configuration, relationship parameterization, and execution APIs of model instances during run-time. Network models are designed to acquire access to modeling-specific APIs of other model instances during run-time in order to establish relationships specified in the network specification.

Abstract: A method for the complete segmentation of an image into regions of near-uniform color first segments the image into blocks of size N×M and applies color clustering within these blocks. This is done with a sequential color clustering algorithm. Subsequent to this, the color clusters that are spatially adjacent and also have similar color characteristics are merged. This is done through a novel method which combines distance in the feature space with distance in the spatial domain. This results in spatially compact color regions which have similar color information. The result of applying this technique is a complete segmentation of the image according to regions of near-uniform color.

Abstract: The present invention provides methods and apparatus to distinguish and/or separate an object from a background. The methods use backgrounds of known and/or advantageous texture. In an embodiment, a measure of image texture, namely the spatial frequency is used to distinguish and/or separate an object from its background. The use of image texture overcomes limitations of chroma keying used as a processing technique in photography for object-background separation. This is useful in the separation of image pixels belonging to the object of interest from image pixels belonging to the background.

Abstract: A semi-digital printer includes a print head assembly that prints an image on a sheet of paper that has been mounted onto a turntable, and a rotating means which rotates the turntable so that the print head assembly ejects ink or toner onto the sheet of paper at one or more predetermined angles. The printing may be halftone or color. If the print head assembly includes more than one print head, the rotating means rotates the turntable to a different angle for each print head. By rotating the turntable in this manner, the printer records an image at any angle (0° to 360°) precisely (i.e., without having to perform the angular approximations required by conventional digital printers). As a result, a printed image of improved quality is produced. Alternatively, the semi-digital printer may be configured so that the print head assembly rotates relative to the paper.

Abstract: A color clustering and segmentation method retains edge. A sigma filter is applied to an input image to generate a smoothed image. The filtered image is divided into a plurality of non-overlapping windows. A sequential clustering algorithm is applied to filtered pixels of each window to generate potential clusters. Generated potential clusters are validated while clusters representing pixels on boundaries are rejected. The result is a generated list of cluster centroids in a chosen color space.

Abstract: A method, system and computer article are presented for smoothing an image calibration signal in order to smooth a reproduced signal, and to identify the presence of any remaining spikes or other significant deviations. The invention recognizes the problems with raw calibration signals, and posits that the calibration signals be filtered by methods and systems described. For example, calibration data may be smoothed by fitting the calibration data to a parametric model employing either linear or non-linear least squares. Alternate techniques implement smoothing using optimal filtering. An aspect of the invention is a method, computer product or article of manufacture for improving an initial calibration profile having an initial profile extent to form an improved calibration profile. The initial profile may be formed for a scanner employing a linear array CCD and having a particular direction of motion.

Abstract: A method, computer program product, and a program storage device readable by machine, for repurposing images includes classifying the pixels of a binary image as being either halftone image pixels or non-halftone image pixels, further processing the halftoned image pixels with halftone image pixel processing and combining the outputs of the halftone image pixel processing and non-halftone image pixel processing to prepare the images for a second purpose such as a second printer. The processing that classifies the binary pixels as being either halftone image pixels or non-halftone image pixels segments the image into regions of halftone image pixels and regions of non-halftone image pixels. The processing of regions of halftone image pixels first constructs an intermediate gray scale representation of the regions of halftone image pixels.

Abstract: Calibrated dither masks adaptable to most printers are constructed in such a way that the threshold values can be adapted to a printer so that said printer can print the originally intended number of distinct tone levels. This adaptation can be done computationally so that the time it takes is not prohibitive. Furthermore, the resulting calibrated dither mask is such that there is no need for a tone reproduction curve in the halftoning process.