Abstract: A method for creating a representation of a fingerprint is disclosed. The method comprises creating unique pairs of minutiae points identified in the fingerprint, each pair of minutiae points being represented by a distance between the minutiae points and by angles associated with the respective minutiae points included in the pair. Moreover, methods are disclosed for use in checking a person's identity and in creating reference data for checking a person's identify. Moreover, computer program products and devices for carrying out the methods are disclosed.

Abstract: Certain embodiments of the present invention provide a method and system for real-time motion correction in compound ultrasound imaging. Certain embodiments include receiving an image frame, estimating motion between the image frame and a previous image frame, updating a previous motion estimate with the estimated motion to form an updated motion estimate, and correcting the image frame and the previous image frame using the updated motion estimate. The method may also include forming a compound image from the image frames. In an embodiment, motion may be estimated between the image frame and a previous frame using cross correlation, reference point registration, and/or other estimation method, for example. The image frame and the previous image frame may be corrected using the updated motion estimate in an affine transformation or other correction method, for example. In an embodiment, the method provides real-time correction as image frames are being received.

Abstract: The depth buffer of a GPU is used to derive a surface normal or other surface parameter, avoiding or limiting computation of spatial gradients in 3D data sets and extra loading of data into the GPU. The surface parameter is used: to add shading with lighting to volume renderings of ultrasound data in real time, to angle correct velocity estimates, to adapt filtering or to correct for insonifying-angle dependent gain and compression. For border detection and segmentation, intersections with a volume oriented as a function of target structure, such as cylinders oriented relative to a vessel, are used for rendering. The intersections identify data for loading into the frame buffer for rendering.

Abstract: A surgeon utilizes a brain scan image to locate a brain lesion and to plan the operation to treat it. Distance measurements representing the location of the lesion are derived from various views of a brain scan image. In the operating room, he transfers these distance measurements onto the patient's cranium in a “warped” or curvilinear Cartesian coordinate system defined by intersecting orthogonal lines extending along the surface of the patient's cranium. As a result, the lesion is localized and the surgeon may establish the appropriate location and orientation of a bone flap to be used to access the lesion.

Abstract: A technique is provided for comparative image analysis and/or change detection using computer assisted detection and/or diagnosis (CAD) algorithms. The technique includes registering a first three-dimensional image of a first volume and a second three-dimensional image of a second volume. The first and the second volume are generally anatomically symmetric to one another. The technique also includes automatically comparing the first three-dimensional image and the second three-dimensional image.

Abstract: The present invention relates principally to the statistical analysis of protein separation patterns. Specifically, the invention provides a method of performing operations on protein samples for the analysis of separation patterns, the method including separating a plurality of protein samples to produce a plurality of respective separation patterns; forming a representation of each separation pattern; building an importance map by iteratively recording performance values of classification models against locations in the importance map which correspond to locations in representations of separation patterns of data points used to build the classification models; and processing the importance map to identify important areas. Parts of the map which include high performance values indicate regions of the separation pattern which are statistically important in predicting a classification of the pattern.

Abstract: The invention relates principally to the statistical analysis of protein separation patterns. The invention solves the problems associated with producing models which are predictive of classification using unreduced data. The invention provides a method of analysing a representation of a separation pattern, the representation including a neighborhood representing a region of the separation pattern, the neighborhood including a plurality of data points, the method comprising augmenting data by representing the entire region using each data point of the neighborhood; and building a classification model using some or all of the data points.

Abstract: A method for determining the degree of twist to be manually introduced into an implant which is to be positioned in the aorta and adjacent iliac branches so as to achieve an effective degree of twist when the implant is positioned in the anatomy, the method comprising: identifying the effective degree of twist desired for the implant; determining the Native Iliac Rotation of a patient; and subtracting the Native Iliac Rotation of a patient from the effective degree of twist desired for the implant so as to determine the degree of twist to be manually introduced into the implant.

Abstract: One embodiment discloses a computerized method of facilitating cardiac intervention. The method may include inputting patient data and creating a computerized interactive model of a heart based on the patient data. The model may include features. The model may simulate at least one proposed cardiac intervention by adding or deleting features to the model, and determining the effects of the proposed cardiac simulation upon the entire model. Simulations may be repeated to allow the user to determine an optimal cardiac intervention. A template and/or patient specific instrument may be created from the model to use as a guide during the cardiac intervention.

Abstract: The present invention discloses a method for registering a measured MRI volume image with appropriate anatomical and blood supply territory Atlases to enable Atlas information to be mapped onto the measured MRI volume image. The disclosed arrangements provide an efficient method for mapping brain Atlas information (including gross anatomy and blood supply territories) into magnetic resonance perfusion and diffusion images.

Abstract: A workstation imports medical images that depict a tumor and provides tools that enable a physician to see the results of prior therapies, plan future therapies, predict the outcome of future therapies and control future therapies. The workstation processes the imported images to produce isonumeric images of the tumor that can be analyzed by an expert system that provides diagnostic and outcome information as well as suggestions for further testing and therapy.

Abstract: A method of providing dental-related imaging data of a patient to a dental practitioner is provided, the dental-related imaging data being obtained by a third party imaging provider at a third-party imaging provider site using a three-dimensional digital imaging device. Three-dimensional image data of the maxillofacial complex of the patient is obtained with the imaging device and analyzed to form a diagnosis. A two-dimensional image associated with the diagnosis is formed from the three-dimensional image data, and the two-dimensional image and diagnosis are combined into a composite file as part of the dental-related imaging data. The dental-related imaging data is stored in encrypted read-only format executable by a standard multi-media player and made available to the dental provider in a secure arrangement. The composite file is thereby selectively viewable by the dental provider for determining an appropriate treatment for the patient. Associated methods and apparatuses are also provided.

Abstract: A system and method for piecewise registration of timepoints are provided. The method comprises: selecting an image dataset of a first or second timepoint to be registered; defining a sub-volume in the selected image dataset; and registering the sub-volume with a whole-volume of the unselected image dataset.

Abstract: A method for segmenting an object of interest from an image of a patient having such object. Each one of a plurality of training shapes is distorted to overlay a reference shape with a parameter ?i being a measure of the amount of distortion required to effect the overlay. A vector of the parameters ?i is obtained for every one of the training shapes through the minimization of a cost function along with an estimate of uncertainty for every one of the obtained vectors of parameters ?i, such uncertainty being quantified as a covariance matrix ?i. A statistical model represented as {circumflex over (ƒ)}H (?,?) is generated with the sum of kernels having a mean ?i and covariance ?i . The desired object of interest in the image of the patient is identified by positioning of the reference shape on the image and distorting the reference shape to overlay the obtained image with a parameter ? being a measure of the amount of distortion required to effect the overlay.

Abstract: A method and computer-implemented system for enhancing the capability of an imaging modality by coupling it with physiological models constructed at length scales below the resolution of the imaging modality. The present invention involves the use of multiple, coupled FEA analyses operating at different length scales to increase the utility of image data from a diagnostic imaging modality by achieving “virtual resolution enhancement.” The preferred embodiment uses asymptotic homogenization FEA methods to map physiological data to the high-level model based on the diagnostic imaging modality and/or to micro-level model(s) based on theoretical or alternative imaging modalities.

Abstract: A method is described for achieving resolutions beyond the resolution of a diagnostic imaging using multilevel computational analysis. This is accomplished by coupling the diagnostic image with images obtained at higher resolutions or with physiological models constructed at size scales beyond the resolution of the original diagnostic image. Using a discretization function, the image data or models are converted or generated so that they can be processed by a multilevel computational analysis function. The multilevel analysis then mathematically couples the models across two or more length scales generating parameters of interest at each level of analysis. A post-processing function provides the interface for the user to view the parameters of interest in the model derived from the original diagnostic image and/or the image itself and then “zoom-in” to a region by accessing the higher resolution image and/or model associated with it and viewing the parameters of interest.

Abstract: In a method and an apparatus for detecting various cells types of cells in a biological sample, an image of the biological sample is provided. This image is normalized with regard to a distribution of the image values, and the normalized image is subsequently divided into a plurality of image sections. Each image section is associated with a predetermined class in dependence on predetermined properties of the image section. In each image section, the individual cells are detected, and features of these individual cells are determined. Subsequently, the individual cells are associated with a specific cell type on the basis of the features detected.

Abstract: In a method and apparatus for locating in a three dimensional data array an arcuate object having an axial extent, slices of data generally transverse to the axial extent of the object are selected. Rays generally radially of the arcuate object are selected within the slices. Crossing points where the rays cross the boundaries of the arcuate object are located. The position of the arcuate object is determined from the positions of the located points.

Abstract: A Bayesian formulation for coupled surface evolutions in level set methods and application to the segmentation of the prostate and the bladder in CT images are disclosed. A Bayesian framework imposing a shape constraint on the prostate is also disclosed, while coupling its shape extraction with that of the bladder. Constraining the segmentation process improves the extraction of both organs' shapes.

Abstract: A method for processing image data includes estimating initial factor images from image data, transforming the estimated initial factor images by a transformation variable to obtain transformed factor images, providing an objective function that is a function of the transformed factor images, and minimizing the objective function to obtain unique factor images from the estimated initial factor images.

Abstract: A light emission section includes a plurality of light sources and emits near infrared low coherent light beams having different specific wavelengths to a light interference section. The light interference section allows the near infrared low coherent light beams to pass therethrough toward the eyeground and partially reflects the beams toward a movable mirror. Measurement light reflected by the eyeground and reference light reflected by the movable mirror interfere at the light interference section. Resultant interference light rays propagate to a light detection section, which calculates the profile of the eyeground from the light quantities of the interference light rays, and calculates the oxygen saturation SO2 from the light quantity distributions of the near infrared low coherent light beams emitted from the light emission section and the light quantities of the received interference light rays. A display section displays the calculated profile and oxygen saturation SO2 in a superposed manner.

Abstract: A data processing apparatus comprising a display device for displaying the data; the first recording device for recording the large volume bit map data; the second recording device recording an index data formed as a two-dimensional image obtained by rendering the large volume bit map data; the first data processing device for reading the large volume bit map data from the first recording device and applying the image processing to the large volume bit map data; the second data processing device for reading the large volume bit map data from the first recording device, forming the two-dimensional image data by rendering the large volume bit map data and transferring the image data to the display device; the third data processing device for transmitting the index data to the display device; and the input device for sending the instructions to the first, second and third data processing devices.

Abstract: Systems and methods are provided for achieving convergent light rays emitted by a planar array of light sources. In one embodiment, an imaging device is provided for inspecting semiconductors or other objects. The imaging device includes one or more imaging lens for imaging light reflected from an object. The imaging device also includes a first light source attached to a planar circuit board and a second light source attached to the planar circuit board. The imaging device further includes a first Fresnel prism for directing light from the first light source toward the object from a first direction and a second Fresnel prism for directing light from the second light source toward the object from a second direction. In one embodiment, the imaging device also includes one or more optical elements for increasing or decreasing the divergence of the light.

Abstract: A fast template matching method by adaptive template decomposition is provided. The template decomposition technique subdivides a template into a number of horizontal and/or vertical subdivisions and one-dimensional characterizations are determined for the subdivisions. The template decomposition may be adapted during learn mode operations of a general-purpose precision machine vision inspection system, with the support of corresponding user interfaces. The matching results for one or more template decomposition configurations may be evaluated by a user, or by an automatic decomposition configuration evaluation routine, to determine a configuration that provides a desirable trade-off between speed and matching position accuracy. Automatic workpiece inspection instructions may implement the configuration to repeatedly provide optimum speed versus accuracy trade-offs during run mode operations of the inspection system.

Abstract: A method of analyzing image data to determine an appropriate resolution level for image to be generated from the image data. In the method image data can be analyzed to determine a high frequency noise quality and a low frequency noise quality in the image data. These different noise qualities can be used to determine an appropriate resolution for an image to be generated. An apparatus which can execute a method of the invention, is also provided.

Abstract: An apparatus which can acquire, readout and perceive a scene based on the insertion, or etching of photosensitive elements into or on a transparent or semi-transparent substrate such as glass. The substrate itself acts as the optical device which deflects the photons incident to the reflected image into the photosensitive elements. Photosensitive elements are interconnected together by a transparent or opaque wiring. A digital neural memory can be trained to recognize specific scenery such as a human face, an incoming object, a surface defect, rain drops on a windshield and more. Other applications include image-perceptive car headlight and flat panel display detecting and identifying the viewer's behavior (gaze tracking, face recognition, facial expression recognition and more). Yet another application includes sliding doors perceiving the direction and speed of an individual coming towards that door.

Abstract: Tone mapping a high dynamic range (HDR) image is performed by obtaining a log-norm luminance component based on a normalized logarithm of the HDR image. The log-norm luminance component is flattened (tone-compressed) using incrementally-spaced adaptation levels, which are increasingly blurrier representations of the log-norm luminance component, weighted by a diminishing factor. Visual cues are restored by injecting a proportion of values of the log-norm luminance component, applying histogram tail clipping, and applying a sigmoid curve mapping, to create a restored luminance component. A tone-compressed image is obtained by mapping luminance of the HDR image using the restored luminance component and adjusting saturation of the mapped HDR image.

Abstract: A method of and a system for splitting a compound object using multi-energy CT data including a density and an atomic number measurements are provided. The method comprises: compound object detection; computing a two-dimensional DZ distribution of a compound object; identifying clusters within the DZ distribution; assigning a component label to each object voxel based on the DZ distribution clusters; and post-processing the set of voxels identified as belonging to each component.

Abstract: A method of and a system for identifying objects using local distribution features from multi-energy CT images are provided. The multi-energy CT images include a CT image, which approximates density measurements of scanned objects, and a Z image, which approximates effective atomic number measurements of scanned objects. The local distribution features are first and second order statistics of the local distributions of the density and atomic number measurements of different portions of a segmented object. The local distributions are the magnitude images of the first order derivative of the CT image and the Z image. Each segmented object is also divided into different portions to provide geometrical information for discrimination.

Abstract: A system and method for graph cut image segmentation using a shape prior is provided. In this method, an initial shape is applied to a portion of an image to be segmented. A narrowband is formed around a border of the shape, and a minimized graph cut is calculated for a portion of the image within the narrowband. The shape is then adjusted using the shape prior to fit the minimized graph cut. This method can be iteratively performed so that the shape evolves to segment an object from an image. The shape prior can be a parametric shape, such as an ellipse, or a statistical shape eigenspace calculated based on one or more training shapes.

Abstract: A data-generating apparatus comprising a bitmap data-generating unit to generate binarized bitmap data indicating an image-formed area and an image-excluding area based on the figure information in response to the figure-describing data being inputted, a judging unit to judge whether modifying information is comprised in the figure-describing data, a modifying unit to modify the bitmap data based on the modifying information, and an image-forming data-generating unit to generate the image-forming data based on the bitmap data modified by the modifying unit and the pattern information in response to the judging unit determining that the modifying information is comprised in the figure-describing data and generates the image forming data based on the bitmap data generated by the bitmap data-generating unit and the pattern information in response to the judging unit determining that no modifying information is comprised in the figure-describing data, is provided.

Abstract: A method for presenting recognised handwritten symbols comprises the steps of recognising the detected handwritten pattern. The step of recognising comprises comparing the handwritten pattern to templates representing ways of writing symbols and returning a best interpretation of the handwritten pattern, said best interpretation being based on the pattern of a best template. At least two templates comprise different patterns which represent different ways of writing a single symbol, and the patterns of the at least two templates return different best interpretations when being most similar to the handwritten pattern. The method further comprises the step of presenting the pattern of the best template on a screen. A device for implementing the method is also disclosed.

Abstract: Scalable image compression is exploited to facilitate the creative process in the post-production of motion pictures. Specifically, digital intermediate (DI) processing of motion pictures is enabled by dynamically rendering proxies 126 (steps 122, 124, 128) in response to client requests (steps 116, 118). A DI application is designed to enhance the efficiency of post-processing and the quality of the work product of the editors, colorists and other creative people. The DI application also provides a method for efficiently formatting the product for film, digital cinema, DVD and other video applications.

Abstract: Described herein is a method and system for motion compensation. This system and method use confidence for motion vector selection. Relative cost and an estimate of noise power may be used to characterize residual values and influence confidence determination.

Abstract: A color image and video encoding and/or decoding apparatus, method, and medium using inter-color-component prediction in accordance with an encoding mode are provided.

Abstract: A method and apparatus for encoding and/or decoding image data. The encoding method includes: if the color space of an image is a single color space, correcting pixel values by applying identical correction pixel values to all color components of a previous image, and if the color space of the image is not a single color space, correcting pixel values by applying different correction pixel values to the color components of the previous image; performing temporal prediction encoding of a current image by using the corrected pixel values of the previous image; quantizing the prediction encoded data; and generating a bitstream by entropy encoding the quantized data. According to the method and apparatus, when the pixel values of a previous image are desired to be corrected in order to perform temporal prediction encoding, different pixel value correction methods are applied according to whether or not the characteristics of color components included in the color space of the image desired to be encoded.

Abstract: Method and apparatus for handling data comprises decomposing data into a plurality of resolution levels using an integer wavelet decomposition. A transform module may be used to perform forward and inverse transformations on multi-dimensional data using integer wavelet transforms. A data stream is compiled comprising the plurality of resolution levels in a predetermined order. At least one resolution level of the plurality of resolution levels associated with a workflow application is accessed by a processor, and the workflow application is performed on the at least one resolution level.

Abstract: An apparatus and method for encoding and decoding image data. The image data encoding apparatus includes: a transformer transforming pixel values of an image in a time domain into pixel values in a frequency domain; a quantization coefficient determiner determining a quantization coefficient proportional to a number of bits per pixel of the image; a quantization unit quantizing the pixel values transformed by the transformer based on the quantization coefficient determined by the quantization coefficient determiner; and an entropy encoder generating a bitstream of the quantized pixel values.

Abstract: A method of generating pixel data of a missing block in an image frame is disclosed. Edge points are detected from neighboring image side adjacent to the missing block. A direction is calculated for each edge point. Edge lines are formed from edge points based on the direction thereof to partition the missing block into a plurality of missing regions. Data for missing pixels in each missing region are then calculated using reference pixels from neighboring image sides adjacent to the missing region.

Abstract: For enabling a change in lighting pattern in an image, adjustment of a shadow pattern is aimed at in an image. For this purpose, a parameter acquisition unit obtains weighting parameters representing the shadow pattern in a face region in the image by fitting to the face region detected by a face detection unit a mathematical model generated by a method of AAM using a plurality of sample images representing human faces in different lighting conditions. A shadow pattern adjustment unit adjusts the shadow pattern in the face region based on the weighting parameters having been obtained.

Abstract: Described herein are a method and system for distinguishing various characteristics of an image and selectively removing them. In video processing applications, the available compression bandwidth may determine the amount of coding loss that will be required. For very low rate encoding, film grain noise may be removed in order to maintain picture quality. For higher rate encoding, the method and system may distinguish a analog noise level from a film grain noise level. According to the film grain noise level and the encoding rate, encoding may selectively remove analog noise and maintain film grain noise.

Abstract: A method and apparatus for modifying, or morphing, a video image. A video feed is received which include an image of a person's face. A number of facial features are detected from the video feed. One or more of those facial features are selected and modified, with the modification being applied to the video feed to produce a morphed image. For example, the morphing can produce fun effects such as oversized or too small eyes, lips, etc.

Abstract: A method for reconstructing an image generated from radial trajectory data in frequency or k-space using a GPU. The method includes using a vertex shader of the GPU to transform coordinates of a window aligned with the radial trajectory data and using a pixel shader of the GPU to combine data along the radial trajectory with the coordinate transformed widow to distribute the data along the radial trajectory fed to the pixel shader into cells of a Cartesian coordinate system.

Abstract: The system of generating geometric characteristics of a digitally encoded image comprises a display device (2) capable of displaying a digitized image, communicating with a control unit (4), and comprising a man-machine interface (6) and means of supplying data (3) to the system via said man-machine interface (6). The system also comprises: a display means (7) for displaying a digitally encoded image on the display device (2), a first delimiting means (8) for delimiting a portion of the image representing a substantially flat surface, a processing means (9) for applying a predetermined deformable geometric pattern to the image in the position of said delimited image portion and deforming the pattern so as to make it correspond to said image portion, and a determination means (10) for determining geometric characteristics of said surface from the deformation of the pattern.

Abstract: Automatic conflation systems and techniques which provide vector-imagery conflation and map-imagery conflation. Vector-imagery conflation is an efficient approach that exploits knowledge from multiple data sources to identify a set of accurate control points. Vector-imagery conflation provides automatic and accurate alignment of various vector datasets and imagery, and is appropriate for GIS applications, for example, requiring alignment of vector data and imagery over large geographical regions. Map-imagery conflation utilizes common vector datasets as “glue” to automatically integrate street maps with imagery. This approach provides automatic, accurate, and intelligent images that combine the visual appeal and accuracy of imagery with the detailed attribution information often contained in such diverse maps. Both conflation approaches are applicable for GIS applications requiring, for example, alignment of vector data, raster maps, and imagery.

Abstract: Motion of the heart during contrast enhancement is modeled at two hierarchical levels: global translation and local deformation. Large-scale, i.e., global, translational motion is identified using global template matching, while the local deformation of a portion of the object (e.g., the left ventricle where the object is a heart) is obtained using an adaptive local template matching scheme which adapts to the local edge distributions by varying the height and the width of the template as well as the location of the template followed by spatial regularization. To address the difficulty of rapid intensity changes across the image sequence as the contrast agent perfuse into the tissue, an edge-based similarity measure is used for template matching.

Abstract: A force sensor particularly suited for use in an electronic stylus that senses the contact force on its nib for recording pen strokes and handwriting recognition. The sensor has a housing for a load bearing member for receiving an input force to be sensed and associated circuitry for converting the input force into an output signal indicative of the input force. The bearing member is movably mounted within the elongate body (up to 100 microns). The input force acting on the load bearing member is caused by contact on the nib. The load bearing member is biased against the direction of the input force. The force sensor also has a light source and photo-detector for sensing levels of illumination from the light source.

Abstract: The present invention provides an apparatus for protecting a device from water damage. The apparatus is capable of being repeatedly opened and then hermetically sealed even when the device has a wire that must be extended outside of the apparatus. The present invention comprises a housing having at least two members that, when juxtaposed and clamped, form a dry interior region. More specifically, each member includes a pair of gaskets that together define the dry interior region and substantially form a hermetic seal about a pouch or container. The apparatus includes a portal through which the wire may extend from a device inside the pouch or container to the outside and a slide mechanism that adjust a gasket around the wire to maintain the dry interior region. The slide mechanism forms a hermetic seal around the wire so that the opening in the pouch from which the wire extends is hermetically sealed. If no wire is present, the slide mechanism may be adjusted to maintain the hermetic seal.

Abstract: A moisture-proof sealing bag comprises a bag body and an exhausting valve. The bag body has an opening, which has a flexible belt on the opening end. A proper position under the flexible belt of the bag body has the exhausting valve. The exhausting valve is concealed inner the bag body, which comprises a valve body, an exhausting unit, a valve gate and an elastomer. The moisture-proof sealing bag has functions of moisture-proof and air-tightness so as to preserve the contents in the bag by use of sealing the opening of the bag with the flexible belt and exhausting the residual air with the exhausting valve.

Abstract: The present invention is a shoelaces laundry bag made of a net-like material, which protects shoelaces from entangling in the washing machine agitator. The shoelaces laundry bag is preferably of rectangular shape and comprises an opening at the top end, a compression-type fastening mechanism with a zipper-type handle that snaps in place to hold the shoelaces laundry bag closed. The shoelaces laundry bag is three-dimensional and has a side dimension with a supporting fabric. The shoelaces laundry bag can be made of natural or synthetic material, which is appropriate for washing and drying. The zipper and fasteners can be made of plastic or any synthetic material.