Abstract: A technique is disclosed for determining a group in which to add a new image set. The new image set is captured by one or more cameras in a video surveillance system. Similarity scores are generated between the new image set and one or more image sets of a plurality of groups, wherein each group includes one or more image sets of at least one object. The new image set is added to a group based on one or more factors. Also, a technique is disclosed for determining when to close a group, wherein a closed group is one to which an image set may not be added.

Abstract: A device for user enrollment is adapted to capture an image of a pattern projected on a target and distorted on the three-dimensional (3D) surface of the target, such as a human face, and an image of a two-dimensional (2D) surface of the target. The device can include an illumination unit adapted to project a patterned light onto the surface of the target in an invisible light wavelength, a 3D image capturing device to capture an image of a pattern projected on the target and distorted on the 3D surface of the target. The device can also include a 2D image capturing device adapted to capture an image of a 2D frontal view of the target in visible light. The device can also include an orientation unit that displays the face of the target in order to facilitate the positioning of the target within the proper fields of view.

Abstract: An apparatus for input and fingerprint recognition comprises a touch surface, and a data processor coupled to the touch surface. The touch surface comprises a first region and a second region. The second region is distinct from and coplanar with the first region and occupies a minor portion of a total surface area of the touch surface. The data processor is configured to selectively operate the touch surface in a touch input mode or a fingerprint detection mode. In the touch input mode, the data processor is configured to operate the second region at a first resolution comparable to that of the first region to detect a touch input anywhere on the touch surface. In the fingerprint detection mode, the data processor is configured to operate the second region at a higher resolution than the first resolution to detect a fingerprint on the second region.

Abstract: A system for analysing a brain image compares the image with a brain atlas, labels the image accordingly, and annotating the regions of interest and/or other structures. This atlas-enhanced data is written to a file (or more than one file) in the Dicom format or any web-enabled format such as SGML or XML format. The image used may be produced by any medical imaging modality. A fast algorithm is proposed for a landmark-based piecewise linear mapping of one volumetric image into another volumetric image. Furthermore, a new set of brain landmarks are proposed, and algorithms for the automatic identification of these landmarks are formulated for three orientations, axial, coronal, and sagittal.

Abstract: A method for determining an orientation of a base (130) to which a fiducial marker (110) is detachably mounted. The method includes the steps of determining the axis of symmetry for the fiducial marker and choosing the determined axis of symmetry of the fiducial marker (110) as the axis of symmetry of the base (130).

Abstract: The invention relates to a method for the reconstruction of a three-dimensional model of a vascular tree from two-dimensional X-ray projection images (A, B, C) that are taken from different spatial directions. On a first projection image (A) at least one reference point (CA) is specified. The gray-value profiles along the epipolar lines (EB, EC) for said reference point (CA) in other projection images (B, C) are then projected on the projection line (L) of the reference point (CA) and added there punctiformly to form a sum profile (S). The sum profile (S) has an extreme, for example, a gray-value minimum, at the position of the space point (C3D) belonging to the reference point (CA). In this way, it is possible to reconstruct semiautomatically a vascular tree from X-ray projections.

Abstract: One embodiment discloses a computerized method of facilitating cardiac intervention, comprising inputting patient data, creating a computerized interactive model of a heart based on the patient data, wherein the model comprises features, simulating at least one proposed cardiac intervention treatment 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. Additionally, a template may be created from the model to use as a guide during the cardiac intervention.

Abstract: A method for using computer-aided diagnosis (CAD) for digital tomosynthesis mammograms (DTM) including retrieving a DTM image file having a plurality of DTM image slices; applying a three-dimensional gradient field analysis to the DTM image file to detect lesion candidates; identifying a volume of interest and locating its center at a location of high gradient convergence; segmenting the volume of interest by a three dimensional region growing method; extracting one or more three dimensional object characteristics from the object corresponding to the volume of interest, the three dimensional object characteristics being one of a morphological feature, a gray level feature, or a texture feature; and invoking a classifier to determine if the object corresponding to the volume of interest is a breast cancer lesion or normal breast tissue.

Abstract: A system and method for tree matching are provided. The method for tree matching includes: acquiring tree-like structures representing a physical object or model; extracting a path from a first tree-like structure and a path from a second tree-like structure; comparing the paths of the first and second tree-like structures by computing a similarity measurement for the paths; and determining if the paths match based on the similarity measurement.

Abstract: Candidate anomalies in an anatomical structure are processed for classification. For example, false positives can be reduced by techniques related to the anomaly's neck, wall thickness associated with the anomaly, template matching performed for the anomaly, or some combination thereof. The various techniques can be combined for use in a classifier, which can determine whether the anomaly is of interest. For example, a computed tomography scan of a colon can be analyzed to determine whether a candidate anomaly is a polyp. The technologies can be applied to a variety of other scenarios involving other anatomical structures.

Abstract: A method of scoring Oestrogen and Progesterone Receptors expression (ER and PR) from histological images determines the percentage of brown image blob area in total blob area and derives percentage thresholds to quantify scoring. Brown blob area proportion is then compared with the thresholds to provide a first contribution to scoring of ER or PR. The number of relatively dark pixels is then counted, pixel number thresholds are determined to quantify scoring, and the number of relatively dark pixels is compared with the thresholds to provide a second contribution scoring of ER or PR. The two contributions are then added to provide an overall scoring in the range 0 to 8 which may be taken as a final score or it may be scaled to a conventional range 0 to 3.

Abstract: Computer-implemented methods for detecting defects in reticle design data are provided. One method includes generating a first simulated image illustrating how the reticle design data will be printed on a reticle using a reticle manufacturing process. The method also includes generating second simulated images using the first simulated image. The second simulated images illustrate how the reticle will be printed on a wafer at different values of one or more parameters of a wafer printing process. The method further includes detecting defects in the reticle design data using the second simulated images. Another method includes the generating steps described above in addition to determining a rate of change in a characteristic of the second simulated images as a function of the different values. This method also includes detecting defects in the reticle design data based on the rate of change.

Abstract: When “0” indicating that intensity of a stereoscopic effect is the lowest is applied as a stereoscopic effect tag, a stereoscopic image is allowed to be displayed as it is. On the other hand, when “1, 2, and 3” are applied as the stereoscopic effect tag, a reduction ratio is determined depending on a value of the stereoscopic effect tag (one-half, one-third, etc.). On the basis of this reduction ratio, the stereoscopic image is displayed and letters of “warning” are displayed. A user selects whether to display the stereoscopic image according to a producer's intention or to maintain the size-reduced stereoscopic image. If an operation requiring for a display of the stereoscopic image as it is intended by the producer is performed, an original stereoscopic image is displayed.

Abstract: A defect detection apparatus (1) comprises an image pickup part (3) for picking up an image of a substrate (9) to acquire a grayscale target image, from which pixel values of the target image are sequentially outputted to a defect detector (43). The defect detector (43) compares the target image with a reference image to generate a defect region image representing regions of defects included in a plurality of predetermined inspection regions, to be stored in a defect region image memory (44). A computer (5) obtains an area and a barycentric position of each of the defects in the defect region image to specify an inspection region including the defect and performs limitation (i.e., selection) of defects on the basis of a defect detection condition set for each inspection region on the area of defect. It is possible to detect defects with high efficiency by using a defect detection condition on a different area of defect for each inspection region.

Abstract: A method and system for generating 3D images of faces from 2D images, for generating 2D images of the faces at different image conditions from the 3D images, and for recognizing a 2D image of a target face based on the generated 2D images is provided. The recognition system provides a 3D model of a face that includes a 3D image of a standard face under a standard image condition and parameters indicating variations of an individual face from the standard face. To generate the 3D image of a face, the recognition system inputs a 2D image of the face under a standard image condition. The recognition system then calculates parameters that map the points of the 2D image to the corresponding points of a 2D image of the standard face. The recognition system uses these parameters with the 3D model to generate 3D images of the face at different image conditions.

Abstract: A method for processing a digital image is disclosed. The method includes the steps of (A) receiving the digital image, the digital image having (i) a Bayer color representation and (ii) two initial dimensions in a horizontal direction and a vertical direction respectively and (B) generating a resample image by down-sampling the digital image in the Bayer color representation such that (i) the resample image has two resample dimensions, (ii) at least one of the resample dimensions is smaller than a respective at least one of the initial dimensions and (iii) the respective at least one initial dimension is a non-integer multiple of the at least one resample dimension.

Abstract: An image conversion method and an apparatus for converting a digital image obtained by a scanning unit into a converted digital image includes the steps of acquiring statistics for at least some pixels of the digital image, extracting characteristic values of a background color using the acquired statistics, operating a selection of pixels in the digital image, and converting the selected pixels. Each pixel in the digital image is sequentially set as a target pixel, and the selection of the target pixel depends on a representative color distance determined between a number of pixels located in a vicinity of the target pixel and the background color.

Abstract: A signal is used to form intermediate feature vectors which are subjected to high-pass filtering. The high-pass-filtered intermediate feature vectors have a respective prescribed addition feature vector added to them.

Abstract: The claimed subject matter provides a system and/or a method that facilitates analyzing and/or recognizing a handwritten character. An interface component can receive at least one handwritten character. A personalization component can train a classifier based on an allograph related to a handwriting style to provide handwriting recognition for the at least one handwritten character. In addition, the personalization component can employ any suitable combiner to provide optimized recognition.

Abstract: A computer-based system is disclosed for the gathering and analysis of data and planning associated with that data captured during or related to events. The system is based on existing core technology that allows for the use of a digital pen land marked with respect to some spatial location on the surface of a computer screen that allows storage of ink data and allows for interpretation of handwritten characters. A mouse can be used in place of the digital pen, however, it is advantageous to use the digital pen on the surface of a computer screen. Part of the invention is able to capture real-time data in dynamic environments where the user must maintain active contact with the scene, allowing only minimal viewing of the computer screen. This minimal viewing component can be applied to, but not limited to, polling, traffic analysis, and sporting events. For the application to team sporting events, the minimal viewing component provides an efficient means for personnel to enter game statistics in real-time.

Abstract: An image recognition apparatus includes an objective image data acquisition unit to acquire objective image data containing a face image portion, a feature area detection unit to detect an eye area corresponding to left and right eyes contained in the objective image data, an inclination estimation unit to estimate inclination of the face image portion in a depth direction thereof based on the relative position of the detected eye area, an area-to-be-extracted determination unit to determine a shape of an area to be extracted in response to the inclination estimated by the inclination estimation unit, and an area-to-be-extracted extraction unit to extract the area to be extracted of the shape determined from the objective image data. Preferably, the area to be extracted is subjected to predetermined processing.

Abstract: A system and method for feature evaluation that include an evaluation system configured to consider extracted features and reference features and an evaluation system configured to quantify accuracy, quality, and correspondence between the reference features and the extracted features.

Abstract: A method of detecting a corner, and an apparatus to perform the method, the method including acquiring a visible light image and an infrared image of a spatial area of interest; and extracting corner information of the spatial area of interest using the acquired visible light image and the acquired infrared image.

Abstract: An image is analyzed to locate an object appearing in the image. A contour of that object is extracted from the image and normalized. Based on the normalized contour, one or more summation invariant values are determined and compared to templates comprising one or more summation invariants for each of one or more target objects. The determined summation invariants for the extracted object are compared to summation invariants for the target objects. When the summation invariants for the extracted object sufficiently match the summation invariants determined from an image of a target object, the extracted object is recognized as that target object. The summation invariants can be semi-local summation invariants determined for each point along the normalized contour, based on a number of points neighboring that point on the normalized contour. The semi-local summation invariants are determined as a function of the x and y coordinates of those points.

Abstract: The present invention includes a method to use a phase modulating micromirror array to create an intensity image that has high image fidelity, good stability through focus and good x-y symmetry. Particular aspects of the present invention are described in the claims, specification and drawings.

Abstract: A method of representing an object appearing in a still or video image, by processing signals corresponding to the image, comprises deriving a curvature scale space (CSS) representation of the object outline by smoothing the object outline, deriving at least one additional parameter reflecting the shape or mass distribution of a smoothed version of the original curve, and associating the CSS representation and the additional parameter as a shape descriptor of the object.

Abstract: Techniques for shape clustering and applications in processing various documents, including an output of an optical character recognition (OCR) process.

Abstract: A combination of inter-frame and intra-frame and sequential classification methods provide for robust and flexible object classification. Intra-frame classification determines the object type based on features extracted from a single image. Inter-frame classification determines object types based on the features extracted from several sequential frames. A sequential classification combines the results of the inter- and intra-frame classifications over a sequence of images.

Abstract: A method of and apparatus for compressing a stream of data, such as video data, is disclosed. First, data in the video stream are classified in accordance with their values. Data with values equal to zero are classified in a first class. Data with values less than a predetermined positive number but greater than a predetermined negative number, and not equal to zero, are classified in a second class. All other data are classified in a third class. Data in the first class is compressed using a run length encoding technique. Data in the second class is compressed by reducing the size of the data value and by adding a constant. Data in the third class is not compressed, but is modified by adding a constant. The data can be decompressed by determining the class of the compressed value and reversing the compression process. The compression method disclosed is easy to implement and results in a significant reduction in the amount of data that needs to be transmitted.

Abstract: Method and apparatus for compressed sensing yields acceptable quality reconstructions of an object from reduced numbers of measurements. A component x of a signal or image is represented as a vector having m entries. Measurements y, comprising a vector with n entries, where n is less than m, are made. An approximate reconstruction of the m-vector x is made from y. Special measurement matrices allow measurements y=Ax+z, where y is the measured m-vector, x the desired n-vector and z an m-vector representing noise. “A” is an n by m matrix, i.e. an array with fewer rows than columns. “A” enables delivery of an approximate reconstruction, x#, of x. An embodiment discloses approximate reconstruction of x from the reduced-dimensionality measurement y. Given y, and the matrix A, x# of x is possible. This embodiment is driven by the goal of promoting the approximate sparsity of x#.

Abstract: An image forming apparatus having a reduction layout function has as its object to suppress any image degradation in recompressed image data. To achieve this object, an image processing method of this invention has the following arrangement.

Abstract: An image encoding apparatus includes an extracting unit and a replacing unit. An image is subjected to quantized orthogonal transformation and quantization, and quantized orthogonal transform coefficients are grouped and encoded group-wise. The extracting unit extracts, from among a group of quantized orthogonal transform coefficients, those quantized orthogonal transform coefficients that are within a designated range starting from boundary values of the next lower group. The replacing unit replaces values of the quantized orthogonal transform coefficients extracted, with values of the quantized orthogonal transform coefficients of the next lower group.

Abstract: An image processing apparatus includes: a block decompression unit that decompresses, block by block, a compressed code formed of a plurality of blocks into which image data is divided, where the compressed code is encoded block by block; and a rendering control unit that causes a code to be decompressed and rendered on a display unit, where the code corresponds to at least one of the blocks which one is renderable in the rendering region of the display unit.

Abstract: An image display control apparatus for controlling a display to display an image on the basis of coded data of an input image encoded layer by layer in a plurality of layers, includes: a decoder that decodes coded data of parts of layers composing an input image to image data; and a controller that controls a display to display image elements on the basis of the image data decoded by the decoder.

Abstract: In the data-transmitting apparatus, the image-comparing circuit compares, when a request for updating the image displayed is made, the image data item being input, with the image data item stored in the memories, which represents the preceding frame. The circuit therefore calculates the difference between the image data items compared. If the difference thus calculated by the image-comparing circuit is smaller than a prescribed value (if No in Step S1), the transmission-region data processing circuit generates, from the difference of the image data, the data that represents that part of the image data which corresponds to a region to be transmitted, and the data that represents this region. These data items generated by the circuit are transmitted. If the difference thus calculated is equal to or greater than the prescribed value (if Yes in Step S1), the coarse-image data processing circuit generates coarse image data, which is transmitted.

Abstract: A plurality of bandpass filters extract high frequency components of a digital image signal sampled every predetermined unit, thus generating a plurality of high frequency signals. The high frequency signals are added to produce a resultant high frequency signal. On the basis of the value of the resultant high frequency signal, the maximum value or minimum value detected from the high frequency signals is selected. The resultant high frequency signal and the selected maximum or minimum value are added according to determined weights, so that an enhancement signal is generated. Edge enhancement is performed using the enhancement signal.

Abstract: Techniques and tools for analyzing and adjusting the exposure of digital images are described. For example, a computer processes a digital image by analyzing exposure data, assigning an image classification (e.g., StretchNeeded, UnderExposed, OverExposed, or Normal) based on the analysis, and selecting an exposure compensation technique (e.g., histogram stretch, positive gamma curve, negative gamma curve, or no adjustment) based on the image classification. The exposure data can be luminance values for pixels in the digital image represented in a histogram. The computer can produce transform data comprising a transformation of the exposure data according to the selected exposure compensation technique. The computer can store transform data in a look-up table and can store the look-up table in the digital image file. The described techniques and tools can be implemented as a feature of an operating system environment and can be activated responsive to user action via a user interface.

Abstract: Methods, systems, and apparatus, including computer program products, for merging images of segments of a view. Methods include: receiving, from a network, a first image representing a first segment of the view and a second image representing a second segment of the view; determining the position of the second segment of the view relative to the first segment of the view; blending the first image with the second image based on the determined position of the second segment relative to the first segment to form a panoramic image of the view; and transmitting the panoramic image over the network.

Abstract: A method and apparatus for producing a customized jigsaw puzzle is disclosed. The apparatus comprises an image capturing mechanism, such as a camera, that captures one or more images of one or more individuals, animals, or objects or combinations of these posed against a background. A computer that is linked to the mechanism and to a printer is programmed to print an image on flexible sheets having a printable surface. Then a press, having a platen carrying a jigsaw puzzle cutting die, when activated uses pressure to laminate together the flexible sheet bearing the printed image and a foam sheet thicker and more rigid than he flexible sheets, setting pressure responsive adhesive material used as a binder to form a laminated product, and substantially simultaneously to cut the laminated product into jigsaw puzzle pieces.

Abstract: A method of detecting an image of a reflective object includes the steps of capturing an exposure image by an image sensor while an LED is ON; down-sampling an exposure image signal from the image sensor to a first digital signal by comparing the level of the first image signal with a first reference level; capturing a dark image by the image sensor while the LED is OFF; down-sampling a second image signal from the image sensor to a second digital signal by comparing the level of the second image signal with a second reference level; computing an image of difference between the exposure image and the dark image by subtracting the second digital signal from the first digital signal; and specifying the image of the reflective object by locating a bright point remaining in the image of difference.

Abstract: Method and computer program product for mirroring an image according to internationalization information in an application supporting images. An initial image to be mirrored, which is described in a graphical format, is read. The image data is wrapped in a new image format by adding information about which area of the image is to be mirrored and how it is to be mirrored. A new image format library added to the application enables the application to read the new image format and transform the image according to the locale.

Abstract: Disclosed are systems for and methods of registering (i.e., aligning) a deformable image with a reference image subject to a spatially variant flexibility model and/or a non-Gaussian smoothing model. These systems and methods allow for the consideration of differences between the ways in which structures of interest may move within a patient. The registration includes modifying the deformable image to match similar features in the reference image. The systems include a deformation engine configured for performing a deformation algorithm subject to the spatially variant flexibility and/or smoothing models.

Abstract: The present invention provides an image display method for downloading an image of large longitudinal and transverse size and displaying it on a viewer with less latency time. The image display method may be used to divide an image larger than a display region of a viewer into a plurality of areas where each divided image is provided beforehand in a server. The viewer determines the plural divided images of which at least a part of each is contained in the display region of the viewer in accordance with a relative position between the image and the display region of the viewer and makes a preferential request of the viewer for the divided images. The viewer rearranges and displays the received divided images in their original form.

Abstract: A method for increasing the resolution of confocal images acquired through an image guide whereof the distal end is associated with an optical head for focusing the laser beam emitted by the image guide in an observation object. For a given position of the optical head, the method includes the following steps: producing a plurality of acquisitions through the image guide, each acquisition being produced for a specific spatial shift of the distal end of the guide image relative to the optical head which remains stationary; transforming the data of each acquisition into a point cloud; registering each scatter plot relative to a point cloud taken as reference; superimposing the thus registered point clouds; and reconstructing a final image from the superimposition. Advantageously, a controlled piezoelectric tube is used arranged about the distal end of the image guide to shift the latter.

Abstract: There is provided an electronic album editing system having a first storage section for storing a plurality of images captured by a user as an electronic album, a second storage section for storing each electronic album containing a plurality of images captured by cameramen other than the user by correlating with traveling routes of the cameramen of the images contained in the electronic albums, a traveling route calculating section for calculating a traveling route of the user in the plurality of images stored in the first storage section, an album detecting section for detecting an electronic album, out of the plurality of electronic albums stored in the second storage section, corresponding to a traveling route that presents a degree of coincidence of a reference value or more with respect to the calculated traveling route and an editing section for storing the images contained in the detected electronic album to the first storage section.

Abstract: A unique system and method that facilitates indexing and retrieving electronic ink objects with improved efficiency and accuracy is provided. Handwritten words or characters are mapped to a low dimension through a process of segmentation, stroke classification using a neural network, and projection along directions found using OPCA, for example. The employment of OPCA makes these low dimensional representations robust to handwriting variations or noise. Each handwritten word or set of characters is stored along with neighborhood hyperrectangle that represents word variations. Redundant bit vectors are used to index the hyperrectangles for efficient storage and retrieval. Ink-based queries can be submitted in order to retrieve at least one ink object. To do so, the ink query is processed to determine its query point which is represented by a (query) hyperrectangle. A data store can be searched for any hyperrectangles that match the query hyperrectangle.

Abstract: A data capturing module combined with a portable data terminal of the hand-held type to record handwritten data. Using a digitized pad, the module can provide for direct input of handwritten data into the system, or a peripheral digital scanner can be employed to provide for data entry. Depending upon the particular application, the module therefore provides for data entry of handwritten text or graphics using the data terminal and other components of a portable data system to enter, display, print or otherwise communicate the handwritten data.

Abstract: Provided is a high-speed ring optical modulator based on a silicon semiconductor, having increased optical modulation speed. The high-speed ring optical modulator includes a ring optical waveguide including a portion in which the refractive index varies, that is, a refractive index variation portion, and an optical waveguide having a constant refractive index. The refractive index variation portion comprises a bipolar transistor. Thus carriers can be supplied to and discharged from the refractive index variation portion, through which light is transmitted, at high speed, and thus the optical modulation speed can be increased.

Abstract: An embodiment relates to an image sensor comprising (a) a optical pipe comprising a core and a cladding, and (b) a pair of photosensitive elements comprising a central photosensitive element and a peripheral photosensitive element, wherein the central photosensitive element is operably coupled to the core and the peripheral photosensitive element is operably coupled to the cladding, and methods of fabricating and using the same. The image sensor could further comprise a lens structure or an optical coupler or an optical coupler over the optical pipe, wherein the lens structure or the optical coupler or the optical coupler is operably coupled to the optical pipe.

Abstract: A system and method for a structure monitoring and locating a disturbance event is disclosed. The system includes a compact transceiver chip sending optical signals in three optical fibers that encompass the monitored structure appropriately. The fiber arrangement has different density in different parts of the monitored structure, such as, for example, critical places in the structure may have larger number of fiber loops surrounding them. All fibers transmit signals in both directions: from the transceiver to a returning point and back. A set of two detectors registers the returning signals, and a time delay between those signals is calculated, which is indicative of the disturbance event location. Polarization states of the returning signals are controlled by transceiver built-in controllers. The event location is determined with different sensitivity in different parts of the monitored structure depending on the density of fibers in these parts.