Abstract: Features are disclosed for classifying pixels included in a digital image. Distance information from a pixel to structural reference points, such as skeletal joints, is generated. The distance information is then applied to a pixel classifier to identify one or more classifications for the pixel.

Abstract: In accordance with the present invention there is provided methods for generating an isotropic or near-isotropic three-dimensional images from two-dimensional images. In accordance with the present invention the method includes, obtaining a first image of a body part in a first plane, wherein the first image generates a first image data volume; obtaining a second image of the body part in a second plane, wherein the second image generates a second image data volume; and combining the first and second image data volumes to form a resultant image data volume, wherein the resultant image data volume is isotropic or near-isotropic.

Abstract: Methods, systems and apparatuses, including computer program products, are described for determining a performance metric of a mobile computing device application. A test computing device captures a plurality of images displayed on a mobile computing device based on execution of a mobile computing device application. The test computing device determines a first property for first and second images of the plurality of images. A first performance parameter is set based on a difference between the first properties of the first and second images. The test computing device determines a first property for third and fourth images of the plurality of images. A second performance parameter is set based on a difference between the first properties of the third and fourth image. A performance metric is determined based on a difference between the first performance parameter and the second performance parameter.

Abstract: An apparatus and method for determining a potential surface for installation of solar panels are provided. The method includes extracting, from a database of overhead images, at least one overhead image respective of a location; identifying a surface outline of at least one surface within the at least one overhead image; determining a pattern associated with the surface outline, the pattern comprising at least a facet; determining a potential installation area for solar panels based on the at least facet; and, displaying the potential installation area overlaid on the overhead image.

Abstract: An apparatus and a corresponding method for checking the security element of a value document, as well as to an apparatus for processing value documents involve at least one sensor for capturing electromagnetic radiation emanating from along a dimension of the security element and for generating a corresponding sensor signal pattern along the one dimension of the security element. Also included is an evaluation device for checking the value document with the help of the sensor signal pattern of the security element, from the sensor signal pattern along the one dimension there being generated a binary signal pattern which has only two different signal values and with the help of which the security element of the value document is checked with regard to a microwriting of the security element.

Abstract: A method for motion detection/characterization is provided including the steps of (a) capturing a series of time lapsed images of the ROI, wherein the ROI moves between at least two of such images; (b) generating a motion distribution in relation to the ROI across the series of images; and (c) identifying motion of the ROI based on analysis of the motion distribution. In a further aspect of motion detection/characterization in accordance with the invention, motion is detected/characterized based on calculation of a color distribution for a series of images. A system and computer program for presenting an augmented environment based on the motion detection/characterization is also provided. An interface means based on the motion detection/characterization is also provided.

Abstract: A computer-implemented method and system is provided, comprising extracting measurements of at least one auditory canal from at least one computerized imaging scan of the at least one auditory canal devoid of physical measurement aids; determining eligibility for at least one auditory canal device at least partly by comparing the measurements of the at least one auditory canal with predetermined measurements of the at least one auditory canal device; and providing an indication of the eligibility determination contemporaneously with the measurement extracting.

Abstract: A method of georeferencing a first image of a scene acquired from a first imaging device based on at least one second image of the scene acquired from a second imaging device. The method includes obtaining data indicative of an eligibility parameter for one or more areas of the scene; selecting one or more pivot areas among the one or more areas of the scene, wherein the eligibility parameter of the pivot areas satisfy a predefined criterion; for at least some of the selected pivot areas, identifying tie points for the first and second images; and solving the external orientation of the first image using the identified tie points and a first imaging device model.

Abstract: The present invention provides an image processing device whereby the probability of outputting a restored image which accurately corresponds to an original image which is included in a low-quality input image is improved. This image processing device comprises: an image group generating means for generating, from the input image, using a dictionary which stores a plurality of patch pairs wherein a degradation patch which is a patch of a degraded image wherein a prescribed image is degraded is associated with a restoration patch which is a patch of this prescribed image, a plurality of restored image candidates including a plurality of different instances of content which have a possibility of being the original content of the input image; and an image selection presentation means for clustering the generated plurality of restored image candidates, and selecting and outputting an image candidate on the basis of the result of this clustering.

Abstract: The present invention relates to a method for generating a risk map indicating predicted voxel-by-voxel probability of tissue infarction for a set of voxels, the method comprising the steps of, receiving for each voxel a first value (x) corresponding to a set of tissue marker values and generating the risk map, using a statistical model based on data from a group of subjects, and a stochastic variable, wherein the statistical model also comprises a second value (zi), being based on the stochastic variable, such as the second value modelling non-measured values. The invention may be seen as advantageous since it acknowledges subject variability in probability of tissue infarction on a voxel-by-voxel basis by taking non-measured values into account, which in turn may enable providing more reliable estimates of probability of infarction.

Abstract: A method for reducing noise in flouroscopic images by detection of the traits in the curvelet domain, matching of the detected traits and time-domain filtering adapted to the type of coefficients associated with a trait. The method uses the discrete curvelet transforms of the images from a sequence. The denoised coefficients are detected, then transmitted to a step for locally matching the traits, the matched data subsequently undergo a step for time-domain filtering allowing the movement of the objects to be preserved in the image and a step for a 2D IDCT (Inverse Discrete Curvelet Transform) in order to produce the final image.

Abstract: Methods and apparatus for obtaining probability density functions representing expected distributions of values of a parameter associated with an imaging modality are disclosed. The probability density functions are derived using data obtained from reference tissue volumes using the same imaging modality and at least one other type of imaging modality. The probability density functions are used to analyze data obtained from a volume of tissue of a patient in order to classify the tissue according to tissue type. Methods and apparatus are also disclosed in which deviations from a mean of an arctangent of ratios of first and second metabolite intensities in voxels are used to identify tissue types.

Abstract: Media monitoring using multiple types of signatures is disclosed. Example methods disclosed herein include sending a first indication to a device meter to indicate that media monitored by the meter corresponds to first reference media in response to determining that a media signature of a first type reported by the meter matched a first reference signature associated with the first reference media. Disclosed example methods also include, after sending the first indication, comparing media signatures of a second type reported by the meter with reference signatures of the second type associated with the first reference media. Disclosed example methods further include, in response to determining that the media signatures of the second type fail to match the reference signatures of the second type, sending a second indication to the meter to indicate that the media monitored by the meter no longer corresponds to the first reference media.

Abstract: A method and apparatus for biometric iris matching comprising pre-processing an input image capturing one or more eyes to produce one or more rectified iris images, coding the one or more rectified iris images into one or more multiresolution iris codes and matching the one or more multiresolution iris code with a set of stored multiresolution iris codes to determine whether a match exists.

Abstract: The present invention relates to a device and method for monitoring movement and orientation of the device, comprising an imaging unit (10) for obtaining images over time, a holding means (12, 13) for holding said imaging unit to obtain images from the surroundings of the device, and a processing unit (14) for detecting movement and orientation of the device by detecting changes in subsequently obtained images.

Abstract: A subject tracking apparatus includes a light detector, a focus detector, and a tracking controller. The focus detector is configured to detect focus information at a plurality of focus detection regions in a view of an image. The focus information includes at least focus information detected at a subject region of a subject in the view. The tracking controller is configured to determine at least one first region having substantially same light information as light information detected at the subject region from among a plurality of light measurement regions, to determine at least one second region having substantially same focus information as the focus information detected at the subject region from among the plurality of focus detection regions, and to determine reference information for tracking the subject in the view based on the at least one first region and the at least one second region.

Abstract: An image processing unit 36 includes an information acquisition unit 40, a filter acquisition unit 42, and a filter processing unit 44. The information acquisition unit 40 acquires imaging information of original image data which is acquired by capturing an object image using an optical system. In a case in which the imaging information includes the first imaging condition and does not include the second imaging condition, the filter acquisition unit 42 acquires a sharpening filter which is associated with the first imaging condition and is associated with a representative condition of the second imaging condition. The filter processing unit 44 applies the sharpening filter acquired by the filter acquisition unit 42 to the original image data to acquire sharp image data.

Abstract: An image measurement device calculates a disparity value from image data of images having disparity, acquires three-dimensional position information at the time of capturing the image data by using the disparity value, and calculates a three-dimensional plane from a region on an image serving as a same plane as a designated measurement region. Three-dimensional positions of the measurement region are acquired from the calculated three-dimensional plane to calculate a length. Accordingly, by using captured images having disparity, it is possible to measure a length of any part even in a region that the disparity value is hard to be acquired.

Abstract: A method is described for automatic recognition of anatomical structures in images obtained by position emission tomography, comprising the steps of: acquiring a 3D matrix of standardized uptake values, SUVs, associated with a plurality of PET pixels in an anatomic volume of patient; calculating the Jacobian matrix of the matrix of standardized uptake values, SUVs, projections, in a predetermined anatomical direction, of the matrix of standardized uptake values, SUVs, or of its Jacobian matrix on an anatomic reference plane; locating a two-dimensional minimum of the matrix of standardized uptake values, SUVs, or of its Jacobian matrix, projected on the anatomic reference plane; locating a one-dimensional minimum in the anatomic direction of projection, corresponding to the coordinates of the two-dimensional minimum located on the reference anatomic plane of projection; and determining a center of gravity of the anatomical structure according to the coordinates of said two-dimensional and one-dimensional minim

Abstract: Methods for dip determination from an image obtained by a down-hole imaging tool. For each pixel forming the image, a probability that a symmetry axis coincides with the pixel is determined. A probability map is then generated, depicting the determined probability of each pixel coinciding with the symmetry axis. The probability map and the image are then superposed to generate a mapped image. The symmetry axis is then estimated based on the mapped image. Image pixels coinciding with a boundary of the geologic feature are then selected in multiple depth zones, and a segment of a sinusoid is fitted to the selected image pixels within each depth zone. Dip within each of the depth zones is then determined based on the fitted sinusoid segments therein.