Abstract: Example computer-implemented method, computer-readable media, and computer system are described for generating subterranean imaging data based on vertical seismic profile (VSP) data. In some aspects, VSP data of a subterranean region can be received. Four angle attributes for each image point can be computed based on the received VSP data. Five-dimensional (5D) angle-domain common-image gathers (ADCIG) can be generated according to a ray-equation method based on the four angle attributes.

Abstract: To make it possible to accurately grasp an exposure state even in the case where noise is included in captured image data. An input image data acquisition unit configured to acquire input image data including a chart, a noise reduction unit configured to perform noise reduction on the input image data, and a histogram generation unit configured to generate a histogram of luminance of the input image data based on noise reduced image data are included, and the noise reduction unit performs noise reduction on the chart area of the input image data in a degree greater than that in which noise reduction is performed on an area other than the chart.

Abstract: Techniques are disclosed for removing haze from an image or video by constraining the medium transmission used in a haze image formation model. In particular, a de-hazed scene, which is a function of a medium transmission, is constrained to be greater than or equal to a fractionally scaled variant of the input image. The degree to which the input image is scaled can be selected manually or by using machine learning techniques on a pixel-by-pixel basis to achieve visually pleasing results. Next, the constrained medium transmission is filtered to be locally smooth with sharp discontinuities along image edge boundaries to preserve scene depth. This filtering results in a prior probability distribution that can be used for haze removal in an image or video frame. The input image is converted to gamma decoded sRGB linear space prior to haze removal, and gamma encoded into sRGB space after haze removal.

Abstract: Removal of the effects of dust or other impurities on image data is described. In one example, a model of artifact formation from sensor dust is determined. From the model of artifact formation, contextual information in the image and a color consistency constraint may be applied on the dust to remove the dust artifacts. Artifacts may also be removed from multiple images from the same or different cameras or camera settings.

Abstract: An image processing method which includes obtaining a normal image captured with all polarization components of light from an object, and a polarization image captured with specific polarization components out of all the polarization components of the light. The method further includes generating a difference image between the normal image and the polarization image; calculating, using pixel values of the difference image, a coefficient to be multiplied by at least one of a pixel value of the normal image and a pixel value of the polarization image; and synthesizing the normal image and the polarization image using a pixel value obtained by multiplying the coefficient by the at least one of the pixel value of the normal image and the pixel value of the polarization image to generate a synthesized image.

Abstract: A system and method is provided which allows for the transfer of an image data file such as a medical image data file. Device scan slices of an object are acquired per time point. A portion of the device scan slices of the object, e.g., live body organ, per time point which illustrate a change in the object from a previous time point is selected. At least one optical temporal image in spiral fashion per time interval is formed from the selected portion. The at least one optical temporal image is transmittable as an image data file to a location.

Abstract: Systems and methods for editing an image file include a server and at least one client device of the server including a display. An imaging module accesses from the server an image file including image content and a header, wherein the header provides information regarding the image file. An editing module receives user edits to the image content and insert information regarding the user edits into the header. The imaging module applies the user edits in an order that is determined based on a weight assigned to each user edit. The imaging module may also access, from the server, an image file including image content and a header thereof, wherein the header provides information regarding the image file and an edit decision list reflecting historical user edits to the image content. The editing module then identifies the edit decision list in the header for application by the imaging module.

Abstract: In phase-contrast imaging, different types of image information, such as absorption image information and differential phase-contrast image information, may be obtained by a single image acquisition process and have different image properties. A frequency dependent combination of different types of image information is obtained, the combined image having improved properties over the image information and respective image information types. Accordingly, an apparatus and a method for image processing in X-ray imaging of an object is provided, including receiving first and second image information of the object of first and second image information types, respectively, where the second image information type is different from the first image information type. The first and second image information is combined to obtain combined image information of the object, where the combined image information is frequency-dependent, depending on spatial frequencies of the first and second image information, respectively.

Abstract: A method and apparatus for forming an overall image of an object from a plurality of images. Each image includes three-dimensional data and color data and is segmented based on the color data to identify a first region with hard tissue and a second region with soft tissue. For each image, first and second weighting factors may be assigned. Points in the second region with a larger distance to a corresponding proximate part of the first region may have a smaller second weighting factor than a point with a smaller distance to a corresponding proximate part of the first region. The second weighting factor may be variable, with its value dependent upon a value of a first area section corresponding to the first region.

Abstract: Various methods are described for improving the compression of location information during a visual search. One example method may comprise identifying one or more features of a source query image for a visual search. The method may further comprise generating a histogram map comprising one or more histogram bins, wherein the histogram map represents the location of the one or more features of the source query image. Additionally, the method may comprise generating a context for at least one of the one or more histogram bins, wherein the context comprises a first context value based on information related to one or more neighboring bins located a first distance from the respective histogram bin and a second context value based on information related to one or more neighboring bins located a second distance from the respective histogram bin. Similar and related methods, apparatuses, and computer program products are also provided.

Abstract: The present invention provides a method and apparatus for reducing artifacts in Computed Tomography (CT) image reconstruction. The method comprises acquiring an original reconstructed image, then conducting total variation processing for the original reconstructed image generating a total variation reconstructed image, conducting an initial metal artifact reduction processing for the original reconstructed image generating an initial metal artifact reduction reconstructed image, generating a weighted image based on the total variation reconstructed image and the initial metal artifact reduction reconstructed image, wherein the weighted image reflects that the original reconstructed image contains white-band artifactsd combining a portion of the original reconstructed image and a portion of the initial metal artifact reduction reconstructed image through the weighted image to generate a final image, wherein the final image does not contain white-band artifact.

Abstract: An animal identification system and method is provided. The system includes a biometric sensor configured to capture a biometric feature of an animal as a biometric representation of the animal and a biometric identification module configured to receive the biometric representation of the animal and compare said biometric representation of the animal with stored biometric data for a plurality of animals and evaluate matching characteristics between the biometric representation of the animal and stored biometric data for the plurality of animals. The biometric sensor may include a nose print sensor, capacitive sensor, or camera. The biometric feature may include a nose print, an iris image of an eye of the animal, or an image of the unique vein pattern in the sclera of an eye of the animal.

Abstract: A method and an apparatus are provided to recognize a shape of a road on which a vehicle is traveling. Road edge shapes on a left side and a right side of the vehicle are recognized, from positions of roadside objects detected based on detection information from an on-board radar. Lane shapes that are shapes of lane boundary lines on the left side and the right side of the vehicle are recognized, from positions of lane boundary lines detected based on an image captured by an on-board camera. For each of the left side and the right side, such that the recognized road edge shape and the recognized lane shape are compared with each other, and the road shape is identified based on the comparison results.

Abstract: When carrying out an average prediction, an intra predictor carries out a filtering process on target pixels of the intra prediction located at an upper end and a left end of the block, the filtering process using an intermediate prediction value, which is an average value of adjacent pixels of the block, and at least one adjacent pixel of the target pixel. The intra predictor also sets a filter coefficient to ¾, associated with the intermediate prediction value for a target pixel at the left end of the block other than the target pixel at an upper left corner of the block, and sets a filter coefficient to ¼, associated with the adjacent pixel adjacent to the left side of the target pixel at the left end of the block. As a result, prediction errors locally occurring can be reduced, and the image quality can be improved.

Abstract: A volumetric segmentation method is disclosed for brain region analysis, in particular but not limited to, regions of the basal ganglia such as the subthalamic nucleus (STN). This serves for visualization and localization within the sub-cortical region of the basal ganglia, as an example of prediction of a region of interest for deep brain stimulation procedures. A statistical shape model is applied for variation modes of the STN, or the corresponding regions of interest, and its predictors on high-quality training sets obtained from high-field, e.g., 7 T, MR imaging. The partial least squares regression (PLSR) method is applied to induce the spatial relationship between the region to be predicted, e.g., STN, and its predictors. The prediction accuracy for validating the invention is evaluated by measuring the shape similarity and the errors in position, size, and orientation between manually segmented STN and its predicted one.

Abstract: In a method of analysis, a target image is registered to define a plurality of keypoints arranged in sets corresponding to polygons or linear segments in the target image. A database of registered and annotated images is accessed and a polygon-wise comparison between the target image and each database image is employed. The comparison is used for projecting annotated locations from the database images into the target image.

Abstract: An object detection device includes a raster scan execution unit that executes a raster scan on an input image using a scan window in order to detect an object within the input image which is input by an image input unit, a scan point acquisition unit that acquires scan points of the scan window which are positions on the input image during the execution of the raster scan, and a size-changing unit that changes a relative size of the input image with respect to the scan window. When the relative size is changed by the size-changing unit, an offset is given to the starting positions of the scan points after the change with respect to the starting positions of the scan points before the change.

Abstract: A digital video rescaling system is provided. The system includes an image data input configured to receive input support pixels y1 to yn and a sharpness control module configured to generate a sharpness control parameter Kshp. The system further includes an interpolated pixel generator configured to use an adaptive interpolation kernel to generate an interpolated pixel ys based on the input support pixels, and adjust a sharpness of the interpolated pixel ys based at least partly upon the sharpness control parameter Kshp. The system also includes a de-ringing control unit to adjust the ringing effect of the interpolated pixel based on a local image feature Kfreq, and an output module configured to output the adjusted interpolated pixel for display.

Abstract: Described here is a system and method for image reconstruction that can automatically and iteratively produce multiple images from one set of acquired data, in which each of these multiple images corresponds to a subset of the acquired data that is self-consistent, but inconsistent with other subsets of the acquired data. The image reconstruction includes iteratively minimizing the rank of an image matrix whose columns each correspond to a different image. The rank minimization is constrained subject to a consistency condition that enforces consistency between the forward projection of each column in the image matrix and a respective subset of the acquired data that contains data that is consistent with data in the subset, but inconsistent with data not in the subset.

Abstract: A coin handling system performs a one or two-part coin handling and recognition process. In the first part of the two-part process, the system images bulk coins, determines the coin types or other attributes, and returns at least some of the coins to the bulk coin receptacle; in the second part, the system re-images the coins and uses the coin types or attributes determined in the first part to efficiently and economically perform machine recognition of attributes of the coins. The output is used to handle the coins and to determine a price to pay for the coins. The images are bright field images suitable for use by people.