Abstract: A device (10), a method and a computer program detect an optical image and generate optical image data of a patient positioning device (20). The device (10) is configured to detect optical image and generate optical image data of a patient positioning device (20) and to determine the position of at least two partial segments (20a; 20b; 20c; 20d) of the patient positioning device (20) on the basis of the image data. The device (10) has, further, an interface (16) for outputting information on the position of the at least two partial segments (20a; 20b; 20c; 20d).

Abstract: A method and system for computing blood flow in coronary arteries from medical image data disclosed. Patient-specific anatomical measurements of a coronary artery tree are extracted from medical image data of a patient. A reference radius is estimated for each of a plurality of branches in the coronary artery tree from the patient-specific anatomical measurements of the coronary artery tree. A flow rate is calculated based on the reference radius for each of the plurality of branches of the coronary artery tree. A plurality of total flow rate estimates for the coronary artery tree are calculated. Each total flow rate estimate is calculated from the flow rates of branches of particular generation in the coronary artery tree. A total flow rate of the coronary artery tree is calculated based on the plurality of total flow rate estimates. The total flow rate of the coronary artery tree can be used to derive boundary conditions for simulating blood flow in the coronary artery tree.

Abstract: A magnetic-resonance imaging apparatus of an embodiment includes acquiring circuitry and processing circuitry. The acquiring circuitry acquires a magnetic resonance signal that is generated from a subject. The processing circuitry creates a phase image based on the magnetic resonance signal. The processing circuitry sets a combination of a plurality of filters that are used to remove a phase variation derived from a background magnetic field according to a region in the phase image. The processing circuitry removes a phase variation derived from the background magnetic field from the phase image by using the combination of the filters.

Abstract: The disclosure relates to phenotype analysis of cellular image data using a machine-learned, deep metric network model. An example method includes receiving, by a computing device, a target image of a target biological cell having a target phenotype. Further, the method includes obtaining, by the computing device, semantic embeddings associated with the target image and each of a plurality of candidate images of candidate biological cells each having a respective candidate phenotype. The semantic embeddings are generated using a machine-learned, deep metric network model. In addition, the method includes determining, by the computing device, a similarity score for each candidate image. Determining the similarity score for a respective candidate image includes computing a vector distance between the respective candidate image and the target image. The similarity score for each candidate image represents a degree of similarity between the target phenotype and the respective candidate phenotype.

Abstract: An intravascular imaging system includes a transducer capable of generating raw data representative of the structure of a patient's vasculature. The system includes an imaging engine for receiving the raw data and generating enhanced data for presentation to a user. The imaging engine includes a coherence filter, an envelope detection module having one or more envelope detectors, and a spatial filter for processing data in various stages. Such stages of processing in the imaging engine act to reduce high frequency noise, generate low frequency data, reduce low frequency noise, and display low frequency data with an improved signal-to-noise ratio. The system can include an image generator for generating an image based on enhanced data and a display for displaying the generated image.

Abstract: The present disclosure relates to calibration assemblies and methods for use with an imaging system, such as an endoscopic imaging system. A calibration assembly includes: an interface for constraining engagement with an endoscopic imaging system; a target coupled with the interface so as to be within the field of view of the imaging system, the target including multiple of markers having calibration features that include identification features; and a processor configured to identify from first and second images obtained at first and second relative spatial arrangements between the imaging system and the target, respectively, at least some of the markers from the identification features, and using the identified markers and calibration feature positions within the images to generate calibration data.

Abstract: A method and system for creating a depth signature from plural images for providing watermark information related to the images. The method comprises analyzing a pair of images, each image containing a plurality of elements, identifying a first element in one of the pair of images, identifying plural elements in the other of the pair of images. The method further comprises measuring a disparity parameter between the first element and a set of the plural elements, matching the first element from the set of plural elements, the matched second element having the smallest measured disparity parameter, and computing a signature based at least in part on the measured disparity between the first and second elements.

Abstract: Described is a system for finding open space for robot exploration. During operation, the system designates a straight forward direction as a default direction. It is determined if a filtered 3D point cloud has a sufficient number of cloud points. If not, the system determines if an obstacle is too close in a previous time. If so, a backward direction is set as a target direction and if not, the straight forward direction is set as the target direction. Alternatively, if there are a sufficient number of points, then calculate a distance of each point to a sensor center and determine if a number of times that the distance is smaller than a distance threshold is greater than a fixed number. The system either sets the backward direction as the target direction or estimates an openness of each candidate direction until a candidate direction is set as the target direction.

Abstract: According to an embodiment of the present technology, there is provided an image processing apparatus including a parallax information generation unit. The parallax information generation unit generates parallax information based on a first phase difference distribution and a second phase difference distribution, the first phase difference distribution being generated on a pixel by pixel basis for the first parallax image and the second parallax image, the second phase difference distribution being generated on a sub-pixel by sub-pixel basis based on the first phase difference distribution.

Abstract: Apparatuses, methods, systems, and program products are disclosed for reducing storage using commonalities. One or more features that are common among each of a plurality of images is determined. One or more background images are generated based on the one or more common features. The one or more background images are used to recreate each of the plurality of images. One or more common features are modified in each image of the plurality of images prior to saving each image. Each of the plurality of images with the modified features is a foreground image.

Abstract: According to an aspect of the embodiments, a search region is set for a recognition target image, cut regions are set at a plurality of positions in the search region, images respectively corresponding to the plurality of set cut regions are extracted, each of the extracted images is compared with dictionary data to detect candidate character information and position information about the cut region that corresponds to the candidate character. Then, the candidate character information that has the highest evaluation value in the detected candidate character information is output as a recognition result, and based on the position information about the cut region corresponding to the recognition result, a search region for a next character is set.

Abstract: Techniques of this disclosure may include processing one or more regions-of-interest (ROI) of an input image through a model of a display processor, calculating a first data integrity check value on the one or more ROI of the input image after processing through the model, processing the input image by the display processor, calculating a second data integrity check value on the one or more ROI by the display processor after the display processor processes the input image, comparing the first data integrity check value to the second data integrity check value, and generating an interrupt if the comparison indicates that the first data integrity check value and the second data integrity check value do not match.

Abstract: A surveillance system 1, which is an example of a surveillance system to which the present invention is applied, includes a surveillance region storage means 2 and an image analyzing means 3. Also, the surveillance system 1 includes an effective area information storage means 4 and an object criterion information storage means 5. A detection subject can be detected efficiently by setting a first step criterion of whether or not a portion of an object in an image is included in a range of a surveillance region and a predetermined second step criterion and determining whether or not these criteria are met.

Abstract: The present disclosure relates to systems, methods, devices, and non-transitory computer-readable storage medium for segmenting three-dimensional images. In one implementation, a computer-implemented method for segmenting a three-dimensional image is provided. The method may include receiving the three-dimensional image acquired by an imaging device, and creating a first stack of two-dimensional images from a first plane of the three-dimensional image and a second stack of two-dimensional images from a second plane of the three-dimensional image. The method may further include segmenting, by a processor, the first stack and the second stack of two-dimensional images using at least one neural network model. The method may also include determining, by the processor, a label map for the three-dimensional image by aggregating the segmentation results from the first stack and second stack.

Abstract: The present invention relates to a device for segmenting an image (12) of a subject (14) comprising a data interface (16) for receiving an image (12) of said subject (14) and at least one contour (18) or at least one part of a contour (18), said contour (18) indicating a structure (19) within said image (12), a selection unit (20) for selecting a region (22) in said image (12) divided into a first and a second disjoint part (24, 26) by said contour (18) or said part of said contour (18), said selected region (22) comprising a drawn region and/or a computed region, a classifier (28) for classifying said selected region (22) based on at least one parameter for image segmentation, an analysis unit (29) for defining an objective function based on the classification result, an optimizer (30) for optimizing said parameter set by varying an output of said objective function and an image segmentation unit (32) for segmenting said image (12) using said optimized parameter set.

Abstract: The present disclosure provides a method for acquiring a retina structure from an optical coherence tomographic image and a system thereof.

Abstract: A system and method are provided for generating time resolved series of angiographic volume data having flow information. The system and method are configured to receive angiographic volume data acquired from a subject having received a dose of a contrast agent using an imaging system and process the angiographic volume data to generate angiographic volume images. The angiographic volume data is processed to derive flow information by determining a distance between two points along a vessel in the angiographic volume images and determining a phase at each of the two points along the vessel in the angiographic volume images. A flow direction or a velocity of flow within the vessel is determined using the distance between the two points along the vessel and the phase at each of the two points along the vessel.

Abstract: According to at least one example embodiment, a method and corresponding apparatus of pruning video data comprise detecting motion areas within video frames of the video data based on short-term and long-term variations associated with content of the video data. Motion events, associated with the content of the video data, are then identified based on the motion areas detected, corresponding filtered motion areas, and variation patterns associated with the video data. Based on the motion events identified, a storage pattern for storing video frames of the video data is determined. The video frames are stored according to the determined storage pattern.

Abstract: Various embodiments are disclosed for detecting, tracking and counting objects of interest in video. In an embodiment, a method of detecting and tracking objects of interest comprises: obtaining, by a computing device, multiple frames of images from an image capturing device; detecting, by the computing device, objects of interest in each frame; accumulating, by the computing device, multiple frames of object detections; creating, by the computing device, object tracks based on a batch of object detections over multiple frames; and associating, by the computing device, the object tracks over consecutive batches.

Abstract: In one embodiment, the disclosure relates to a method for inspecting a load (101) in a container (100), comprising: classifying (S2) one or more patches (11) of a digitized inspection image (10), the digitized inspection image (10) being generated by an inspection system (1) configured to inspect the container (100) by transmission of inspection radiation (3) from an inspection radiation source (31) to an inspection radiation detector (32) through the container (100), wherein the classifying (S2) comprises: extracting (S21) one or more texture descriptors (V, P) of a patch (11), and classifying (S22) the patch (11), by comparing the one or more extracted texture descriptors (V, P) of the patch (11) to respective one or more reference texture descriptors (Vr, Wr, Pr) corresponding to respective one or more classes (202) of reference items (201), the one or more reference texture descriptors (Vr, Wr, Pr) of each class of reference items (201) being extracted from one or more reference images (20) of the one or

Abstract: Breast density is a significant breast cancer risk factor measured from mammograms. Disclosed is a methodology for converting continuous measurements of breast density and calibrated mammograms into a four-state ordinal variable approximating the BI-RADS ratings. In particular, the present disclosure is directed to a calibration system for a specific full field digital mammography (FFDM) technology. The calibration adjusts for the x-ray acquisition technique differences across mammograms resulting in standardized images. The approach produced various calibrated and validated measures of breast density, one of which assesses variation in the mammogram referred to as Vc (i.e. variation measured from calibrated mammograms). The variation in raw mammograms [i.e. Vr] is a valid breast density risk factor in both FFDM in digitized film mammograms.

Abstract: A method of generating a descriptor of at least part of an image includes receiving image data representing the at least part of the image. The image data is processed to identify at least one texture characteristic of the at least part of the image, thereby generating texture data indicative of a texture of the at least part of the image. The texture data is processed with the image data, thereby generating weighted texture data. A descriptor of the at least part of the image is generated using the weighted texture data.

Abstract: A computing device includes a memory for storing instructions and a processor. The processor is configured to execute the instructions to identify a location for a graphical element in a predefined three-dimensional scene using depth information of content included in two or more different two-dimensional representations of the predefined three-dimensional scene. The processor is also configured to produce two or more different two-dimensional representations of the predefined three-dimensional scene including the graphical element.

Abstract: A verification method for people counting includes steps of displaying a people counting video by a display device, wherein the people counting video shows an entry and exit boundary and an accumulated number of persons; when at least one person exists in the people counting video, displaying an initial position and a current position of each of the at least one person by the display device; determining whether each of the at least one person passes across the entry and exit boundary according to the initial position and the current position of each of the at least one person by a user, so as to determine whether the accumulated number of persons is incorrect; and when the user determines that the accumulated number of persons is incorrect, receiving a modified number of persons from the user by an input device.

Abstract: A method to locate material bodies on an at least 2-dimensional occupancy grid G, having a first resolution stepsize RG, that includes a set of cells represented by vertices and segments connecting these vertices. The method uses a sensor for detecting an obstacle which is positioned at source point S, and includes at least the following steps: acquisition by the sensor of a measurement of the position of a material body detected at a point F; defining the coordinates of a point M by using a space discretized with the aid of a spatial stepsize ? which is finer than the resolution stepsize RG, initializing an integer, error parameter, and calculating the value of the error parameter for at least one first vertex of the cell of the current grid.

Abstract: An embodiment of the invention is directed to a system that comprises one or more processors and a memory communicatively coupled to the one or more processors. Herein, the memory including logic that, upon executing by the one or more processors and in response to receiving information that uniquely identifies a vehicle, automatically generating a plurality of images of the vehicle. A vehicle identification number (VIN) may be used as the information that uniquely identifies a vehicle and causes automatic generation of the interior and exterior images for that specific vehicle.

Abstract: A user interface adaptation module identifies a dominant color of a portion selection of a frame of a video and, based on the dominant color, generates colors for components of a user interface in which the video is displayed. The colors of the user interface components are set based upon the generated colors and upon context information such as a playing state of the video. The setting of the component colors in this way allows the user interface to adjust to complement both the played content of the video and the video's context. In one embodiment, the dominant color is identified by partitioning individual pixels of the portion selection based on their respective colors. In one embodiment, a set of primary color variants is generated based on the dominant color, and different colors are generated for each type of user interface component based on the different primary color variants.

Abstract: Embodiments of the present disclosure are directed to a system for generating three-dimensional images of a target region of a patient. The system may include at least one computer system. The computer system may be configured to receive a plurality of non-parallel projection images of the target region of the patient, convert the plurality of non-parallel projection images into a non-spatial domain, reconstruct a three-dimensional image from the plurality of non-parallel projection images in the non-spatial domain, and convert the reconstructed three-dimensional image from the non-spatial domain to the spatial domain.

Abstract: In a method and an evaluation device for the evaluation of projection data of an object being examined, which are determined along a trajectory in a multiplicity of projection positions relative to a co-ordinate origin, a particular trajectory function is determined for the projection positions, for each of a multiplicity of positions from a reconstruction region of dimension n by establishing an offset (d) and a direction vector at the co-ordinate origin, establishing a hyperplane of dimension n?1 which runs perpendicular to the direction vector and has an offset to the co-ordinate origin, establishing a number of intersection points where the hyperplane intersects the trajectory, establishing a derivative vector of the trajectory according to its trajectory path and calculating the derivative vector in the projection position, and establishing an absolute value of a scalar product between the derivative vector and the position and dividing the absolute value by the number.

Abstract: [Problem] To further reduce artifacts of a reconstructed image.

Abstract: Systems, methods, and software are disclosed herein for supporting directional stamping. In an implementation, an input stroke is received on a canvas in a user interface to an application. The application identifies at least a directional effect with which to render each of a set of discontinuous objects along a continuous path taken by the input stroke on the canvas. The application then renders the set of discontinuous objects on the canvas along the continuous path with at least the directional effect identified for each discontinuous object.

Abstract: The disclosed embodiments provide a system that processes data. During operation, the system obtains a data set and metadata corresponding to a data model, wherein the data model includes a metric and a set of dimensions associated with the metric. Next, the system applies a set of rules to the data set to obtain a deconstruction of the metric by the set of dimensions. Finally, the system displays the deconstruction in one or more charts to a user independently of a domain of the data set.

Abstract: Visibility may be analytically resolved rather than using point-sampling, thereby entirely avoiding geometric aliasing and the need to store multiple samples per pixel. By relying on existing techniques for shading, i.e., by shading once per fragment and focusing on visibility, visual results may be equivalent to multi-sampled anti-aliasing (MSAA) using an infinite sampling rate in some embodiments.

Abstract: A method for applying a graphic effect in an electronic device is provided. The method includes receiving an input of a filling line that indicates attribute information of a graphic effect to be applied to at least a partial area of an image displayed in a screen, identifying an attribute of the received filling line, and applying the graphic effect corresponding to the identified attribute of the filling line to at least the partial area of the image.

Abstract: Particular embodiments of a computing device receive an indication of a character encoding system and a combining-character sequence. The character encoding system may comprise one or more ranges of character elements. The combining-character sequence may comprise two or more character elements. The two or more character elements may comprise at least one base letter and one or more combining marks. A mapping code may be determined for the combining-character sequence. If no mapping code exists, a next-available mapping code may be determined, and the combining-character sequence may be stored in association with the next-available mapping code in a data store on the computing device. A corresponding glyph may be determined based on the mapping code—if no glyph exists, the glyph may be generated or retrieved from a server and stored in association with the mapping code in the data store. Information may be provided to display the glyph.

Abstract: A method, apparatus, and system provide the ability to detect an object framework in an image. A frame (of an image) is obtained. The image is pre-processed to smooth the image. Edges in the image are detected and an edge map is generated. Straight lines are detected from the detected edges in the edge map. One or more quadrangles are assembled from the detected straight lines. The quadrangles are sorted. One of the one or more quadrangles are selected based on the sorting. A selected quadrangle is returned to the user.

Abstract: There is provided an information processing apparatus that is capable of generating image data including the original image data, which reflects the geometric features of the original image data, the information processing apparatus including: an acquisition unit and a generation unit. The acquisition unit acquires geometric feature information extracted by analyzing first image data. The generation unit generates second image data and third image data, the second image data being generated on the basis of the geometric feature information, the third image data including a first area and a second area, corresponding image data being placed in the first area, the corresponding image data corresponding to the first image data, the second image data being placed in the second area.

Abstract: Image distractor detection and processing techniques are described. In one or more implementations, a digital medium environment is configured for image distractor detection that includes detecting one or more locations within the image automatically and without user intervention by the one or more computing devices that include one or more distractors that are likely to be considered by a user as distracting from content within the image. The detection includes forming a plurality of segments from the image by the one or more computing devices and calculating a score for each of the plurality of segments that is indicative of a relative likelihood that a respective said segment is considered a distractor within the image. The calculation is performed using a distractor model trained using machine learning as applied to a plurality images having ground truth distractor locations.

Abstract: Apparatus, including a retaining structure (54), positioned near a subject's eye that has a pupil with a diameter, an optical combiner (52A) mounted on the structure before the eye, and a pixelated screen (60A) having an array of variably transparent pixels coating the combiner. There is an image capturing device (68A) mounted on the structure to capture an image of a scene viewed by the eye, and a projector (64A) is mounted on the structure to project at least one of a portion of the captured image and a stored image onto a section of the screen at a selected location thereof. A processor (26) renders the screen section at least partially opaque, selects the section location in response to a region of interest in the scene identified by analysis of the captured image, and determines a dimension of the section in response to the pupil diameter.

Abstract: Using curves to emulate soft body deformation in a computer-generated character is disclosed. A method can include accessing a reference model mapped to one or more deformation curves for the character. The reference model can include a mesh of vertices representing a soft body layer of the character. The deformation curve can include multiple sample points selected for mapping. Each mesh vertex on the model can be mapped to each sample point on the curve to establish a relationship between them for deformation. The method can also include receiving a movement of one or more sample points on the curve to a desired deformation position. The method can further include calculating primary and secondary movements of the mesh vertices on the model based on the movements of sample points. The method can move the mesh vertices as calculated to a desired deformation position and output the reference model with the moved vertices for rendering to emulate the soft body deformation of the character.

Abstract: One embodiment of the present invention includes a double solve unit that configures a kinematic chain representing an animated character. The double solve unit generates a first solution for the kinematic chain based on a first solving order. While generating the first solution, the doubles solve unit determines the recursion depth of each output connector included in the kinematic chain. Subsequently, the double solve unit identifies any output connectors for which the recursion length exceeds a corresponding expected recursion depth—indicating that a custom recursive dependency exists that is not reflected in the first solution. For these custom recursive output connectors, the double solve unit creates a second solving order and generates a more accurate solution.

Abstract: One embodiment of the present invention sets forth a method for accessing texture objects stored within a texture memory. The method comprises the steps of receiving a texture bind request from an application program, wherein the texture bind request includes an object identifier that identifies a first texture object stored in the texture memory and an image identifier that identifies a first image unit, binding the first texture object to the first image unit based on the texture bind request, receiving, within a shader engine, a first shading program command from the application program for performing a first memory access operation on the first texture object, wherein the memory access operation is a store operation or atomic operation to an arbitrary location in the image, and performing, within the shader engine, the first memory access operation on the first texture object via the first image unit.

Abstract: Various embodiments are generally directed to techniques to generate stereoscopic views of a scene for purposes of providing an illusion of depth to the scene. An apparatus for stereoscopic rendering includes a processor component; a vertex shader to generate a plurality of vertices corresponding to primitives that are a representation of the scene to be displayed, the vertex shader transforming a first instance of the plurality of vertices to a first projected space in a first portion of a two-dimensional (2D) area and transforming a second instance of the plurality of vertices to a second projected space in the 2D area, the first portion of the 2D area corresponding to a first stereoscopic view of the scene and the second portion of the 2D area corresponding to a second stereoscopic view of the scene.

Abstract: A graphics processing pipeline comprises a tessellation stage 10 operable to tessellate a patch representing some or all of an object to be rendered, so as to generate positions for a set of vertices for one or more output primitives, and a primitive assembly stage 20 operable to assemble one or more output primitives for processing using the positions for a set of vertices generated by the tessellation stage and pre-defined information defining the connectivity between at least some of the vertices of the set of vertices.

Abstract: A first request is received from a window checker, requesting to read cell data from a window buffer or write cell data into the window buffer, where the first request contains at least first cell index. A second request is received from a window releaser, requesting to read cell data from the window buffer or write cell data into the window buffer, where the second request contains at least second cell index. A register stores the first cell index, the second cell index, a first lock flag indicating whether the window checker has read cell data but hasn't written cell data back and a second lock flag indicating whether the window releaser has read cell data but hasn't written cell data back. One of the requests is granted according to the first and second cell indices and the first and second lock flags.

Abstract: A texture processing unit includes a controller configured to obtain a texture coordinate and spatial frequency information for each channel of a texture corresponding to the texture coordinate, and determine a filtering control signal for each channel of the texture based on the spatial frequency information for each channel, and a texture filter configured to perform filtering for each channel of the texture according to the filtering control signal for each corresponding channel.

Abstract: A virtual-reality computing device comprises a pose sensor, a rendering tool, and a display. The pose sensor is configured to measure a current pose of the virtual-reality computing device in a physical space. The rendering tool is configured to receive a holographic animation of a 3D model that includes a sequence of holographic image frames. The rendering tool is also configured to receive a render-baked dynamic lighting animation that includes a sequence of lighting image frames corresponding to the sequence of holographic image frames. The rendering tool also is configured to derive a 2D view of the 3D model with a virtual perspective based on the current pose and texture map a corresponding lighting image frame to the 2D view of the 3D model to generate a rendered image frame of the 2D view with texture-mapped lighting. The display is configured to visually present the rendered image frame.

Abstract: In a computer graphics processing unit (GPU) having a texture unit, when pixel sample locations are based on a non-orthonormal grid in scene space, the texture unit receives texture space gradient values directly, e.g., from a shader unit or generates them from texture coordinates supplied, e.g., by a shader unit, and then applies a transformation to the gradient values configured to adjust the gradient values to those which would arise from the use of a orthonormal screen space grid.

Abstract: A classification method includes: setting a position of a projective point based on information on a domain of definition of a feature value space, using a processor; and projecting a vector present in the feature value space to a sphere present in a space of dimensions higher by at least one dimension than a dimension of the feature value space by using the set position of the projective point, using the processor.

Abstract: A method and an apparatus for adjusting a pose in a face image are provided. The method of adjusting a pose in a face image involves detecting two-dimensional (2D) landmarks from a 2D face image, positioning three-dimensional (3D) landmarks in a 3D face model by determining an initial pose of the 3D face model based on the 2D landmarks, updating the 3D landmarks by iteratively adjusting a pose and a shape of the 3D face model, and adjusting a pose in the 2D face image based on the updated 3D landmarks.