Abstract: A user terminal device is provided. The user terminal device includes a plurality of different types of sensors, a storage unit configured to store object information, and a controller configured to acquire sensing results of the plurality of sensors, determine a plurality of object categories respectively corresponding to the sensing results, and compare objects belonging to the plurality of object categories to estimate an object commonly belonging to the object categories as a recognition result.
Abstract: A magnetic resonance imaging apparatus according to an embodiment includes processing circuitry. The processing circuitry generates an image based on a magnetic resonance signal from a subject. The processing circuitry generates a susceptibility image representing magnetic susceptibility of the subject from a phase component contained in a plurality of pixels in the image. The processing circuitry generates an artifact component of the susceptibility image based on a frequency signal obtained by frequency transform of the susceptibility image. The processing circuitry generates an artifact component-removed susceptibility image by removing the artifact component from a susceptibility image generated based on the magnetic resonance signal.
Abstract: A multimodal and real-time method for filtering sensitive content, receiving as input a digital video stream, the method including segmenting digital video into video fragments along the video timeline; extracting features containing significant information from the digital video input on sensitive media; reducing the semantic difference between each of the low-level video features, and the high-level sensitive concept; classifying the video fragments, generating a high-level label (positive or negative), with a confidence score for each fragment representation; performing high-level fusion to properly match the possible high-level labels and confidence scores for each fragment; and predicting the sensitive time by combining the labels of the fragments along the video timeline, indicating the moments when the content becomes sensitive.
Type:
Grant
Filed:
June 30, 2016
Date of Patent:
January 29, 2019
Assignees:
SAMSUNG ELETRÔNICA DA AMACÔNIA LTDA., UNIVERSIDADE ESTADUAL DE CAMPINAS
Inventors:
Sandra Avila, Daniel Moreira, Mauricio Perez, Daniel Moraes, Vanessa Testoni, Siome Goldenstein, Eduardo Valle, Anderson Rocha
Abstract: According to an embodiment, a grid is provided between an X-ray generator and a flat panel detector. Processing circuitry configured to convert original image based on X-rays having passed through the grid and detected into a plurality of pieces of frequency band data, remove interference fringes contained in at least one piece of frequency band data among the pieces of frequency band data, reduce noise contained in the pieces of frequency band data, correct a scattered radiation of the original image based on a scattered radiation contained in the X-rays having passed through the grid and a scattered radiation contained in X-rays having passed through a grid that removes scattered radiation to a larger extent than the grid, and synthesize a plurality of pieces of frequency band data to generate image.
Abstract: A method for correction of an x-ray image recorded with an x-ray device with an anti-scatter grid for effects of the anti-scatter grid is provided. The anti-scatter grid has a spatially periodically repeating geometrical embodiment, and a calibration image recorded without an imaging object is used. The calibration image and the x-ray image are transformed by a transformation into the position frequency space. In the position frequency space, adaptation parameters describing changes of the calibration image optimizing a measure of matching between the x-ray image and the calibration image are established. For correction, the adapted calibration image is subtracted from the x-ray image, and the x-ray image is transformed back into the position space again using an inverse of the transformation.
Abstract: Systems and methods for generating and distributing photo filters are described. A photo filter publication application receives filter data and object criteria and generates a photo filter based on the filter data. The photo filter is associated with satisfaction of the object criteria. A photo filter engine then identifies that a client device has taken a photograph. The photo filter engine then provides the photo filter to the client device based on the photograph including an object that satisfies the object criteria. The photo filter may then be displayed as an option on a user interface of the client device. The object criteria may include associations between an object and a source of image data, for example, a brand of a merchant in which case the associated photo filter may include images associated with the brand of the merchant.
Type:
Grant
Filed:
July 27, 2017
Date of Patent:
December 18, 2018
Assignee:
Snap Inc.
Inventors:
Sheldon Chang, Chamal Samaranayake, Timothy Michael Sehn, Rong Yan
Abstract: A method is provided that determines velocity encoding direction of volumetric image data sets comprising three-directional velocity information (V0, V1, V2) of a target volume, which involves: a) defining a coordinate system (X, Y, Z); b) determining all the possible arrangements of the three velocity components (V0, V1, V2) along the three coordinate axes (X, Y, Z); c) determining reference point or points in the target volume either automatically or upon user input; d) determining streamlines for each point for all possible combinations of velocity components as determined in b); and e) considering as velocity encoding direction the arrangement of the three velocity components corresponding to the streamlines having the longest length or a length above a threshold. A corresponding apparatus and computer program are also disclosed.
Type:
Grant
Filed:
April 19, 2017
Date of Patent:
December 4, 2018
Assignee:
Pie Medical Imaging B.V.
Inventors:
Leon Ledoux, Bas Weijers, Jean-Paul Aben
Abstract: A method and apparatus of displaying a magnified image comprising obtaining an image of a scene using a camera with greater resolution than the display, and capturing the image in the native resolution of the display by either grouping pixels together, or by capturing a smaller region of interest whose pixel resolution matches that of the display. The invention also relates to a method whereby the location of the captured region of interest may be determined by external inputs such as the location of a person's gaze in the displayed unmagnified image, or coordinates from a computer mouse. The invention further relates to a method whereby a modified image can be superimposed on an unmodified image, in order to maintain the peripheral information or context from which the modified region of interest has been captured.
Type:
Grant
Filed:
March 31, 2017
Date of Patent:
November 13, 2018
Assignee:
eSight Corp.
Inventors:
ReJean J. Y. B. Munger, Robert G. Hilkes, Marc Perron, Nirmal Sohi