Abstract: An imagery processing system obtains capture inputs from capture devices that might have capture parameters and characteristics that differ from those of a main imagery capture device. By normalizing outputs of those capture devices, potentially arbitrary capture devices could be used for reconstructing portions of a scene captured by the main imagery capture device when reconstructing a plate of the scene to replace an object in the scene with what the object obscured in the scene. Reconstruction could be of one main image, a stereo pair of images, or some number, N, of images where N>2.
Type:
Grant
Filed:
August 26, 2021
Date of Patent:
January 18, 2022
Assignee:
WETA DIGITAL LIMITED
Inventors:
Kimball D. Thurston, III, Peter M. Hillman
Abstract: A system and method for predicting an outcome specific signal (OSS) in test subject images. The method includes detecting the OSS in image data from outcome and control subjects; extracting a volumetric space containing the detected OSS and dividing the extracted volumetric space into a first set of sub-regions; determining a set of image features for the first set of sub-regions; determining a global feature set (GFS) by averaging the set of image features; utilizing a machine learning algorithm to select a subset of discriminant GFS to determine a best signal model (BSM) that distinguishes the outcome and control subjects; extracting volumetric space containing the target anatomy in test subject images and dividing the extracted volumetric space into a second set of sub-regions; and determining the subset of discriminant GFS at each of the second set of sub-regions, and using them in the BSM to generate the predicted OSS.
Abstract: A remote image interpretation management apparatus includes a hardware processor. The hardware processor obtains, from a storage storing evaluation values about quality of image interpretation reports by evaluator and by image interpretation facility and/or image interpretation doctor, evaluation values of evaluators who have evaluated a predetermined number of image interpretation reports or more. Based on the obtained evaluation values of the evaluators, for each of the evaluators, the hardware processor calculates a statistic of the evaluation values of the evaluator and normalizes the evaluation values with the calculated statistic, thereby obtaining normalized evaluation values for the respective evaluators. For each image interpretation facility and/or each image interpretation doctor, the hardware processor calculates a mean value based on the normalized evaluation values of the respective evaluators.
Abstract: A device for extracting dynamic information comprises a convolutional neural network, wherein the device is configured to receive a sequence of data blocks acquired over time, each of said data blocks comprising a multi-dimensional representation of a scene. The convolutional neural network is configured to receive the sequence as input and to output dynamic information on the scene in response, wherein the convolutional neural network comprises a plurality of modules, and wherein each of said modules is configured to carry out a specific processing task for extracting the dynamic information.
Abstract: A device for image processing includes a memory configured to store multiple image frames of a sequence of image frames. The device includes a reference frame accumulator configured to combine a first group of image frames of the sequence of image frames to generate a reference frame. The device also includes a target frame accumulator configured to combine a second group of image frames of the sequence of image frames to generate a target frame. The device includes a difference frame generator configured to generate a difference frame based on subtracting the reference frame from the target frame.
Type:
Grant
Filed:
August 12, 2019
Date of Patent:
December 7, 2021
Assignee:
THE BOEING COMPANY
Inventors:
Kevin R. Paxton, Maurice Masequesmay, Peter Bystrom
Abstract: Disclosed is an image processing apparatus. The present image processing apparatus comprises: an input unit for inputting an image; and a processor for shrinking the inputted image to a predetermined ratio, extracting a visual feature from the shrunken image, performing an image quality enhancement process reflecting the extracted visual feature in the inputted image, repeatedly performing, for a predetermined number of times, the shrinking, the extracting, and the image quality enhancement process on the image that has undergone the image quality enhancement process. The present disclosure relates to an artificial intelligence (AI) system and an application thereof that simulate the functions of a human brain, such as recognition, judgment, etc., by using a machine learning algorithm such as deep learning, etc.
Abstract: A method and apparatus for generating augmented training data for hand pose estimation include receiving source data that is associated with a first lighting condition. Target data that is associated with a second lighting condition is received. A lighting condition translation between the first lighting condition and the second lighting condition is determined. Lighting translated data is generated based on the lighting condition translation and the source data. Augmented training data for hand pose estimation is generated based on the target data and the lighting translated data.
Type:
Grant
Filed:
May 24, 2019
Date of Patent:
November 16, 2021
Assignee:
TENCENT AMERICA LLC
Inventors:
Shih-Yao Lin, Yusheng Xie, Kun Wang, Lianyi Han, Wei Fan
Abstract: A method of authenticating physical activity in a monitored space, comprising: obtaining monitored space activity data from at least one activity detector deployed in the monitored space to capture simultaneously physical activity of a plurality of moving objects in said monitored space; analyzing said monitored space activity data to identify a plurality of spatiotemporal movement patterns in said monitored space; obtaining a plurality of inertial data patterns from each one of a plurality of applications executed in a plurality of mobile devices, each one of said inertial data patterns is recorded using an inertial sensing device installed in one of said plurality of mobile devices, each one of said plurality of mobile devices is associated with one of a plurality of persons; identifying at least one correlation between at least one of said plurality of inertial data patterns and at least one of said plurality of spatiotemporal movement patterns; authenticating said physical activity according to said at le
Abstract: The technology described in this document can be embodied in a method for preventing access to a secure system based on determining that a subject is an alternative representation of a live person. The method includes illuminating a first subject with electromagnetic radiation using a first wavelength range that cause fluorescence in human tissue. The fluorescence is in a second wavelength range different from the first wavelength range. The method also includes receiving, responsive to illuminating the first subject and using one or more sensors, electromagnetic radiation emitted from the first subject, and determining that the received electromagnetic radiation is outside the second wavelength range. Responsive to determining that the received electromagnetic radiation is outside the second wavelength range, the method further includes identifying the first subject as an alternative representation of a live person, and preventing access to the secure system in response.
Abstract: An image processing apparatus includes: an acquisition unit that acquires a radiographic image of a breast; and a derivation unit that derives a percentage of mammary glands of a breast image in the radiographic image acquired by the acquisition unit on the basis of an amount of incident radiation on a direct region which is a region directly irradiated with radiation without passing through the breast and an amount of incident radiation on a mammary gland tissue pixel obtained by a portion of the breast which is estimated to be composed of only mammary gland tissues in the radiographic image.
Abstract: An imagery processing system determines alternative pixel color values for pixels of captured imagery where the alternative pixel color values are obtained from alternative sources. A main imagery capture device, such as a camera, captures main imagery such as still images and/or video sequences, of a live action scene. Alternative devices capture imagery of the live action scene, in some spectra and form, and that alternative imagery is processed to provide user-selectable alternatives for pixel ranges from the main imagery.
Type:
Grant
Filed:
January 14, 2021
Date of Patent:
November 2, 2021
Assignee:
WETA DIGITAL LIMITED
Inventors:
Kimball D. Thurston, III, Peter M. Hillman
Abstract: A system and method include execution of a first scan to acquire a first PET dataset, back-projection of the first PET dataset to generate a first histo-image, input of the first histo-image to a trained neural network, and reception of a first output image from the trained neural network.
Type:
Grant
Filed:
October 3, 2019
Date of Patent:
November 2, 2021
Assignee:
Siemens Medical Solutions USA, Inc.
Inventors:
William Whiteley, Vladimir Y. Panin, Deepak Bharkhada
Abstract: An imagery processing system obtains capture inputs from capture devices that might have capture parameters and characteristics that differ from those of a main imagery capture device. By normalizing outputs of those capture devices, potentially arbitrary capture devices could be used for reconstructing portions of a scene captured by the main imagery capture device when reconstructing a plate of the scene to replace an object in the scene with what the object obscured in the scene. Reconstruction could be of one main image, a stereo pair of images, or some number, N, of images where N>2.
Type:
Grant
Filed:
January 11, 2021
Date of Patent:
October 19, 2021
Assignee:
WETA DIGITAL LIMITED
Inventors:
Kimball D. Thurston, III, Peter M. Hillman
Abstract: An image processing apparatus includes: an acquisition unit that acquires a plurality of radiographic images of the same breast which have captured in a plurality of different states related to compression of the breast; and a derivation unit that derives, on the basis of an amount of incident radiation derived from a value of a fat tissue pixel in a radiographic image in which the fat tissue pixel obtained by a portion of the breast which is estimated to be composed of only fat tissues is included in a breast image among the plurality of radiographic images acquired by the acquisition unit, a percentage of mammary glands of a breast image in a radiographic image different from the radiographic image used to derive the amount of incident radiation.
Abstract: A method for training a person recognition model using images from a camera 100, wherein the method has at least a reading-in step in which a detection signal 135 representing a detected person within a monitoring area of at least the camera 100 in a camera network is read in. The method also has at least a collecting step in which a plurality of image signals 140 from the camera 100 are collected using the detection signal 135 which has been read in, wherein the collected image signals 140 represent a recorded image section from each image from the camera 100. Finally, the method has at least an adapting step in which the person recognition model is adapted using the collected image signals 140 in order to recognize the detected person in an image from the camera 100 or from an at least second camera in the camera network.
Abstract: An apparatus of controlling a region of interest (ROI) in an image and a method for controlling the same are provided to determine a region of interest (ROI) in a forward-view image based on braking information and steering information of the vehicle, and obtain driving assistance information from the ROI image. The apparatus includes an image acquisition device configured to acquire a forward-view image by capturing an image about a forward region of a vehicle, a steering information acquisition device configured to acquire steering information by detecting a steering direction and a steering angle of the vehicle, a braking information acquisition device configured to acquire braking information by detecting a braking or non-braking state and a deceleration of the vehicle, and a controller configured to determine a region of interest (ROI) within the forward-view image based on at least one of the steering information or the braking information of the vehicle.
Abstract: According to one embodiment, a sorting system has a delivery processing apparatus, a video coding terminal, and a recognition support apparatus. The recognition support apparatus has an information management portion, a correct solution derivation portion, and a machine learning portion. The information management portion acquires an image obtained by imaging a delivery object and keying information. The correct solution derivation portion derives respective correct solutions for a plurality of processings for the image obtained by imaging the delivery object, based on the keying information acquired by the information management portion. The machine learning portion performs machine learning using the respective correct solutions for the plurality of processings derived by the correct solution derivation portion, to adjust the plurality of processings.
Type:
Grant
Filed:
January 4, 2018
Date of Patent:
August 24, 2021
Assignees:
Kabushiki Kaisha Toshiba, Toshiba Infrastructure Systems & Solutions Corporation
Abstract: A system and method for analyzing scan data of a lung and presenting a lung candidacy report. The lung candidacy report includes determinations represented visually of whether lung lobes are suitable candidates for a bronchoscopy guided lung volume reduction procedure. The lung candidacy report includes emphysema values and fissure integrity determined from the scan data.
Abstract: A method of recognizing a feature of an image may include receiving an input image including an object; extracting first feature information using a first layer of a neural network, the first feature information indicating a first feature corresponding to the input image among a plurality of first features; extracting second feature information using a second layer of the neural network, the second feature information indicating a second feature among a plurality of second features, the indicated second feature corresponding to the first feature information; and recognizing an element corresponding to the object based on the first feature information and the second feature information.
Abstract: Systems and techniques for facilitating image analysis using deviation from normal data are presented. In one example, a system generates atlas map data indicative of an atlas map that includes a first portion of patient image data from a plurality of reference patients and a second portion of the patient image data from a plurality of target patients. The first portion of the patient image data is matched to a corresponding age group for a set of patient identities associated with the first portion of the patient image data. The system also generates deviation map data that represents an amount of deviation for the second portion of the patient image data compared to the first portion of the patient image data. Furthermore, the system trains a neural network based on the deviation map data to determine one or more clinical conditions.