Abstract: A metrology system for obtaining a measurement representative of a thickness of a layer on a substrate includes a camera positioned to capture a color image of at least a portion of the substrate. A controller is configured to receive the color image from the camera, store a predetermined path in a coordinate space of at least two dimension including a first color channel and a second color channel, store a function that provides a value representative of a thickness as a function of a position on the predetermined path, determine a coordinate of a pixel in the coordinate space from color data in the color image for the pixel, determine a position of a point on the predetermined path that is closest to the coordinate of the pixel, and calculate a value representative of a thickness from the function and the position of the point on the predetermined path.

Abstract: A method and device for image processing, and storage medium are provided. In the method, an initial image I is acquired; a set of m predetermined tone-mapping functions is provided; a pixel I(i) of the initial image is selected; a pixel weight w(i) for the selected pixel I(i) is determined based on pixel information of at least the selected pixel; for each tone-mapping function, a tone-mapping function weight is determined based on the pixel weight; each tone-mapping function is applied to the selected pixel I(i) and weighting the result with the respective tone-mapping function weight; the sum of the weighted result as final pixel I?(i) is determined.

Abstract: This document generally describes systems, methods, devices, and other techniques related to speaker verification, including (i) training a neural network for a speaker verification model, (ii) enrolling users at a client device, and (iii) verifying identities of users based on characteristics of the users' voices. Some implementations include a computer-implemented method. The method can include receiving, at a computing device, data that characterizes an utterance of a user of the computing device. A speaker representation can be generated, at the computing device, for the utterance using a neural network on the computing device. The neural network can be trained based on a plurality of training samples that each: (i) include data that characterizes a first utterance and data that characterizes one or more second utterances, and (ii) are labeled as a matching speakers sample or a non-matching speakers sample.

Abstract: Disclosed are systems and methods that convert digital video data, such as two-dimensional digital video data, into a natural language text description describing the subject matter represented in the video. For example, the disclosed implementations may process video data in real-time, near real-time, or after the video data is created and generate a text-based video narrative describing the subject matter of the video. In addition, the disclosed implementations may also support a question and answer session in which a user may submit queries about the subject matter of one or more videos and the disclosed implementations will present natural language responses based on the subject matter of the video and any corresponding context.

Abstract: Systems and methods for reducing error from noisy data received from a high frequency sensor by fusing received input with data received from a low frequency sensor by collecting a first set of dynamic inputs from the high frequency sensor, collecting a correction input point from the low frequency sensor, and adjusting a propagation path of a second set of dynamic inputs from the high frequency sensor based on the correction input point either by full translation to the correction input point or dampened approach towards the correction input point.

Abstract: A method of detecting and responding to a visitor to a smart home environment via an electronic greeting system of the smart home environment, including determining that a visitor is approaching an entryway of the smart home environment; initiating a facial recognition operation while the visitor is approaching the entryway; initiating an observation window in response to the determination that a visitor is approaching the entryway; obtaining context information from one or more sensors of the smart home environment during the observation window; and at the end of the time window, initiating a response to the detected approach of the visitor based on the context information and/or an outcome of the facial recognition operation.

Abstract: A computer implemented method of processing a medical image is disclosed. The method includes receiving a medical image comprising a first plurality of pixels each having an initial pixel value. For each of the first plurality of pixels, a filtering operation is applied to the pixel to generate a filtered pixel value for the pixel based on the initial pixel values of pixels that surround the pixel in the medical image. For each of the first plurality of pixels, a comparison of the initial pixel value with the filtered pixel value is performed. The method comprises, for each of the first plurality of pixels, determining, based on the comparison, whether or not to categorize the pixel as an erroneous pixel; and for each of the first plurality of pixels for which it is determined to categorize the pixel as an erroneous pixel, categorizing the pixel as an erroneous pixel.

Abstract: Self-supervised training of machine learning (“ML”) algorithms for reconstruction in inverse problems are described. These techniques do not require fully sampled training data. As an example, a physics-based ML reconstruction can be trained without requiring fully-sampled training data. In this way, such ML-based reconstruction algorithms can be trained on existing databases of undersampled images or in a scan-specific manner.

Abstract: A method for image-guided agriculture includes receiving images; processing the images to generate reflectance maps respectively corresponding to spectral bands; synthesizing the reflectance maps to generate a multispectral image including vegetation index information of a target area; receiving crop information in regions of the target area; and assessing crop conditions for the regions based on the identified crop information and the vegetation index information.

Abstract: This application provides an apparatus and method for detecting tab folds, and an image analyzer. The apparatus for detecting tab folds includes: a first image obtaining module, configured to obtain a first image of a first lateral face of tabs of a battery cell; a second image obtaining module, configured to obtain a second image of a second lateral face of the tabs, where the second lateral face is different from the first lateral face; and an image analyzer, configured to obtain, based on the first image, a first number of layers of the tabs corresponding to the first lateral face, and obtain, based on the second image, a second number of layers of the tabs corresponding to the second lateral face, and determine, based on at least one of the first number of layers or the second number of layers, whether the tabs are in a folded state.

Abstract: An exemplary system, method, and computer-accessible medium for detection of structural disorder(s) of patient(s) can be provided which can include, for example, receiving magnetic resonance imaging (MRI) information of the portion(s), generating gadolinium (“Gd”) enhanced map(s) based on the MRI information using a machine learning procedure(s), and detecting the structural disorder(s) of the patient(s) based on a GD contrast of the Gd enhanced map(s). The Gd enhanced map(s) can be a full dosage Gd enhanced map. The machine learning procedure can be a convolutional neural network. The MRI information can include (i) a low-dosage Gd MRI scan(s), or (ii) a Gd-free MRI scan(s). The Gd contrast can be generated in the Gd enhanced map(s) using a T2-weighted MRI image of the portion(s). Structural disorder(s) can include Stroke, tumor, trauma, infection, Multiple sclerosis and/or other inflammatory disease.

Abstract: An information processing apparatus (2000) includes a detection unit (2020), a state estimation unit (2040), and a height estimation unit (2080). The detection unit (2020) detects a target person from a video frame. The state estimation unit (2040) estimates a state of the detected target person. The height estimation unit (2080) estimates a height of the person on the basis of a height of the target person in the video frame in a case where the estimated state satisfies a predetermined condition.

Abstract: A vehicle identification system may perform operations that include: receiving a scan request that includes an image that comprises image data; identifying one or more vehicles within the image based on the image data based on computer vision and object recognition; generating bounding boxes based on the identified vehicles; cropping the image based on one or more of the bounding boxes; classifying a vehicle depicted within the cropped image; and presenting a notification that includes a display of the classification of the vehicle at the client device.

Abstract: An intraoral scanner generates 2D images of a dental site and 3D intraoral scans of the dental site. The computing device receives the 2D images of the dental site and the 3D intraoral scans of the dental site from the intraoral scanner, generates a 3D model of the dental site based on the 3D intraoral scans of the dental site, and processes at least one of a) one or more of the 2D images of the dental site, b) one or more of the 3D intraoral scans of the dental site, or c) data from the 3D model of the dental site to identify one or more intraoral areas of interest (AOIs) at the dental site. The computing device determines a dental condition associated with the one or more intraoral AOIs, and determines a manner for scanning the one or more intraoral AOIs.

Abstract: Camera platform techniques are described. In an implementation, a plurality of digital images and data describing times, at which, the plurality of digital images are captured is received by a computing device. Objects of clothing are recognized from the digital images by the computing device using object recognition as part of machine learning. A user schedule is also received by the computing device that describes user appointments and times, at which, the appointments are scheduled. A user profile is generated by the computing device by training a model using machine learning based on the recognized objects of clothing, times at which corresponding digital images are captured, and the user schedule. From the user profile, a recommendation is generated by processing a subsequent user schedule using the model as part of machine learning by the computing device.

Abstract: An intelligent video surveillance system is disclosed which performs real-time analytics on a live video stream. The system includes a training database populated with frames of actual video of objects of interest taken in a relevant environment. A subset of the frames include bounding boxes and/or bounding polygons which can be augmented. The training database also includes classification/annotation of data/labels relevant to the object of interest, a person carrying the object of interest, and/or the background or environment. The training database is searchable by the classification/annotation of data/labels.

Abstract: This relates to systems and processes for using a virtual assistant to control electronic devices. In one example process, a user can speak an input in natural language form to a user device to control one or more electronic devices. The user device can transmit the user speech to a server to be converted into a textual representation. The server can identify the one or more electronic devices and appropriate commands to be performed by the one or more electronic devices based on the textual representation. The identified one or more devices and commands to be performed can be transmitted back to the user device, which can forward the commands to the appropriate one or more electronic devices for execution. In response to receiving the commands, the one or more electronic devices can perform the commands and transmit their current states to the user device.

Abstract: Techniques are described for closed surface fitting (CSF). Processing circuitry may determine a plurality of points on a shape, determine a contour, used to determine a shape of an anatomical object, from image information of one or more images of a patient, and determine corresponding points on the contour that correspond to the plurality of points on the shape based on at least one of respective normal vectors projected from points on the shape and normal vectors projected from points on the contour. The processing circuitry may generate a plurality of intermediate points between the points on the shape and the corresponding points on the contour, generate an intermediate shape based on plurality of intermediate points, and generate a mask used to determine the shape of the anatomical object based on the intermediate shape.

Abstract: A technique is directed to methods and systems for calculating building heights from mono imagery. In some implementations, a building height calculation system performs orthorectification of an image of buildings against a digital terrain model to remove effects of terrain distortion from the image. The building height calculation system can execute an edge detection algorithm on the image to identify the edges of the building in the image. The edges can provide a rooftop vector of the building. The building height calculation system can execute, using image data at input, a machine learning algorithm to determine the footprint vector of the building in the image. The building height is calculated based on a camera angle, a distance from the camera to the building, and a pixel offset from the footprint vector to the rooftop vector.

Abstract: Techniques are described for determining a pre-morbid shape of an anatomical object. Processing circuitry may determine an aligned shape based on image data with under- or over-segmentation. The processing circuitry may utilize the aligned shape and a shape model such as a mean shape model of the anatomical object to register the aligned shape to the shape model and generate information indicative of the pre-morbid shape of the anatomical object.