Abstract: A computer-implemented method is performed by one or more processors to automatically register a plurality of captured data obtained using a respective measurement device, each of the captured data is obtained separately. The computer-implemented method includes accessing a first captured data of a portion of an environment, and a first image corresponding to said portion of the environment captured from a known relative position and angle with respect to the first captured data. Further, from the plurality of captured data, a second captured data is identified that has at least a partial overlap with said portion, the second captured data is identified based on a corresponding second image. The second image is captured from a known relative position and angle with respect to the second captured data. The method further includes transforming the second captured data and/or the first captured data to a coordinate system.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for characterizing a gaze position of a user in a query image. One of the methods includes obtaining a query image of a user captured by a camera of a mobile device; obtaining device characteristics data specifying (ii) characteristics of the mobile device, (ii) characteristics of the camera of the mobile device, or (iii) both; and processing a neural network input comprising (i) one or more images derived from the query image and (ii) the device characteristics data using a gaze prediction neural network, wherein the gaze prediction neural network is configured to, at run time and after the gaze prediction neural network has been trained, process the neural network input to generate a neural network output that characterizes a gaze position of the user in the query image.

Abstract: A cleaning wizard monitors and provides feedback for cleaning of medical equipment to ensure that cleaning is performed based on best practices. The cleaning wizard receives a video stream comprising an item of medical equipment and inputs a first set of video frames from the video stream into a first machine learning model. The first machine learning model is trained to output whether the first set of video frames corresponds to activity that initiates a cleaning protocol for the item of medical equipment. Responsive to the cleaning protocol being initiated, the cleaning wizard inputs a second set of video frames into a second machine learning model trained to output whether the second set of frames meets criteria of the cleaning protocol. Responsive to all criteria of the cleaning protocol being met, the cleaning wizard transmits a notification to an operator that the cleaning protocol is complete.

Abstract: In one embodiment, a sensor system includes an active thermal sensor pixel matrix, a plurality of presence sensors, and an image acquisition controller. The pixel matrix includes a plurality of pixels arranged in a plurality of rows and a plurality of columns and a boundary defining a perimeter. The plurality of presence sensors is disposed at least partially within the boundary of the pixel matrix. The image acquisition controller is coupled to the pixel matrix and the plurality of presence sensors. The image acquisition controller is configured to: (i) receive signals from the presence sensors; (ii) identify, based on the signals, a scan region, wherein the scan region is a portion of the pixel matrix that is in contact with or adjacent to a specimen; and (iii) obtain image data only from pixels that are within the scan region for generating an image of the specimen.

Abstract: A fingerprint recognition device is provided. The fingerprint recognition device includes an image acquisition module acquiring a fingerprint image including an input fingerprint, a preprocessing module generating a preprocessed image by preprocessing the fingerprint image, a minutiae extraction module extracting coordinates of each of minutiae and orientation points of the input fingerprint from the preprocessed image and a fake detection module receiving regions-of-interest (ROIs), including the coordinates of each of the minutiae or orientation points of the input fingerprint, and determining whether the input fingerprint is a fake by performing learning using the received ROIs.

Abstract: An automated process for data annotation of medical images includes obtaining image data from an imaging sensor, partitioning the image data, identifying an object of interest in the partitioned image data, generating an initial contour with one or more control points with respect to the object of interest, identifying a manual adjustment of one of the control points, automatically adjust a position of at least one other control point within a predetermined range of the manually adjusted control point to a new position, the new position of the at least one other control point and manually adjusted control point defining a new contour, and generating an updated image with the new contour and corresponding control points.

Abstract: A method for deblurring a blurred image includes dividing the blurred image into overlapping regions each having a size and an offset from neighboring overlapping regions along a first direction as determined by a period of a ringing artifact in the blurred image, or by obtained blur characteristics relating to the blurred image and/or attributable to the optical system, or by a detected cause capable of producing the blur characteristics, stacking the overlapping regions to produce a stacked output, wherein the overlapping regions are sequentially organized along the first direction, convolving the stacked output through a first convolutional neural network (CNN) to produce a first CNN output having reduced blur as compared to the stacked output, and assembling the first CNN output into a re-assembled image, and processing the re-assembled image through a second CNN to produce a deblurred image having reduced residual artifacts as compared to the re-assembled image.

Abstract: An electronic device extracts feature data from an input image, calculates one or more class maps from the feature data using a classifier layer, calculates one or more cluster maps from the feature data using a clustering layer, and generates image segmentation data using the one or more class maps and the one or more cluster maps.

Abstract: An evaluation apparatus according to an embodiment includes processing circuitry. On the basis of performance information related to performance of a medical diagnostic imaging device and numerical information related to at least one evaluation item, the processing circuitry makes an evaluation of a first imaging plan used by the medical diagnostic imaging device, the numerical information conforming to a guideline related to imaging plans. On the basis of a result of the evaluation, the processing circuitry generates, from the first imaging plan, a second imaging plan conforming to the guideline. The processing circuitry outputs the second imaging plan.

Abstract: An automation system uses cameras (134) and sensors (136) to identify a set of vehicle wheels within a lift area (118), then virtualizes the position and orientation of the vehicle relative to the lift posts (122, 130). Lift arms (124, 132) extending from the lift posts are moved to a first position that places a profile camera near the predicted position of lift points, and image analysis is used to positively identify the lift points. The lift arms are then moved to a second position that places an adapter camera below the identified lift points, and image analysis is used to confirm safe positioning below the lift point. Captured images and feedback from image analysis are used to improve and refine the system's ability to identify wheels, profile view lift points, and plan view lift points. The system may be integrated with lift arms allowing for automated rotation, extension, and elevation of lift adapters.

Abstract: Methods, systems, and apparatus are described herein for tracking objects and managing data. One or more objects may be determined in a first image. An avatar may be generated which is associated with the one or more objects in the first image. A second image may be received. The second image may comprise a change in at least one object of the one or more objects. Based on the change, in the at least one object, the avatar may be updated and the information kept for a predetermined period of time.

Abstract: Systems and methods are provided for point cloud compression. An exemplary method includes: receiving point cloud data; quantizing the point cloud data to remove noise to produce quantized point cloud data; generating, using the quantized point cloud data, a plurality of multi-level tiles; performing reordering within the multi-level tiles to optimize a compression rate producing a plurality of reordered multi-level tiles; bit packing the reordered multi-level tiles minimizing bits required to store per tile header data producing a bit packed multi-level tile data; and performing additional compression on the bit-packed multi-level tile data using a first compression algorithm.

Abstract: An information generating apparatus includes: an information managing unit that associates and manages an image obtained by photographing skin of a person, marking information indicating one or more markings that one or more operators perform with respect to one or more characteristic parts of skin in the image, and amendment information indicating amendment that a specialist makes to the marking information; and a marking-UI processing unit that superimposes and displays the one or more markings, indicated by the marking information, and the amendment, indicated by the amendment information, on the image.

Abstract: Facial recognition adversarial patch adjustment is performed by applying a patch to a digital image including image data representing a face to obtain a patched image, applying a face detector to the patched image to obtain a detection value representing a likelihood that the patched image includes image data representing facial features, applying a feature extractor to the patched image to obtain a feature vector, applying a similarity determiner to the feature vector and a target feature vector to obtain a similarity value representing a likelihood that the patched image includes image data representing a target face, calculating a loss based on the detection value and the similarity value, and adjusting the patch based on the loss.

Abstract: A label is attached to data corresponding to an activity included in time series data. A labeling system includes a processor and a machine learning model from which, in response to an input of time series data, a high-level label indicating a high-level activity included in the time series data and low-level labels indicating a plurality of low-level activities included in the high-level activity are outputted. The processor is configured to output a high-level label and a low-level label by using the machine learning model and cause the high-level label and the low-level label to be displayed, accept an input regarding a high-level label included in the time series data, train the machine learning model assuming that a high-level activity corresponding to the accepted high-level label is included in the time series data, and output a high-level label and a low-level label by using the trained machine learning model.

Abstract: One embodiment provides a method comprising acquiring 3D content comprising a 3D object in 3D space. The 3D object has object information indicative of a location of the 3D object in the 3D space. The method further comprises projecting the 3D object to a 2D object in 2D space based on the object information. The 2D object has one or more 2D vertices indicative of a location of the 2D object in the 2D space. The method further comprises determining one or more latent variables in the 2D space based on the object information and the one or more 2D vertices, and generating a 2D feature database including the one or more latent variables.

Abstract: A first object detection unit detects an object from a captured image and outputs object position information, in a non-high speed processing mode. A switching unit switches to a high-speed processing mode when the first object detection unit outputs the object position information. An image trimming unit extracts a trimmed image from the captured image based on the object position information output from the first object detection unit, in the high-speed processing mode. A second object detection unit detects an object from the trimmed image and outputs the object position information. A protrusion determination unit determines whether the object thus detected protrudes from the trimmed image. When it is determined that the object thus detected protrudes from the trimmed image, the switching unit switches to the non-high speed processing mode.

Abstract: The learning apparatus classifies target domain data into (N-c) classes based on unique features of the target domain data, classifies source domain data into N classes based on unique features of the source domain data, and classifies the target domain data and the source domain data into the N classes based on common features of the target domain data and the source domain data. Also, the learning apparatus calculates a first distance between the common features of the target domain data and the source domain data, and calculates a second distance between the unique features of the target domain data and the source domain data. Next, the learning apparatus updates parameters of a common feature extraction unit based on the first distance, and updates parameters of a target domain feature extraction unit and a source domain feature extraction unit based on the second distance.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for detecting regions of an environment. One of the methods includes receiving a representation of a scene in an environment; processing the representation using a center prediction neural network to generate: (i) features of the scene in the environment, and (ii) a respective center score corresponding to each of a plurality of locations in the environment; selecting, based on the respective center scores, one or more of the plurality of locations; and for each selected location: processing an input comprising the features of the scene in the environment and data specifying the selected location using a geometry prediction neural network to generate a geometry prediction that represents a geometry of the region that is centered at the selected location.

Abstract: Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing predictive recommendations using an MRI acquisition set associated with a common target object. Certain embodiments of the present invention utilize systems, methods, and computer program products that perform predictive recommendations based at least in part on an MRI set and utilizing one or more of techniques using image preprocessing models, techniques using image segmentation models, techniques using voxel integrity score generation machine learning models, and techniques using integrity score normalization models.