Abstract: An augmented reality viewing system that aids a patron in visualizing a prepared food dish. The restaurant prepares ahead of time three-dimensional images of available food dishes. The patron, using their portable electronic device, images the table at which they plan on having their meal. Any selected dish can then be superimposed onto the image of the actual table so the patron can view, through augmented reality, what they can anticipate when the dish is delivered to the table.

Abstract: In some embodiments, the method includes a creating a plurality of session records for a subject, generating a subject progression model based on the plurality of session records, and comparing the subject progression model to a health progression model. The method further includes determining, based on the comparing the subject progression model to the health progression model, at least one progression deviation and generating a notification including an indication of the at least one progression deviation. In some embodiments, the plurality of session records include both objective data and subjective data. In some embodiments, the objective data includes one or more of body motion data captured with an RGB-D camera or RGB camera and voice data captured with a microphone. In some embodiments, the subjective data includes one or more of self-reported data from the subject and physician-reported data associated with the subject.

Abstract: Aspects of the present disclosure involve a system and a method for performing operations comprising: accessing a source image depicting a target structure; accessing one or more target images depicting at least a portion of the target structure; computing correspondence between a first set of pixels in the source image of a first portion of the target structure and a second set of pixels in the one or more target images of the first portion of the target structure, the correspondence being computed as a function of camera parameters that vary between the source image and the one or more target images; and generating a three-dimensional (3D) model of the target structure based on the correspondence between the first set of pixels in the source image and the second set of pixels in the one or more target images based on a joint optimization of target structure and camera parameters.

Abstract: An information processing apparatus for supporting a user's task for identifying a defect in an object based on a target image that is a photographed image of the object, includes: a selecting unit that selects, based on an user's input, one from one or more reference images to which is referred by the user for identifying a defect in the object; a display unit that comparably displays the target image and the selected reference image on a certain display device; a specifying unit that receives an user's operation for specifying a defect in the target image displayed by the display unit; and a generating unit that generates a new reference image based on a partial area, of the target image, including the specified defect. A new reference image generated by the generating unit is added to the one or more reference images selectable by the selecting unit.

Abstract: The disclosure relates to a method and to an image processing facility configured to carry out the method for the segmentation of image data of a target object. In the method, a first segmentation is generated by a trained algorithm. Furthermore, a statistical shape and appearance model is provided, which is trained on corresponding target objects. An interference region is further determined, in which the image data is impaired by an image artifact. A final segmentation of the image data is then generated by adjusting the shape and appearance model to the respective target object outside the interference region and using the first segmentation in the interference region.

Abstract: Computer-implemented methods, systems and devices having segmented numeral character recognition. In an embodiment, users may take digital pictures of a seven-segment display on a sensor device. For example, a user at a remote location may use a digital camera to capture a digital image of a seven-segment display on a sensor device. Captured images of a seven-segment display may then be sent or uploaded over a network to a remote health management system. The health care management system includes a reader that processes the received images to determine sensor readings representative of the values output on the seven-segment displays of the remote sensor devices. Machine learning and OCR are used to identify numeric characters in images associated with seven-segment displays. In this way, a remote heath management system can obtain sensor readings from remote locations when users only have access to sensor devices with seven-segment displays.

Abstract: Disclosed is a computer-implemented method for partitioning a medical image which encompasses acquiring a medical image of a surface of a patient and a surface of at least one object (embodied by image data), for example, by means of a 3D scanning device. Furthermore, a thermal image of the surface of the patient and the surface of the object is acquired (embodied by thermal data), for example, by means of a thermal camera. The medical image and the thermal image are fused (based on registration data), such that the image data is associated with the thermal data (embodied by association data). By analyzing the association data with regard to a specified condition (embodied by condition data), for example a condition related to a temperature threshold, a subset of the association data which fulfills the condition and describes a part of the medical image is determined (embodied by condition compliance data).

Abstract: A method of image processing for occlusion removal in images and videos captured by light field camera systems. The method comprises: capturing a plurality of camera views using a plurality of cameras; capturing a plurality of depth maps using a plurality of depth sensors; generating a depth map for each camera view; calculating a target view on a focal plane corresponding to a virtual camera; set a weighting function on the pixels on the camera views based on the depth map and a virtual distance; and blending the pixels in accordance with the weighting function to generate a refocused target view.

Abstract: A camera module according to an embodiment of the present invention includes a structured light projector configured to generate structured light of a specific pattern and changes an optical path of the structured light into units of subpixels of an image sensor for each image frame to project the structured light onto a subject, and a structured light camera configured to photograph the subject onto which the structured light is projected to generate a plurality of low-resolution image frames and generate a high-resolution depth map from the plurality of low-resolution image frames.

Abstract: In an example method for training image signal processors, a reconstructed image is generated via an image signal processor based on a sensor image. An intermediate loss function is generated based on a comparison of an output of one or more corresponding layers of a computer vision network and a copy of the computer vision network. The output of the computer vision network is based on the reconstructed image. An image signal processor is trained based on the intermediate loss function.

Abstract: Embodiments discussed herein facilitate employing a pretrained model to determine risk(s) of adverse event(s) based on Computed Tomography (CT) image volume(s) of an artery and/or training a model to determine such risk(s). Example embodiments can determine risk based on territory-specific calcium score(s) and/or intensity/morphological/location features discussed herein. Various embodiments can determine risk(s) based on a single CT image volume and/or change(s) in CT image volumes taken over a series of time points.

Abstract: The present disclosure provides a device and method for depth sensing by utilizing the combination of a ranging sensor and an image sensor. The ranging sensor can accurately detect distance measurement from an object. The image sensor can take images with high resolution of the object. By combining each sensor data from the ranging sensor and the image sensor, accurate depth information with high resolution of the object may be obtained. A structured light having patterned shapes are used in conjunction with the ranging sensor to receive reflected patterned shapes of the object. These reflected patterned shapes are used to analyze distance measurements associated with the specific patterned shapes. These distance measurements from both the ranging sensor and the image sensor is aligned and combined to generate an accurate depth map with high resolution using a processor of an electronic device including the ranging sensor and the image sensor.

Abstract: A computer implemented method includes supplying to a client device prompts for a first individual to specify matching criteria for a potential introduction to a second individual. The matching criteria includes a filter to sort a pool of individuals by a facial feature categorized by a facial recognition module. Matching criteria from the client device are collected. Matches between the first individual and a pool of individuals are generated based upon the matching criteria. The matches are supplied to the client device. A match acceptance by the first individual of the second individual is collected. Attributes of the second individual are verified to selectively establish a verified status. Network communication between the first individual and the second individual are enabled in response to the verified status.

Abstract: Systems and methods for extracting a feature in an image are provided. In one example embodiment, a computer-implemented method includes obtaining image data representing a scene, wherein the image data includes a plurality of images of the scene, each image associated with a different polarization angle. The method includes determining attribute information based at least in part on the plurality of images. The method includes determining one or more features in the image data based at least in part on the attribute information.

Abstract: A coordinate measuring machine has a measurement head having a point measurement device which measures first coordinates of only a single point on the surface of a workpiece at a given time. An area measurement device records images of a reference surface. A displacement device displaces the measurement head and/or the workpiece such that they assume different relative positions with respect to one another. An evaluation device calculates a shift between images that the area measurement device has recorded of the reference surface at different times at different relative positions, with a stitching algorithm. Based on this, second coordinates of the measurement head, which are defined relative to the reference surface, are determined. By linking the first coordinates with the second coordinates, third coordinates are determined, which define the points on the surface of the workpiece measured by the point measurement device relative to the reference surface.

Abstract: A method of finding a range to a target object includes extracting a signal component from a beat signal obtained by synthesizing a transmission wave irradiated onto the target object and a reflection wave reflected and received from the target object, generating a matching evaluation value of a plurality of image data of the target object captured by an imaging device, fusing the signal component and the matching evaluation value before generating a distance image from the matching evaluation value, and setting distance information for each pixel of the image data of the target object based on the signal component and the matching evaluation value fused together to generate a distance image.

Abstract: An electronic device is disclosed herein that includes an infrared light source to emit infrared light, a rolling shutter sensor, and at least one processor. The at least one processor is to: cause the rolling shutter sensor to output a first signal corresponding to a first frame of image data during exposure to the infrared light, reset the rows of the rolling shutter sensor at a same time, cause the rolling shutter sensor to output a second signal corresponding to a second frame of image data without exposure to the infrared light from the infrared light source, determine a difference between the first signal and the second signal to generate an ambient infrared free frame, and recognize a face based on the ambient infrared free frame.

Abstract: Methods and systems for training a non-blind deblurring module are disclosed. Unblurred test images and blurred test images are received, wherein each of the blurred test images is related to a corresponding one of the unblurred test images by a blur kernel term and a noise term. A regularized deconvolution sub-module and a convolutional neural network are jointly trained by adjusting a regularization parameter of a regularized deconvolution function and weights of a convolution neural network in order to minimize a cost function representative of a difference between each deblurred output image and a corresponding one of the unblurred test images.

Abstract: An information processing device (100) extracts a first point group constituting an object from a first distance image acquired by a first sensor. The information processing device (100) extracts a second point group constituting an object from a second distance image acquired by a second sensor. The information processing device (100) generates a first translated point group by translating the first point group by first translation coordinates. The information processing device (100) generates a second translated point group by translating the second point group by second translation coordinates. The information processing device (100) calculates a rotation parameter and a translation parameter based on the first translated point group and the second translated point group.

Abstract: The present disclosure provides a detection method of a projector, a projector, and an electronic device. The method includes: obtaining a speckle pattern, the speckle pattern being an image generated by irradiating laser light generated by a light source in the projector onto an object by an optical element; and performing an abnormality detection on the projector according to the speckle pattern.