Abstract: A digital imaging method of analyzing pixel data of an image of a user's body for determining a user-specific hair removal efficiency value after removing hair is disclosed. The digital imaging method includes: aggregating training images of respective individuals' bodies after removing hair; training, using the pixel data of the training images, a hair removal efficiency model to determine hair removal efficiency values associated with a degree of hair removal efficiencies ranging from a least efficient to a most efficient; receiving an image of a user's body after removing hair; analyzing by the user image using the hair removal efficiency model to determine a user-specific hair removal efficiency value; generating a user-specific electronic recommendation designed to address a feature identifiable within the pixel data of the user's body based on the user-specific hair removal efficiency value; and rendering the recommendation on a display screen of a user computing device.

Abstract: An image binarization method and an electronic device using the same are provided. The method includes capturing an image by an image capturing device; selecting a target pixel row arranged at the front from one or more unselected first pixel rows among M pixel rows of the image according to a row order by a binarization circuit; performing, by the binarization circuit, a binarization operation on the target pixel row to obtain a binarized pixel row; storing the binarized pixel row to a main memory by the binarization circuit; performing, by the binarization circuit, the binarization operation to the remaining one or more first pixel rows until M binarized pixel rows are obtained, so as to complete the binarization operation.

Abstract: Methods and systems for image registration using an intelligent artificial agent are disclosed. In an intelligent artificial agent based registration method, a current state observation of an artificial agent is determined based on the medical images to be registered and current transformation parameters. Action-values are calculated for a plurality of actions available to the artificial agent based on the current state observation using a machine learning based model, such as a trained deep neural network (DNN). The actions correspond to predetermined adjustments of the transformation parameters. An action having a highest action-value is selected from the plurality of actions and the transformation parameters are adjusted by the predetermined adjustment corresponding to the selected action. The determining, calculating, and selecting steps are repeated for a plurality of iterations, and the medical images are registered using final transformation parameters resulting from the plurality of iterations.

Abstract: A computerized method for estimating bone mineral density, z and t-scores and/or fracture risk by receiving single-energy x-rays of the thoracic spine, chest x-ray, lumbar spine, whole body x-ray, hip, arm, leg, hand or foot in addition to imaging technical parameters and clinical parameters such as patient demographics, medical history, and other risk factors. The results are presented to a user for the diagnosis or screening of osteoporosis and/or risk stratification of osteoporotic fractures. A classifier may be trained using a dataset of single energy x-rays correlated to results from dual energy x-ray readings performed in the same patient and of the same body part, along with fracture incidence, to correlate the inputs provided to the desired output. A classifier may also be trained to predict fracture risk directly from x-ray image data and optionally additional patient characteristics.

Abstract: A fused imaging device and method are disclosed. The device comprises a light source component, an image capture component, and a control component. The control component may be configured to control the light source component to illuminate a target object based on a preset plurality of first optimal lighting configurations. The control component may further control the image capture component to capture images of the target object to obtain multiple first images, under the illumination of the light source component and generate a target image of the target object, based on the first images. The control component may further adjust the incidence angle, pattern, and wavelength of the light source in the light source component, as well as the exposure, lens focus, and polarization of the image capture component, to detect target object defects in captured images of the target object.

Abstract: According to one embodiment, a medical examination assistance apparatus includes processing circuitry. The processing circuitry outputs presence/absence of pre-detection for an adverse event at respective time points when a pre-detection model for an adverse event is applied to time-series medical examination data multiple times. The processing circuitry classifies a detection event of the pre-detection model, into a plurality of patterns each defined by a combination of presence/absence of the pre-detection of an adverse event and presence/absence of a medical event related to the adverse event. The processing circuitry calculates a performance indicator for evaluating the pre-detection model based on the number of instances of each pattern.

Abstract: In some embodiments, apparatuses and methods are provided herein useful to automatically annotating images. In some embodiments, a system for automatically annotating images comprises a database, wherein the database is configured to store images and annotations for the images and a control circuit, wherein the control circuit is communicatively coupled to the database, and wherein the control circuit is configured to retrieve, from the database, an image, generate, based on the image, a collection of augmented images, generate segmentation maps for each image in the collection of augmented images, wherein each of the segmentation maps include segments, select, based on a threshold, ones of the segments above a threshold, merge the ones of the segments above the threshold to create a segmented image, and generate, for each segment of the segmented image, classifications, wherein an annotation for the image includes the segmented images and the classifications.

Abstract: A milk analyser comprising a milk analysis unit having an analysis modality wherein the milk analysis unit further comprises a milk classification system having an imaging device configured to image milk for generation of digital image data; a processor of a computing device which is adapted to execute a program code to implement a deep learning neural network classifier trained using labelled milk images from milk within the classes into which the imaged milk may be classified and operable to generate a classification of the imaged milk; and a controller configured to output a control signal in dependence of the generated classification to control a sample intake to regulate the supply of milk to the analysis unit.

Abstract: Example apparatus disclosed herein include a watermark detector to detect watermarks in a media signal. Disclosed example apparatus also include a controller to operate the watermark detector to (1) detect a first watermark in the media signal, and (2) cycle between sleep intervals and active intervals based on a repetition rate of the watermarks in the media signal to perform a detection operation for a second watermark at a second location in the media signal relative to a first location of the first watermark in the media signal. In some examples, the controller is to search a buffer of prior detected watermark symbols to detect a third watermark at a third location prior to the second location in the media signal in response to the second watermark not being detected at the second location in the media signal.

Abstract: A method for automatically recognizing content of labels on objects includes: capturing visual information of an object using a scanning system including one or more cameras, the object having one or more labels on one or more exterior surfaces; detecting, by a computing system, one or more surfaces of the object having labels; rectifying, by the computing system, the visual information of the one or more surfaces of the object to compute one or more rectified images; and decoding, by the computing system, content of a label depicted in at least one of the one or more rectified images.

Abstract: A system and method for self-inspection of a vehicle is disclosed. The self-inspection may be performed by an application executed on a mobile device, with the application being configured to determine excessive wear and use. The mobile device may obtain images from a plurality of predetermined views of the vehicle, with damage input being determined for the plurality of predetermined views. In turn, a cost estimate may be output for repair or replacement due to the damage for each of the plurality of predetermined views as well as a total cost for repair or replacement, which may be dynamically updated as additional damage is input for the plurality of predetermined views.

Abstract: Methods and systems for image processing are provided. Image data may be obtained. The image data may include a plurality of voxels corresponding to a first plurality of ribs of an object. A first plurality of seed points may be identified for the first plurality of ribs. The first plurality of identified seed points may be labelled to obtain labelled seed points. A connected domain of a target rib of the first plurality of ribs may be determined based on at least one rib segmentation algorithm. A labelled target rib may be obtained by labelling, based on a hit-or-miss operation, the connected domain of the target rib, wherein the hit-or-miss operation may be performed using the labelled seed points to hit the connected domain of the target rib.

Abstract: A preprocessing technique for synthetic radar images. An embodiment of a method for preprocessing synthetic aperture radar images includes: receiving range-compressed radar data generated from raw radar image data on-board a satellite or an airborne vehicle; generating a preliminary SAR image by performing a pre-focusing on the range-compressed radar data; extracting image subsectors from the preliminary SAR image; transmitting the extracted image subsectors to an on-ground portion; reconstructing the range-compressed radar data pertaining to the extracted image subsectors; and making the range-compressed radar data pertaining to the extracted image subsectors available for a Nominal synthetic aperture radar processor, wherein the Nominal synthetic aperture radar processor is configured to generate a focused SAR image having a nominal value of image resolution that is higher than the resolution of the preliminary SAR image.

Abstract: Embodiments of the disclosure provide methods, apparatuses, and computer-readable media for generating image reports. In one embodiment, the method includes: obtaining an image to be analyzed; determining at least one reference image corresponding to the image to be analyzed, the at least one reference image corresponding to a respective reference image report; and generating, based on the reference image report, an image report corresponding to the image to be analyzed. In the method for generating an image report provided by the embodiments, by obtaining an image to be analyzed is obtained, at least one reference image corresponding to the image to be analyzed is determined; and an image report corresponding to the image to be analyzed is generated based on a respective reference image report corresponding to the at least one reference image.

Abstract: Techniques for improving image processing related to item deliveries are described. In an example, a computer system receives image data showing a portion of a delivery location. The computer system determines an artificial intelligence (AI) model associated with the delivery location. The computer system inputs the image data to the AI model. The computer system receives an indication of whether the portion corresponds to a correct drop-off location and causes a presentation about the indication to be provided at a device.

Abstract: A three-dimensional data encoding method includes: determining a total number of layers; when the total number of the layers is greater than 1, selecting, from pieces of attribute information of three-dimensional points, attribute information of a three-dimensional point based on a sampling period according to a data order of the pieces of attribute information of the three-dimensional points, and classifying the pieces of attribute information of the three-dimensional points into layers by assigning a first layer to pieces of attribute information of three-dimensional points selected and a second layer to pieces of attribute information of three-dimensional points non-selected; encoding the pieces of attribute information of the three-dimensional points for each of the layers; and generating a bitstream including the pieces of attribute information encoded, layer-number information, and sampling period information.

Abstract: Systems and methods for mapping neuronal circuitry in accordance with embodiments of the invention are illustrated. One embodiment includes a method for generating a neuronal shape graph, including obtaining functional brain imaging data from an imaging device, where the functional brain imaging data includes a time-series of voxels describing neuronal activation over time in a patient's brain, lowering the dimensionality of the functional brain imaging data to a set of points, where each point represents the brain state at a particular time in the timeseries, binning the points into a plurality of bins, clustering the binned points, and generating a shape graph from the clustered points, where nodes in the shape graph represent a brain state and edges between the nodes represent transitions between brain states.

Abstract: An apparatus for determining a functional index for stenosis assessment of a vessel is provided. The apparatus comprises an input interface (40) and a processing unit (50). The input interface is configured to obtain image data (30) representing a two-dimensional representation of a vessel (6). The processing unit (50) is configured to determine a course of the vessel (6) and a width (w1, w2) of the vessel along its course in the image data and is further configured to determine the functional index for stenosis assessment of the vessel based on the width of the vessel in the image data.

Abstract: Methods for reconstructing images from undersampled k-space data using a machine learning approach to learn non-linear mapping functions from acquired k-space lines to generate unacquired target points across multiple coils are described.

Abstract: Systems and methods for facilitating communication with autonomous vehicles are provided. In one example embodiment, a computing system can obtain a first type of sensor data (e.g., camera image data) associated with a surrounding environment of an autonomous vehicle and/or a second type of sensor data (e.g., LIDAR data) associated with the surrounding environment of the autonomous vehicle. The computing system can generate overhead image data indicative of at least a portion of the surrounding environment of the autonomous vehicle based at least in part on the first and/or second types of sensor data. The computing system can determine one or more lane boundaries within the surrounding environment of the autonomous vehicle based at least in part on the overhead image data indicative of at least the portion of the surrounding environment of the autonomous vehicle and a machine-learned lane boundary detection model.