Abstract: A method of generating synthetic data from time series data, such as from handwritten characters, words, sentences, mathematics, and sketches that are drawn with a stylus on an interactive display or with a finger on a touch device. This computationally efficient method is able to generate realistic variations of a given sample. In a handwriting or sketch recognition context, synthetic data is generated from real data in order to train recognizers and thus improve recognition accuracy when only a limited number of samples are available. Similarly, synthetic data can also be used to test and validate such recognizers. Also discussed is a dynamic time warping based approach for both segmented and continuous data that is designed to be a robust, go-to method for gesture recognition across a variety of modalities using only limited training samples.

Abstract: Field data is collected of a field. Each instance of field data contains information that can be used to determine a value corresponding to whether or not a plant is present or absent in a particular location and is referred to as a plant presence value. The plant presence values are aggregated using the position data associated with each instance of field data to generate aggregated plant presence values. Gaps between plots are identified based partly on variations in the plant presence values within the aggregated field data. Information known about a field can be used to heuristically identify gaps in a seed line or used to eliminate locations on a seed line that may look like a gap based on low plant presence values. The aggregated plant presence values can be presented as a heat map of plant presence values showing the relative plant density of the field.

Abstract: Provided is a method of operating a medical imaging apparatus, comprising: acquiring a first image of a first type corresponding to a first respiratory state of an object; determining motion information of the object with respect to a respiratory state, based on first and second images of a second type respectively corresponding to the first respiratory state and a second respiratory state of the object; and generating a second image of the first type corresponding to the second respiratory state by applying the motion information to the first image of the first type.

Abstract: An imaging system, a method for imaging an object of interest, and an image of the object of interest. In one embodiment, an imaging system includes a channel configured to receive information from an object of interest, a 3DSS sub-system configured to capture information from the object of interest and generate at least one of 3D surface data or 3D position data based on the information captured by the 3DSS sub-system, and an OCT sub-system configured to perform a line scan of light reflected from the object of interest, generate OCT image data from the line scan, receive the at least one of the 3D surface data or the 3D position data, and generate one or more OCT images using the OCT image data and the at least one of the 3D surface data or the 3D position data.

Abstract: An optical sensor system for determining trajectory of a wheel includes: a wheel mounted in a wheel arch having an outer surface covered with evenly-spaced wheel treads; a plurality of optical sensors mounted in the wheel arch but not touching the wheel, for performing a plurality of counts corresponding to respectively capturing a plurality of images of the wheel according to the wheel treads; and a plurality of clear casings respectively mounted in the wheel arch between the wheel and the plurality of optical sensors, but not touching the wheel. The captured images are compared with a reference image to determine a 2D displacement and a calculation is further performed to convert the measured 2D displacement of the wheel from its original position into a distance the wheel travels along a path in order to determine the wheel trajectory.

Abstract: Example systems and methods are disclosed for determining the direction of an actor based on sensors within an environment. The method may include receiving point cloud data representative of the actor within the environment. The method may also include generating data segments of the point cloud data corresponding to respective height levels of the actor. The method may further include determining an area value for each data segment. Also, the method may include determining a transition between a first data segment and an adjacent second data segment based on a difference between the corresponding area values. Further, the method may include determining that the first data segment is representative of a head of the actor while the second data segment is representative of a body of the actor. The method may also include providing information indicating a direction of the actor based on the second data segment.

Abstract: An image processing apparatus according to an embodiment includes storage circuitry and processing circuitry. The storage circuitry stores therein fluid resistance data representing a correlation among a vascular shape, a blood flow rate, and a pressure loss. The processing circuitry extracts, from three-dimensional image data in which a blood vessel of a subject is rendered, vascular shape data representing a shape of the blood vessel. The processing circuitry performs fluid analysis based on the vascular shape data and the blood flow rate and the pressure loss that correspond to the vascular shape data and that are correlated by the fluid resistance data to derive a functional index related to a blood circulation state in the blood vessel of the subject.

Abstract: A computer-implemented method for performing spatiotemporal background phase correction for phase contrast velocity encoded magnetic resonance imaging includes performing a phase contrast magnetic resonance imaging scan of a region of interest within a patient to yield a complex image and calculating a plurality of filter cut-off frequencies based on physiological limits associated with the patient. A spatiotemporal filter is created based on the plurality of filter cut-off frequencies. This spatiotemporal filter is applied to the complex image to yield a low-pass filtered complex image. Then, complex division is performed using the complex image and the low-pass filtered complex image to yield a corrected image.

Abstract: In one aspect, the present disclosure relates to a method which, in one embodiment, includes: receiving video data for a first video and deconstructing the video data of the first video into a plurality of context windows; performing, on each context window of the plurality of context windows that includes an image frame, a video analytic function on the image frame to identify one or more characteristics of the context window that are associated with image-related content of the first video; performing, on each context window of the plurality of context windows that includes an audio frame, a video analytic function on the audio frame to identify one or more characteristics of the context window that are associated with audio-related content of the first video; generating, for each of the plurality of context windows, a respective local atomic unit comprising attributes derived from the identified one or more characteristics of the respective context window, to form a plurality of local atomic units; and gen

Abstract: The present disclosure relates generally to medical systems and methods for combining and synergizing information in an expedient format for viewing on a display screen. In one embodiment, a method for combining and synergizing data from different medical systems comprises obtaining from a first medical system an image disposed relative to a first coordinate system, obtaining from a second medical system supplemental data; synchronizing first and second clocks of the first and second medical systems, respectively, and displaying in synchronicity the supplemental data combined with the image. In other embodiments, coordinate systems of the first and second medical systems can be co-registered. In another embodiment, sensor integration time and spatial accuracy of the first and second medical systems can be used with an algorithm to produce synergized information.

Abstract: A store-entering person attribute extraction apparatus includes a timing detector, an extraction unit, and an associating unit. The timing detector detects a boundary crossing timing for entering a store. The extraction unit extracts predetermined personal attributes from a captured store-entering person image acquired by capturing an image of a person entering the store. The associating unit associates the boundary crossing timing detected by the timing detector with the attributes extracted by the extraction unit.

Abstract: An event signal processing method and apparatus are provided. The event signal processing method includes receiving, from an event-based sensor, event signals including timestamps, generating a first timestamp map based on the timestamps, and interpolating a new timestamp into the first timestamp map based on at least two timestamps of the first timestamp map, to generate a second timestamp map.

Abstract: A method of investigating a specimen using a tomographic imaging apparatus, by performing, in multiple iterations, the following steps: (i) Using a Back Projection technique to produce an initial tomogram from a set of initial images; (ii) Subjecting said initial tomogram to a mathematical filtering operation, thereby producing an adjusted tomogram; (iii) Using a Forward Projection technique on said adjusted tomogram to dissociate it into a set of calculated images; (iv) Repeating steps (i)-(iii) until said calculated images satisfy an acceptance criterion.

Abstract: A pattern drawing apparatus includes a first image-pickup device for reading an alignment mark and reading a first pattern image for detecting a positional shift, a second image-pickup device for reading the first pattern image and reading a second pattern image for detecting a positional shift drawn by an irradiation light beam from the optical head while carrying out a relative movement between the table and the optical head, and a positional shift detection unit for obtaining a first coordinate difference between a center of a visual field of the first image-pickup device and a center of the first pattern based on a read image by the first image-pickup device and obtaining a second coordinate difference between the center of the first pattern and a specific position of the second pattern based on a read image by the second image-pickup device.

Abstract: A method for processing a frame in a sequence of successively acquired frames in dynamic digital radiography includes the multi-scale representation of frames being subjected to temporal filtering by adding at least one correction image to a corresponding detail image(s) in the multi-scale representations of a frame of interest, the correction image being computed by combining clipped difference images obtained as the difference between the multi-scale representation of the frame of interest and the multi-scale representations of a selection of other frames in said sequence.

Abstract: Methods, apparatus, and other embodiments distinguish disease phenotypes and mutational status using co-occurrence of local anisotropic gradient orientations (CoLIAGe) and Laws features. One example apparatus includes a set of circuits that acquires a radiologic image (e.g., MRI image) of a region of tissue demonstrating breast cancer, computes a gradient orientation for a pixel in the MRI image, computes a significant orientation for the pixel based on the gradient orientation, constructs a feature vector that captures a discretized entropy distribution for the image based on the significant orientation, extracts a set of texture features from the MRI image, and classifies the phenotype of the breast cancer based on the feature vector and the set of texture features. Embodiments of example apparatus may generate and display a heatmap of entropy values for the image. Example methods and apparatus may operate substantially in real-time, or may operate in two, three, or more dimensions.

Abstract: A non-transitory computer readable storage medium that stores a program for image processing that causes a computer to execute a process including: detecting a change in a lung based on a plurality of images of the chest scanned at different times, the change in the lung indicating that each position of each part of the lung changes toward a specified position of the lung, and outputting the change of the lung.

Abstract: A supplemental device (2) for attachment to a pen-type drug injection device, the supplemental device comprising an optical sensor array or camera (25) configured to capture an image of one or more numbers representing dose values on a dose dial sleeve of the injection device, and a processor (24) and memory (240,241) arrangement configured to run an algorithm to receive image data from the sensor/camera and extract the dialed dose value from said image via optical character recognition (OCR). The algorithm is able to determine the set dose value which is at the centre of the image (902), also if the dose scale only comprises integer values in steps of two (see FIG. 9).

Abstract: A method and computing device for detecting and outputting notable moments of a performance. The method may be executable by a processor. The method may include receiving, by a processor, an input video stream of a performance. The method may further include determining, by the processor, a notable moment within the input video stream, the notable moment including an amount of motion greater than a threshold value. The method may also include generating, by the processor, a video clip including the determined notable moment, a portion of the input video stream preceding the determined notable moment, and a portion of the input video stream following the determined notable moment. The method may additionally include outputting, by the processor, the video clip.

Abstract: Aspects of the present invention include a method, system and computer program product. The method includes a method includes selecting a chart, and interpreting contents within the selected chart. The method also includes searching for additional sources of information, and extracting information from the additional sources of information. The method further includes combining the interpreted chart contents with the extracted information, and generating a textual description of the selected chart.