Abstract: The technology described herein can be embodied in a method that includes receiving data representing information captured using a first sensor and a second sensor of a multi-sensor camera. The sensors are configured to capture a surgical scene illuminated by a light source configured to emit wavelengths in the visible spectrum corresponding to sensing capabilities of the first and second sensors, respectively. The method also includes receiving data representing information captured using a third sensor of the multi-sensor camera, the third sensor configured to capture the surgical scene as illuminated by a near-infrared light source, and generating a first visual representation of the surgical scene based on the data representing the information captured using the first and second sensors. The first visual representation is combined with the information captured using the third sensor to generate a second visual representation, and the second visual representation is presented on a display device.

Abstract: Provided is a diagnosis system for anterior eye diseases. An image obtainer obtains an anterior eye image of an image obtainer configured to obtain an anterior eye image of a subject. A characteristic extractor extracts characteristic information of the obtained anterior eye image on the basis of a machine-learning model. A disease analyzer determines whether or not an anterior eye of the subject has a disease and classifying a disease class according to the extracted characteristic information.

Abstract: A laser-surgical apparatus includes a laser emitting laser light with a narrowband wavelength distribution, a digital image sensor or a plurality of digital image sensors that separately record(s) different color channels that represent mutually different spectral wavelength distributions with in each case one maximum corresponding to a specific spectral color and produce(s) separate pieces of image information for the individual color channels, and a graphics module for combining the separate pieces of image information into one color image. In addition, it includes a manipulation module for suppressing the laser light in the color image, which makes it possible to electronically manipulate the pieces of image information of the color channel the spectral wavelength distribution of which has the largest overlap with the narrowband wavelength distribution of the laser light before the separate pieces of image information are combined or during the combining of the separate pieces of image information.

Abstract: An example system includes a thermal camera, a memory, and processing circuitry coupled to the thermal camera and the memory. The processing circuitry is configured to acquire a core temperature of a patient and acquire a first thermal image associated with the patient. The processing circuitry is configured to determine, based on the first thermal image, a first sensed temperature of a location associated with the patient. The processing circuitry is configured to determine a core temperature delta between the core temperature and the first sensed temperature. The processing circuitry is configured to acquire a second thermal image associated with the patient. The processing circuitry is configured to determine, based on the second thermal image, a second sensed temperature. The processing circuitry is configured to determine, based on the second sensed temperature and the core temperature delta, a measure of the core temperature.

Abstract: A light color identifying method and apparatus of a signal light, and a roadside device provided in the present application relate to the field of intelligent transportation. A solution includes: collecting an image including the signal light through an image collecting apparatus; determining a background image according to N preceding frames of images of a current frame of image, where N is a positive integer greater than or equal to 1; performing foreground identification on the current frame of image according to the background image to obtain a moving foreground, where the moving foreground represents a change of the current frame of image relative to the background image; and determining, according to the moving foreground, a light color of a light that is turned on in the current frame of image.

Abstract: A neural network system implements a model for generating an output image based on a received input image. The model is learned through a training process during which parameters associated with the model are adjusted so as to maximize a difference between a first image predicted using first parameter values of the model and a second image predicted using second parameter values of the model, and to minimize a difference between the second image and a ground truth image. During a first iteration of the training process the first image is predicted and during a second iteration the second image is predicted. The first parameter values are obtained during the first iteration by minimizing a difference between the first image and the ground truth image, and the second parameter values are obtained during the second iteration by maximizing the difference between the first image and the second image.

Abstract: In one implementation, a method of defining a negative space in a three-dimensional scene model is performed at a device including a processor and non-transitory memory. The method includes obtaining a three-dimensional scene model of a physical environment including a plurality of points, wherein each of the plurality of points is associated with a set of coordinates in a three-dimensional space. The method includes defining a subspace in the three-dimensional space with less than a threshold number of the plurality of points. The method includes determining a semantic label for the subspace. The method includes generating a characterization vector of the subspace, wherein the characterization vector includes the spatial extent of the subspace and the semantic label.

Abstract: Previous information generating devices or printers were designed to print a paper copy of data and/or receipts which causes a disconnect with modem day data manipulation. This information redirector can redirects generated data to and receive data from the internet and hand held devices which will open up extremely fast data exchange and data manipulation for consumers, cities, states and the federal government without the expense of having to purchase complete new systems. By simply adding the redirector we can connect all old computer systems with modem day systems that now have the ability to manipulate data automatically.

Abstract: A series of images is obtained from an endoscope. Three-dimensional reconstruction is performed on the series of images to reconstruct anatomy shown in the series of images. A graphic, such as a grid, is rendered based on the three-dimensional reconstruction, over the series of images resulting in an enhanced endoscopic video feed to be shown on a display.

Abstract: An object of one embodiment of the present invention is to accurately derive an inclination of a line image sensor. One embodiment of the present invention is an image reading apparatus including: a line image sensor in which reading elements for reading an image are arrayed in a predetermined direction; a first derivation unit configured to, based on read data acquired by reading a chart on which a plurality of dot patterns is printed with the line image sensor, derive coordinates of each of the plurality of dot patterns; a second derivation unit configured to derive an inclination angle of the line image sensor based on the coordinates derived by the first derivation unit; and a first calculation unit configured to calculate a first correction value for correcting the inclination of the line image sensor based on the inclination angle derived by the second derivation unit.

Abstract: Provided is an apparatus for acquiring images including an image sensor including a sensor substrate including a plurality of photo-sensing cells sensing light, and a color separation lens array provided above the sensor substrate, the color separation lens array including a fine structure in each of a plurality of regions respectively facing the plurality of photo-sensing cells and separating incident light based on color, the fine structure forming a phase distribution to condense light having different wavelengths on adjacent photo-sensing cells, a signal processor configured to perform, based on a point spread function corresponding to each color pixel by the color separation lens array, deconvolution on sensing signals of the plurality of photo-sensing cells to process an image signal for each color obtained by the image sensor, and an image processor configured to form a color image from the image signal for each color processed by the signal processor.

Abstract: The present invention is related to a method, a computer program, and apparatus for adapting an estimator for use in a microscope for estimating a position of an emitter in a sample based on a method, in which the sample is illuminated with light at one or more sets of probe positions and fluorescence photons are acquired for the sets of probe positions. The invention is further related to a microscope, which makes use of such a method or apparatus. The sample is illuminated with light at one or more sets of probe positions and fluorescence photons are acquired for the sets of probe positions. Photon counts of the acquired photons are then added to vectors of photon counts or sums of photon counts are determined for the sets of probe positions. A value representative of background noise is determined and used for adapting the estimator in real-time.

Abstract: The present disclosure provides a medical image analysis method and apparatus. The medical image analysis method according to an exemplary embodiment includes: receiving a frontal image of a spine; separating vertebral bodies from a vertebrae constituting the spine in the frontal image and extracting a contour of each of the vertebral bodies; deforming a 3D vertebral body model prepared in advance to match with the contour of each vertebral body; detecting an upper plane and a lower plane of each vertebral body in a matched 3D vertebral body model; determining an inclination of each vertebral body based on the upper plane and the lower plane of each vertebral body; and calculating a Cobb's angle based on the inclination of the vertebral body.

Abstract: An application running on a device to manage insulin site rotation may read a configuration file including a group, a plurality of sites in the group, and an image associated with the group. The application may detect an input selecting a site from the plurality of sites for administration of an insulin management device. The application may also set the selected site as unavailable for a predetermined duration in response to the input selecting the site. A log entry may be written to track usage of the site in response to the input selecting the site. A visual indicator on the selected site may show that the site is recently selected in response to detecting the input selecting the site within a predetermined duration. The insulin management device may be a pump, a syringe, or a glucose monitor.

Abstract: A system for generating image content, the system comprising an image region identification unit operable to identify one or more regions of an image to be displayed as low-detail regions, an image processing unit operable to perform processing to reduce colour differences for each of one or more areas within one or more of the identified regions, and an image output unit operable to output one or more processed images.

Abstract: An information processing apparatus includes a processor configured to control change of an image in accordance with a situation in a place where authentication is executed, the image being formed in air to indicate a position where information is to be read in a non-contact manner from an object used for the authentication.

Abstract: Deep learning is used to train a neural network for end-to-end prediction of short term (e.g., 20 minutes or less) solar irradiation based on camera images and metadata. The architecture of the neural network includes a recurrent network for temporal considerations. The images and metadata are input at different locations in the neural network. The resulting machine-learned neural network predicts solar irradiation based on camera images and metadata so that a solar plant and back-up power source may be controlled to minimize output power variation.

Abstract: An image of a check is captured by an imaging device and processing of the digital image of the check for deposit at a remote server may be accomplished with a downloaded software application on a portable computing device associated with the imaging device. The downloaded application may include one or more trained machine learning models for processing the captured image. The portable computing device may utilize deterministic algorithms for certain image processing tasks and machine learning models for others. The selection between machine learning and deterministic processing may be made locally on the portable device or in response to instructions from an institution server to use a particular processing method.

Abstract: A method for detecting a grasping position of a robot in grasping a target object includes: collecting a target RGB image and a target Depth image of the target object at different view angles; inputting each of the target RGB image to a target object segmentation network for calculation to obtain an RGB pixel region of the target object in the target RGB image and a Depth pixel region of the target object; inputting the RGB pixel region to an optimal grasping position generation network to obtain an optimal grasping position for grasping the target object; inputting the Depth pixel region of the target object and the optimal grasping position to a grasping position quality evaluation network to calculate a score of the optimal grasping position; and selecting an optimal grasping position corresponding to a highest score as a global optimal grasping position of the robot.

Abstract: A reading unit is configured to capture an image of a shadow generated at a leading end of a document, and a control unit is configured to estimate a thickness of the document based on a pixel value of the shadow. A multifeeding error is displayed on a display unit when it is determined as thin paper in a thick paper determination. The control unit turns multifeeding detection to OFF and stands by until a feeding is completed, and upon completion, returns the multifeeding detection to ON.