Abstract: A body fluid volume estimation device includes a pre-training unit, a transfer learning unit, and an estimation unit. The pre-training unit performs pre-training by using, as supervised information, information indicating body fluid volumes of the multiple patients when face images of multiple patients are captured. The transfer learning unit further performs transfer learning on multiple face images of one specific patient after the pre-training, and constructs a trained model. The estimation unit estimates, by inputting a face image of the one specific patient to the trained model, a body fluid volume at a point in time at which the face image of the one specific patient is captured. By estimating a body fluid volume from a face image by machine learning, the body fluid volume can be used for assistance such as decision making of a user.

Abstract: There is described a system for determining an atherosclerotic pathological tissue type of a coronary artery, the system comprising: an optical coherence tomography (OCT) imaging system being configured for acquiring an OCT image of tissue within said coronary artery; and a controller configured for: using a trained fully convolutional engine stored on said memory and having a plurality of convolutional layers with respective dilation rates different than unity, extracting pathological tissues regardless their type in at least a region of interest of said OCT image; using a trained auto-encoder classification engine stored on said memory and having a layer characterized with a sparsity regularization parameter, determining an atherosclerotic pathological tissue type associated to said region of interest of said OCT image based on said extracted pathological tissues; and outputting said atherosclerotic pathological tissue type of said coronary artery.

Abstract: Remote sensing and social sensing for flood mapping is provided by identifying where floodwater is present in an image of a location affected by a flooding event; identifying a social media post posted on a social media platform from the location and associated with the flooding event; and overlaying the image with the social media post. In some embodiments, the remote and social sensing includes one or more of: generating a permanent water mask identifying where permanent water is located at the location, and applying the permanent water mask to the image to differentiate the floodwater from permanent water for the location; identifying where the social media post was posted from; and overlaying the image with the social media post includes positioning a photograph included in the social media post for display with the image where a subject of the photograph is located at the location.

Abstract: A method and a laser processing system are for laser processing a workpiece by a laser beam. The method includes: recording an image of the workpiece with a camera, the beam path of which is coaxially coupled into a beam path of the laser beam and runs together with the beam path of the laser beam via a scanning device; determining a respective contour point for each measuring line of a plurality of measuring lines which are laid through an expected contour path of the workpiece in the recorded image; determining an actual contour path of the workpiece based on the determined contour points; and controlling the scanning device for positioning the laser beam for laser processing based on the actual contour path.

Abstract: The present disclosure provides a system and method for AI-based cell classification of cells from a patient sample to determine if cells indicative of lung cancer are present. In the system and method, 2D imaging is used to eliminate cells not likely to be indicative of lung cancer from subsequent 3D imaging, while 3D imaging is conducted for cells likely to be indicative of lung cancer. The present disclosure further provides a method of training 2D cell classifiers for use in the system and method for AI-based cell classification.

Abstract: The present disclosure relates to a method for identifying or authenticating a physical object using computer vision models with machine learning algorithms. The method includes capturing an image of the physical object, focusing on a portion of the physical object in more detail to capture a first analysis image. The method further includes determining a first set of features associated with the first analysis image, generating a first feature-vector for the physical object, comparing the first feature-vector with a second feature-vector, and generating a notification associated with a status for identification or authentication of the physical object based on the comparison. The second feature-vector is generated from a second set of features that are associated with a second analysis image. The first feature-vector is compared with the second feature-vector to determine a match. A notification is generated indicating a status of the machine matching of the physical object.

Abstract: A detection device capable of detecting an actual pupil center with high accuracy even in an off-axis sight line detection. The detection device includes an obtainment unit configured to obtain an image of an eyeball of a user, a memory device that stores a set of instructions, and at least one processor that executes the set of instructions to: detect a position of a pupil center of the eyeball from an image obtained by the obtainment unit, detect a direction of a sight line based on the position of the pupil center, and detect a gaze point of the user based on the position of the pupil center and an angle formed between an optical axis of the obtainment unit and the direction of the sight line.

Abstract: A MRI apparatus according to an embodiment includes processing circuitry. The processing circuitry obtains MR data acquired by implementing an IR method under a condition where a phase difference in a complex signal related to observed elements is equal to ?, due to a difference in longitudinal magnetization relaxation time between the observed elements; generates phase data on the basis of the MR data; multiplies a phase angle in the phase data by 2n; unfolds the phase of phase data having the phase angle multiplied by 2n; multiplies the phase angle in the unfolded phase data by 1/(2n); generates a phase correction map used for correcting a phase with respect to the complex signal, by applying a complex conjugate to phase data having the phase angle multiplied by 1/(2n); and performs a phase correction on the MR data by using the phase correction map.

Abstract: The inventive concept relate to a technology, which recognizes widely deformable markers with high accuracy in an end-to-end manner of message encoding and decoding, and which generates and recognizes deformable fiducial markers based on artificial intelligence, and includes generating, by a marker generator, a unique marker pattern as a fiducial marker in an input binary message, rendering, by an imaging simulator, an image by generating a training dataset of a realistic scene image with the generated fiducial marker, and training a marker detector with the rendered image.

Abstract: Disclosed is an image enhancement method, including: obtaining an image adjustment parameter; converting first image data to be processed into second image data; adjusting the luminance data to obtain adjusted luminance data, updating the luminance adjustment parameter when that the adjusted luminance data does not meet a preset luminance enhancement condition, and based on an updated luminance adjustment parameter, continuing to adjust the adjusted luminance data until final adjusted luminance data meets the luminance enhancement condition; adjusting the chroma data to obtain adjusted chroma data, updating the chroma adjustment parameter when that the adjusted chroma data does not meet a preset chroma enhancement condition, and based on an updated chroma adjustment parameter, continuing to adjust the adjusted chroma data until final adjusted chroma data meets the chroma enhancement condition; and performing image color dimension conversion on the luminance data and the chroma data to obtain third image data.

Abstract: A camera device for observing and recognizing a livestock animal in a shed environment. The camera includes a housing with an outer surface and with a light transmitting opening, an optics for forming an image of the environment, a light-sensitive sensor provided in the housing for recording the formed image, an image processing device for processing the recorded image and recognizing a portion of a shed animal, and a control unit. A first portion of the outer surface is lighter in colour on a side of the opening at least directly around than opening than a second portion of the outer surface which is located away from the opening and which is at least half the size of the first portion. The lighter colour around the one or more openings reduces soiling by flies in comparison with known cameras with black surroundings for these openings.

Abstract: A display device includes: a base; light emitting element groups on one surface of the base, and each including a plurality of light emitting elements arranged in a first direction; and light receiving element groups on the one surface of the base, and each including a plurality of light receiving elements arranged in the first direction, wherein the light emitting element groups are arranged in a second direction, wherein the light receiving element groups are adjacent and parallel to the light emitting element groups, and wherein, based on a first light emitting element group among the light emitting element groups emitting light, first sensing data is obtained, without emission of a second light emitting element group arranged in the second direction from the first light emitting element group, by using at least one first light receiving element group adjacent to the second light emitting element group.

Abstract: One embodiment of the present disclosure provides an artificial intelligence (AI) assistance device based on door image analysis. The device comprises: an image reception unit for receiving an image captured by a camera attached to a door, the image including an image of a person entering or exiting through the door; and a processor, which uses a storage place for storing the received image and an AI model, so as to analyze the image stored in the storage, and thus infers the characteristics of the entering or exiting person and provides information corresponding to the inferred characteristics.

Abstract: The information processing apparatus acquires the first body color desired by a user as a body color of a vehicle ordered by the user. Furthermore, based on at least the appraised value of the vehicle having a first body color after a predetermined period has elapsed, the information processing apparatus determines whether or not to propose to the user to topcoat the vehicle having the second body color with an easily peelable paint of the first body color.

Abstract: A method of detecting inappropriate imagery in a customer user profile image intending to be displayed on digital signage at a quick service restaurant can include identifying the presence of a customer adjacent a digital sign; associating the customer with a customer user profile; analyzing, by a computer processor, the customer user profile image for inappropriate imagery in the customer user profile image; in response to the detection of inappropriate imagery, displaying on the digital sign either no image or a different image that does not contain inappropriate imagery; and, in response to the detection of inappropriate imagery, displaying on the digital sign the customer user profile image.

Abstract: Various embodiments of a system and associated method for a smart handoff integrated platform for handoff of items to customers in the retail space are disclosed herein.

Abstract: Disclosed is a control method for a test system including a smear imaging unit configured to image a smear of a specimen, the control method including: preparing a plurality of the smears; sequentially storing, in a storing container capable of storing therein a plurality of the smears, the smears having been prepared; and transporting, when information about a standby situation for imaging processing by the smear imaging unit satisfies a predetermined condition, the storing container that stores therein the smears to the smear imaging unit regardless of the number of the smears stored in the storing container.

Abstract: A method of depositing material on an electronic substrate with a dispensing system includes acquiring images of adjacent features, assigning programmed search boxes to edges of the features, identifying programmed edges of the features, for each feature identifying an intersection point of the programmed edges, determining a centerline from the intersection point, determining a midpoint of the, determining an intersect command for a dispense operation between the first component and the second component, and performing the dispense operation.

Abstract: This disclosure provides a hand tracking system. A camera is configured to obtain a hand image of a hand of a user. A tracker is adapted to be attached to an object and configured to obtain tracker data. A processor is configured to determine the hand being touching the object based on the hand image or the tracker data. The processor is configured to determine a contact portion of the object based on the object. The contact portion is adapted to be in contact with the hand of the user. The processor is configured to determine a hand gesture of the user based on the hand image. The processor is configured to determine a hand pose of the hand and an object pose of the object based on the hand gesture and the contact portion.

Abstract: A non-transitory computer-readable recording medium stores a machine learning program for causing a computer to execute processing including: inputting learning data related to a plurality of persons to a first machine learning model, and executing machine learning of the first machine learning model so as to identify a person; extracting a part of layers of the first machine learning model generated by the machine learning; generating a new second machine learning model by using the extracted part of the layers; and inputting a plurality of pieces of learning data related to a predetermined person to the second machine learning model, and executing machine learning of the second machine learning model so as to identify whether or not the person is the same person as the person included in each of the plurality of pieces of learning data.