Abstract: A substrate transfer system includes: a transfer device provided with a substrate holder configured to hold a substrate; a lower line camera provided in a transfer path of the substrate to capture an image of a rear surface of the substrate which is being transferred and an image of the substrate holder; an upper line camera provided in the transfer path of the substrate to capture an image of a front surface of the substrate which is being transferred; and a controller that generates a rear-surface image based on the image captured by the lower line camera and generates a front-surface image based on the image captured by the upper line camera.

Abstract: A method and a device for data processing. The method is adapted to a generative adversarial network obtained by model distillation, and the generative adversarial network includes a first generator, a second generator and a discriminator. The model distillation is a process of alternately training the first generator and the second generator. A model scale of the first generator is smaller than a model scale of the second generator. The method includes: obtaining an image to be processed; and processing the image with a first generator to obtain a processed image.

Abstract: A data exchanging method of pipeline elements is adapted to process a pipeline of a data stream, and includes: processing, by a generic element in the pipeline, first raw data in the data stream to generate first analysis data; receiving and processing, by a first docking element, the first analysis data to generate the; and receiving, by the generic element, data associated with first feedback data and processing, by the generic element, second raw data in the data stream according to the data associated with first feedback data.

Abstract: Methods and systems for macroalgae or marine debris detection are disclosed. A method includes accessing or receiving multispectral aerial images of a target region; preprocessing the aerial images; determining, using one or more characteristics of the aerial images, an image type for each of the aerial images; generating the one or more geospatial data images by: providing preprocessed aerial images of each image type to a machine learning algorithm trained using images having that image type; receiving, as outputs from each DCNN, image data indicating whether macroalgae are present in regions corresponding to each pixel of the aerial images; altering pixel values of the aerial images to visually indicate the presence of macroalgae in regions corresponding to the altered pixel values; and providing the one or more geospatial data images to the user device via a user interface. Other aspects, embodiments, and features are also claimed and described.

Abstract: The disclosure relates to a method for providing a result dataset, a method for providing a trained function, a provisioning unit, a medical imaging device, and a computer program product. The method for providing the result dataset includes capturing medical image data, wherein the medical image data maps a temporal change in an anatomical object in an examination object in a spatially and temporally resolved manner. The method further includes identifying at least one inhomogeneously deforming region of the anatomical object based on the image data and providing the result dataset based on the image data, wherein the result dataset has a dedicated map and/or at least one deformation parameter of the at least one inhomogeneously deforming region.

Abstract: A cell image analysis method according to this invention includes a step of acquiring a cell image (10) including a cell (90); a step of inputting the cell image to a learned model (6) that has learned classification of the cell into one of two or more types; a step of acquiring an index value (20) indicating accuracy of the classification of the cell that is included in the cell image into one of two or more types based on an analysis result of each of pixels of the cell image output from the learned model; and a step of displaying the acquired index value.

Abstract: Computer vision is applied to images of food objects, allowing tracking of sub-objects separated there-from during processing and relating back outcomes observed to original locations within the food object. A method includes: obtaining an image of an object having a pattern; thereafter identifying sub-objects; determining an object location of respective sub-objects relative to the object based on the pattern; and providing an indicator, for the respective sub-objects, associated with the food processing and based on the object location of the respective sub-objects. The indicator may be a highlighted location of the sub-object within a three-dimensional (3D) model, a tracked or predicted outcome or classification, or an adjustment to a food processing step or equipment configuration.

Abstract: A system for the rectification of batch-induced distortions and the extraction of phenotypic attributes from biological images is presented. This system encompasses a deep-learning generative adversarial network model, expertly tailored to converse with and modify the contrast of input images, resulting in the creation of output images. A discriminator, operating as a feedback mechanism, discriminates the output image against the input image, ensuring precise image contrast conversion. Integral to this system is a morphology distillator, having a dual classifier framework comprising a batch classifier and a cell type/state classifier. This distillator adeptly identifies phenotypic characteristics and batch-related disparities, subsequently eradicating these batch variations from the output image. The resultant augmentation enriches the cellular information within the image.

Abstract: Systems and methods of tumor segmentation are receiving data having dimensions of a first size and a first kernel size. A residual volume is produced from the input volume. A first, second, and third intermediate volume are produced by from convolving a first, second, and third dimension volume of the residual volume to 1. A first global volume is produced from sums of the residual volumes. A downsampled volume is produced from the input volume. A residual downsampled volume is produced from the downsampled volume. A first, second, and third intermediate downsampled volume is produced from convolving a first, second, and third dimension volume of the downsampled volume to 1. A second global volume is produced from sums of the intermediate downsampled volumes. The second global volume is upsampled. An output volume is produced from integrating the first global volume and the second global volume.

Abstract: An encoding step and an image selection step are performed by a computer 20. In the encoding step, a plurality of partial images D2 of an object are input to a learned VAE model M, and the plurality of partial images D2 are encoded to a plurality of latent variables in a multi-dimensional latent space. In the image selection step, one or more partial images D2 that are likely to include an alignment mark are selected on the basis of a distribution of the plurality of latent variables in the latent space. Thus, a partial image that is likely to include an alignment mark is automatically detected by the computer 20 with the use of the VAE model M. This can lighten a burden on an operator who searches for an alignment mark.

Abstract: A portable information handling system includes a battery having a pattern that aids in detection of battery swell, such as by capture of a visual image of the battery and pattern with a camera for comparison against a threshold of the pattern distortion that indicates excessive battery swell. For instance, the pattern is parallel lines of a strain gauge that detects strain introduced by battery swell. Distortion of the parallel lines by expansion of the battery due to swelling is detected by changes in distance between the parallel lines and confirmed with distances measured between the camera and the pattern by an infrared depth camera.

Abstract: A system includes a controller configured to receive one or more fixed text prompts and one or more images, wherein the fixed text prompts are associated with the one or more images. The controller is further configured to, in response to utilizing the fixed text prompt and the one or more images at a foundation model associated with a machine-learning network, output an intermediate representation from generating a series of objects and a task, decode the intermediate representation utilizing a decoder associated with the foundation model to generate a matrix associated with the task associated with the fixed text prompt and the image, and in response to identifying a highest probability associated with the matrix utilizing label selection, output a final label associated with a visual based prediction task.

Abstract: Certain embodiments provide a method of generating a color-corrected ophthalmic image. The method comprises obtaining an ophthalmic image of an eye with a nuclear sclerotic cataract or a tinted intraocular lens (“IOL”). The method further comprises determining color-shift information associated with the ophthalmic image based on at least one of user input and by processing the obtained image, the color-shift information indicative of the extent to which color in the obtained image is to be corrected to at least partially remedy the effect of the nuclear sclerotic cataract or the tinted IOL on the color of the obtained image. The method further comprises color-correcting the ophthalmic image based on the color-shift information. The method further comprises generating the color-corrected ophthalmic image based on the color-correcting.

Abstract: A method for determining an intracranial hemodynamic parameter according to embodiments of the present disclosure is provided, which includes determining a three-dimensional a model of a blood vessel based on CT angiographic data, and determining at least one of a boundary condition of each inlet or a boundary condition of each outlet in the three-dimensional vessel model based on CT perfusion imaging data and CT angiographic data.

Abstract: Methods and systems are provided for establishing an activity zone within video captured by a camera. A user device may establish an activity zone or an exclusion zone within video representing a physical view captured by the camera. An automatic monitoring system may analyze the video of the camera with respect to the activity zone or exclusion zone and trigger notifications that are associated with a zone so as to limit notifications transmitted to the user device to those notifications that are relevant to the user. With activity or exclusion zones video from a camera may be automatically monitored to reduce a volume of notifications transmitted to the user device.

Abstract: A method for identifying medical devices, referred to as medical devices of interest, the method including: collecting images of the outer portions of the medical devices of interest, each image being labeled with an identifier of the medical device of interest, the images collected forming a training image database; training an identification model from the training image database in order to obtain an identification model trained to assign an identifier to a medical device of interest to be identified according to an image of the outer portion of the medical device; c. receiving an image of the outer portion of a medical device of interest to be identified; assigning, by the trained classification model, of an identifier to the medical device of interest captured on the received image; and characterizing the medical device of interest according to the assigned identifier.

Abstract: An object of the present invention is to generate a highly accurate trail by correcting detection box information of an object in an object tracking apparatus that generates a trail of an object within a measurement range.

Abstract: Systems and methods are provided for deterministically estimating whether the location of a computing device that is fixed or mobile is inside a building or not using location data. Particularly, the system may compare 3D geoposition uncertainty region of a location to a 3D volumetric structure shape of the location, and determining a confidence value based on the comparison associated with a likelihood that the location associated with the computing device is indoors or outdoors. Various states of the computing device are supported by the substance of the disclosure, including indoor and outdoor states.

Abstract: A method for measuring a feature near the edge of an object comprising receiving image data characterizing the object, identifying an edge of the object, identifying a point on the perimeter of the feature at a position opposite the edge of the object, determining a reference plane, determining a three-dimensional reference line on the reference plane associated with the edge of the object, determining a three-dimensional measurement point on the reference plane based on the point on the perimeter of the feature, and determining the perpendicular distance from the measurement point to the reference line.

Abstract: A method includes providing a sample holder having a plasmonic layer and applying the sample to the sample holder. The sample is illuminated and an image formed. The method enables identifying a structure in the sample from the image based at least partly on its colour. The colour can encode a structural property of the sample, preferably without staining. The method can be used to differentiate a state of at least one cell in a sample. Application to identification of cancer and non-cancer abnormalities are disclosed.