Abstract: In order to provide a learning data generating apparatus that is able to efficiently restrain erroneous detections, the learning data generating apparatus includes a data acquisition unit configured to acquire learning data including teacher data, and a generation unit configured to generate generated learning data based on the learning data and a generating condition, wherein the generation unit converts teacher data of a positive instance into teacher data of a negative instance according to a preset rule when generating the generated learning data.

Abstract: Systems and methods for registering arbitrary visual features for use as fiducial elements are disclosed. An example method includes aligning a geometric reference object and a visual feature and capturing an image of the reference object and feature. The method also includes identifying, in the image of the object and the visual feature, a set of at least four non-colinear feature points in the visual feature. The method also includes deriving, from the image, a coordinate system using the geometric object. The method also comprises providing a set of measures to each of the points in the set of at least four non-colinear feature points using the coordinate system. The measures can then be saved in a memory to represent the registered visual feature and serve as the basis for using the registered visual feature as a fiducial element.

Abstract: A method includes receiving a video comprising images representing an object, and determining, using a machine learning model, based on a first image of the images, and for each respective vertex of vertices of a bounding volume for the object, first two-dimensional (2D) coordinates of the respective vertex. The method also includes tracking, from the first image to a second image of the images, a position of each respective vertex along a plane underlying the bounding volume, and determining, for each respective vertex, second 2D coordinates of the respective vertex based on the position of the respective vertex along the plane. The method further includes determining, for each respective vertex, (i) first three-dimensional (3D) coordinates of the respective vertex based on the first 2D coordinates and (ii) second 3D coordinates of the respective vertex based on the second 2D coordinates.

Abstract: Embodiments of the disclosure provide systems and methods for generating a diagnosis report based on a medical image of a patient. The system includes a communication interface configured to receive the medical image acquired by an image acquisition device. The system further includes at least one processor. The at least one processor is configured to detect a medical condition based on the medical image and automatically generate text information describing the medical condition. The at least one processor is further configured to construct the diagnosis report, where the diagnosis report includes at least one image view showing the medical condition and a report view including the text information describing the medical condition. The system also includes a display configured to display the diagnosis report.

Abstract: A method and system for tone-mapping an image includes determining a tone-curve based on a model of image contrast distortion between the input image and a tone-mapped image and tone-mapping the input image according to the determined tone-curve. Determining the tone curve includes analytically calculating values of the tone-curve that reduce the image contrast distortion within the model of image contrast distortion. A tone-mapping operator includes a noise model generator and a tone-mapping module operable to receive one or more contextual parameters. The tone-mapping module includes an edge-stopping filtering submodule for extracting a base layer and detail layer of the input image, a tone-curve generating submodule and a combining submodule for combining the base layer and detail layer. At least one of the edge-stopping filtering submodule, the tone-curve generating submodule and combining submodule is adjustable based on the contextual parameters.

Abstract: Systems and methods to detect one or more segments of one or more objects within one or more images based, at least in part, on a neural network trained in an unsupervised manner to infer the one or more segments. Systems and methods to help train one or more neural networks to detect one or more segments of one or more objects within one or more images in an unsupervised manner.

Abstract: A system comprising: a document holder; an image sensor directed toward the document holder; a polarized filter between the image sensor and the document holder; a filter motor configured to rotate the polarized filter; one or more processors; and at least one memory having stored thereon computer program code that, when executed by the one or more processors, instructs the one or more processors to: control the filter motor to rotate the polarized filter; control the image sensors to capture a plurality of images of a document within the document holder, the plurality of images corresponding to a respective relative orientations of the polarized filter to the document; identify a feature of the document; and output, in response comparing respective visual characteristics of the feature of the document to corresponding expected visual characteristics of the first feature for the document, an indication of a verification of the document.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an encoder neural network configured to receive a data item and to process the data item to output a compressed representation of the data item. In one aspect, a method includes, for each training data item: processing the data item using the encoder neural network to generate a latent representation of the training data item; processing the latent representation using a hyper-encoder neural network to determine a conditional entropy model; generating a compressed representation of the training data item; processing the compressed representation using a decoder neural network to generate a reconstruction of the training data item; processing the reconstruction of the training data item using a discriminator neural network to generate a discriminator network output; evaluating a first loss function; and determining an update to the current values of the encoder network parameters.

Abstract: Systems and methods in accordance with embodiments of the invention are configured to render images using light field image files containing an image synthesized from light field image data and metadata describing the image that includes a depth map. One embodiment of the invention includes a processor and memory containing a rendering application and a light field image file including an encoded image, a set of low resolution images, and metadata describing the encoded image, where the metadata comprises a depth map that specifies depths from the reference viewpoint for pixels in the encoded image. In addition, the rendering application configures the processor to: locate the encoded image within the light field image file; decode the encoded image; locate the metadata within the light field image file; and post process the decoded image by modifying the pixels based on the depths indicated within the depth map and the set of low resolution images to create a rendered image.

Abstract: A method of filtering a target pixel in an image forms, for a kernel of pixels comprising the target pixel and its neighbouring pixels, a data model to model pixel values within the kernel; calculates a weight for each pixel of the kernel comprising: (i) a geometric term dependent on a difference in position between that pixel and the target pixel; and (ii) a data term dependent on a difference between a pixel value of that pixel and its predicted pixel value according to the data model; and uses the calculated weights to form a filtered pixel value for the target pixel, e.g. by updating the data model with a weighted regression analysis technique using the calculated weights for the pixels of the kernel; and evaluating the updated data model at the target pixel position so as to form the filtered pixel value for the target pixel.

Abstract: Automated and objective methods for quantifying a retinal characteristic include segmenting an optical coherence tomography retinal image into a plurality of layered retinal regions, and quantifying the retinal characteristic for each region as normalized to a range defined by the characteristic value in the vitreous region and in the retinal pigment epithelium region. Such methods are useful for detecting occult ocular pathology, diagnosing ocular pathology, reducing age-bias in OCT image analysis, and monitoring efficacy ocular/retinal disease therapies.

Abstract: A device may receive document image data that includes an image of a document to be digitized. The device may detect, from the document image data, a table of information that is depicted in the image. The device may determine a data extraction score associated with a table image, wherein the data extraction score is associated with using a data conversion technique to convert the table image to digitized table data. The device may perform, based on the data extraction score not satisfying a threshold, a morphological operation on the table image to generate an enhanced table image that corresponds to an enhanced table of information associated with the table of information. The device may process, using the data conversion technique, the enhanced table image to extract the information from the enhanced table. The device may perform an action associated with the extracted information.

Abstract: In various examples, the present disclosure relates to using temporal filters for automated real-time classification. The technology described herein improves the performance of a multiclass classifier that may be used to classify a temporal sequence of input signals—such as input signals representative of video frames. A performance improvement may be achieved, at least in part, by applying a temporal filter to an output of the multiclass classifier. For example, the temporal filter may leverage classifications associated with preceding input signals to improve the final classification given to a subsequent signal. In some embodiments, the temporal filter may also use data from a confusion matrix to correct for the probable occurrence of certain types of classification errors. The temporal filter may be a linear filter, a nonlinear filter, an adaptive filter, and/or a statistical filter.

Abstract: Head pose information may be determined using information describing a fixed gaze and image data corresponding to a user's eyes. The head pose information may be determined in a manner that is disregards facial features with the exception of the user's eyes. The head pose information may be usable to interact with a user device.

Abstract: An image decoding apparatus obtain pieces of coded data that is included in a bitstream and generated by coding tiles. Tile boundary independence information is further obtained from the bitstream, with the tile boundary independence information indicating whether each of boundaries between the tiles is one of a first boundary or a second boundary. The pieces of coded data are decoded to generate image data of the tiles. Image data of a first tile is generated by decoding a first code string included in first coded data with reference to decoding information of a decoded tile when the tile boundary independence information indicates the first boundary, and by decoding the first code string without referring to the decoding information of the decoded tile when the tile boundary independence information indicates the second boundary.

Abstract: A device implementing a system for machine-learning based gesture recognition includes at least one processor configured to, receive, from a first sensor of the device, first sensor output of a first type, and receive, from a second sensor of the device, second sensor output of a second type that differs from the first type. The at least one processor is further configured to provide the first sensor output and the second sensor output as inputs to a machine learning model, the machine learning model having been trained to output a predicted gesture based on sensor output of the first type and sensor output of the second type. The at least one processor is further configured to determine the predicted gesture based on an output from the machine learning model, and to perform, in response to determining the predicted gesture, a predetermined action on the device.

Abstract: Systems and methods of encoding display data include performing a part of a first predetermined transform algorithm on at least a first part of a first frame of display data, and analyzing a light level to determine whether a different transform algorithm would be more suitable for encoding a second part of the first frame of the display data. If it is determined that a different transform algorithm would be more suitable for encoding, the second part of the first frame of the display data is encoded using the different transform algorithm to generate an encoded first frame. If it is determined that a different transform algorithm would not be more suitable for encoding, the second part of the first frame of the display data is encoded using the first predetermined transform algorithm to generate the encoded first frame.

Abstract: A seed camera disposed a first location is manually calibrated. A second camera, disposed at a second location, detects a physical marker based on predefined characteristics of the physical marker. The physical marker is located within an overlapping field of view between the seed camera and the second camera. The second camera is calibrated based on a combination of the physical location of the physical marker, the first location of the seed camera, the second location of the second camera, a first image of the physical marker generated with the seed camera, and a second image of the physical marker generated with the second camera.

Abstract: Described herein are software and systems for analyzing videos and/or images. Software and systems described herein are configured in different embodiments to carry out different types of analyses. For example, in some embodiments, software and systems described herein are configured to locate an object of interest within a video and/or image.

Abstract: An image decoding method according to the present document comprises the steps of: deriving transform coefficients through inverse quantization on the basis of quantized transform coefficients for a target block; deriving modified transform coefficients on the basis of an inverse reduced secondary transform (RST) for the transform coefficients; and generating, on the basis of an inverse primary transform for the modified transform coefficients, a restoration picture based on residual samples for the target block, wherein the modified transform coefficients derived according to the inverse RST are two-dimensionally arranged according to the order of a row priority direction or a column priority direction according to an intra prediction mode to be applied to the target block.