Abstract: A device and a method for detecting a purpose of an article are provided. The device is configured to divide the article into a plurality of sentences and input the sentences to a feature identification model to generate a contextualized word vector corresponding to each of the sentences. The device further inputs the representation to a specific purpose detecting model to generate a distributed representation similarity of the article. When the distributed representation similarity of the article is greater than a threshold, the device determines that the article conforms to a specific purpose.

Abstract: To enable a good HDR image or video coding technology, being able to yield high dynamic range images as well as low dynamic range images, we invented a method of encoding a high dynamic range image (M_HDR), comprising the steps of: converting the high dynamic range image to an image of lower luminance dynamic range (LDR_o) by applying a) scaling the high dynamic range image to a predetermined scale of the luma axis such as [0,1], b) applying a sensitivity tone mapping which changes the brightnesses of pixel colors falling within at least a subrange comprising the darker colors in the high dynamic range image, c) applying a gamma function, and d) applying an arbitrary monotonically increasing function mapping the lumas resulting from performing the steps b and c to output lumas of the lower dynamic range image (LDR_o); and outputting in an image signal (S_im) a codification of the pixel colors of the lower luminance dynamic range image (LDR_o), and outputting in the image signal (S_im) values encoding the f

Abstract: The technology described herein is directed to systems, methods, and software for indexing video. In an implementation, a method comprises identifying one or more regions of interest around target content in a frame of the video. Further, the method includes identifying, in a portion of the frame outside a region of interest, potentially empty regions adjacent to the region of interest. The method continues with identifying at least one empty region of the potentially empty regions that satisfies one or more criteria and classifying at least the one empty region as a negative sample of the target content. In some implementations, the negative sample of the target content in a set of negative samples of the target content, with which to train a machine learning model employed to identify instances of the target content.

Abstract: Certain aspects and features of the present disclosure relate to analysis of physical media copies of wellbore schematics and the generation of corresponding digital wellbore schematics. Wellbore data may be analyzed by a wellbore schematic analysis tool to produce a structured data file containing information harvesting from a physical media copy of a wellbore schematic. This information may be compared to data from other wellbores and or may be used to generate a new digital wellbore schematic.

Abstract: Disclosed is a medical system for displaying and recording injection sites of patients. After patient identification based on the patient's vein patterns, the system can retrieve and display previous injection sites (e.g., for blood draw or injection) of the patient as overlaid at actual positions of the injection sites. The system can determine potential new injection sites based on the locations of the previous injection sites. The system can also ensure workflow compliance by displaying and tracking procedures performed by the healthcare professional.

Abstract: A system includes a neural network implemented by one or more computers, in which the neural network includes an image depth prediction neural network and a camera motion estimation neural network. The neural network is configured to receive a sequence of images. The neural network is configured to process each image in the sequence of images using the image depth prediction neural network to generate, for each image, a respective depth output that characterizes a depth of the image, and to process a subset of images in the sequence of images using the camera motion estimation neural network to generate a camera motion output that characterizes the motion of a camera between the images in the subset. The image depth prediction neural network and the camera motion estimation neural network have been jointly trained using an unsupervised learning technique.

Abstract: A method, a device and a terminal for generating training data is provided. The method for generating training data includes: obtaining an original image; determining a transferred image based on the image style transfer model and the original image, wherein the image style transfer model is obtained by minimizing a loss function, the loss function is determined by the original loss function the background loss function and the foreground loss function; determining the training data based on the transferred image. The difference between the generated training data and the target image is small, thereby improving the accuracy of the training model obtained by using the training data.

Abstract: System and method to recognise characters from an image are disclosed. The method includes receiving the at least one image, pre-processing the at least one image, extracting a plurality of characters from the corresponding at least one image, extracting at least one structure from the corresponding at least one image upon applying an edge detection technique to extract a structure, identifying a template based on extracted structure, subjecting the plurality of characters into a plurality of ensemble AI models to extract one of a plurality of texts, a plurality of non-textual data and a combination thereof, comparing a plurality of extracted plurality of texts, a plurality of non-textual data, or a combination thereof from the corresponding plurality of ensemble AI models with each other, generating a confidence score and validating one of the plurality of accurate texts, the plurality of accurate non-textual data, or a combination thereof.

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: Visual content may be captured by an image capture device. The characteristics of the visual content may be determined based on assessment of separate visual content and without assessment of the visual content. The assessment of the separate visual content may include identification of thing(s) depicted within the separate visual content. The separate visual content may be temporally and/or spatially separate from the visual content.

Abstract: A cluster classification device includes an environmental condition acquisition unit, a classification unit, and a storage unit. The environmental condition acquisition unit acquires an environmental condition in order to generate a specific environment in a target space. The classification unit generates a cluster from a plurality of environmental conditions acquired by the environmental condition acquisition unit, based on features of the environmental conditions. The storage unit stores the cluster and a feature of the cluster in association with each other. An environment generation device generates, using an environmental condition classified by the cluster classification device, a predetermined environment in the target space. An environment generation system includes the cluster classification device and a control device that controls an environment generation device that generates a specific environment in the target space.

Abstract: A first plurality of images obtained via an image capture device is obtained. A first set of pixels in a first image of the first plurality of images identify is identified based on specified criteria. A first set of coordinates associated with the first set of pixels is determined. A second set of coordinates is generated based on the first set of coordinates. A second set of pixels in a second image of the first plurality of images is identified, based on the specified criteria and a proximity to the second set of coordinates. A first trajectory between the first set of pixels and the second set of pixels is generated. The first trajectory is determined to correspond to a second trajectory associated with a second plurality of images obtained via a second image capture device, and the first trajectory and the second trajectory are outputted.

Abstract: Systems and methods for using facial patterns for information access via optical barcodes are provided. In example embodiments, a computer accesses an image. The computer determines, using facial recognition, that the accessed image includes a face. The computer determines, using the face, an orientation of the image. The computer decodes, based on the determined orientation of the image, data encoded within the geometric shape. The computer may then access a resource based on the decoded data. In some aspects, a graphical output may be presented on a display device indicating the accessed resource.

Abstract: A method and a system of distributed estimation using q-diffusion least mean squares (qDiff-LMS) to modify adaptive filter weights in a decentralized wireless sensor network of N nodes is described. The method includes receiving, at each node, k, a local estimate of a previous time instance weight, wk(i?1), of an adaptive filter of each neighboring node, l, where l=1, 2, . . . , M, combining the local estimates of the previous time instance weights to generate a linear combination of global diffused weights, Øk(i?1), measuring, for each node k, an output, yk(i), of the adaptive filter of the node k, calculating, for each node k, a desired response, dk(i); generating, for each node k, an estimation error, ekCTA(i) by subtracting the output, yk(i) from the desired response, dk(i), and updating the global diffused weights by adding a portion of the estimated error to the global diffused weights.

Abstract: Methods of processing video are presented to generate signatures for motion segmented regions over two or more frames. Two frames are differenced using an adaptive threshold to generate a two-frame difference image. The adaptive threshold is based on a motion histogram analysis which may vary according to motion history data. Also, a count of pixels is determined in image regions of the motion adapted two-frame difference image which identifies when the count is not within a threshold range to modify the motion adaptive threshold. A motion history image is created from the two-frame difference image. The motion history image is segmented to generate one or more motion segmented regions and a descriptor and a signature are generated for a selected motion segmented region.

Abstract: Methods of segmenting an abdominal image, computer apparatuses and storage mediums. The method includes acquiring an abdominal image to be examined; and classifying pixels in the abdominal image to be examined based on a trained full convolution neural network, and determining a segmented image corresponding to the abdominal image to be examined, wherein the trained full convolution neural network is trained and determined based on a first training set and a second training set, the first training set includes first sample abdominal images and pixel classification label images corresponding to the first sample abdominal images, the second training set includes second sample abdominal images and the number of pixels of second sample abdominal images correspondingly belong to each class. Through the methods herein, the accuracy of the segmentation can be improved.

Abstract: In a console according to an embodiment, a control unit functions as a generation unit that generates a tomographic image from a plurality of projection images, which have been captured by a radiation detector at each of a plurality of imaging positions with different irradiation angles, with radiation sequentially emitted from each of the plurality of imaging positions, using a reconstruction process. In addition, the control unit functions as a derivation unit that derives the degree of enhancement as a parameter value used in a frequency enhancement process which is an example of image processing for a tomographic image, on the basis of the image analysis result of a projection image corresponding to an irradiation angle of 0 degrees.

Abstract: In an approach for an automatic document separation, a processor extracts one or more features from a document containing a plurality of pages. A processor generates a data frame based on the feature extraction. In response to analyzing a similarity between the plurality of pages, a processor determines whether the similarity exceeds a predetermined threshold. In response to determining that the similarity does not exceed the predetermined threshold, a processor transforms text into vectors forming float arrays. In response to benchmarking a set of predetermined clustering algorithms, a processor identifies a clustering algorithm using a predetermined criterion. A processor clusters the plurality of pages, using the clustering algorithm, to create a group of pages. A processor validates the clustered group of pages. In response to passing validation, a processor generates a set of final separated files based on the clustered group of pages.

Abstract: According to an aspect of an embodiment, operations include receiving a set of datapoints for integrated clustering and outlier detection. The operations further include receiving, as a first input, a clustering constraint comprising a number of outlier datapoints to be detected from the set of datapoints and a second input including a distance metric. The operations further include formulating an objective function based on the first and second inputs and transforming the objective function into an unconstrained binary optimization formulation. The operations further include providing such formulation as input to an optimization solver machine and generating a clustering result and an outlier detection result based on output of the optimization solver machine for the input. The clustering result includes a set of datapoint clusters, and the outlier detection result includes a set of outlier datapoints. The clustering result and the outlier detection result are published on a publisher system.

Abstract: A method of generating a training sample for matching unlabelled objects in a sequence of images. A first representation of unlabelled objects is generated from images of a first and second set of images. A second representation of the unlabelled objects is generated using an unsupervised method. An anchor image in the first set is selected. A first set of candidate images in the second set that are close to the anchor image in both the first and second representations, is determined. A second set of candidate images in the second set that are distant from the anchor image in either the first or the second representations, is determined. A match candidate image is selected from the first set or the second set of candidate images. The training sample is generated from at least the anchor image and the match candidate image.