Abstract: A finite element (FE) model of an anatomical structure is generated based on a fitted model of the anatomical structure and association data. A segmentation model is provided for segmenting the anatomical structure. Association data is obtained which associates a segmentation model part of the segmentation model with a mesh property. The segmentation model part represents a pre-determined anatomical region of interest. The segmentation model is applied to a medical image of a subject, thereby obtaining the fitted model for segmenting the anatomical structure. The finite element model is generated based on the fitted model and the association data, by meshing a finite element model part of the finite element model corresponding with the pre-determined anatomical region of interest in accordance with the mesh property. Advantageously, this results in an efficient generation of the FE model needing fewer manual iterations and/or alterations in the model or in the mesh.

Abstract: The invention relates to a system and process for generating digital images of a site having a structure with superimposed intersecting grid lines and annotations. The process includes acquiring a plurality of digital images, still frames and/or video images of the site, the structure, or both, with each of the digital images. The structure, the site and points of interest within the digital images are identified, and then the system and process photogrammetrically generates a three-dimensional point cloud from the digital images. The identified structures, objects and features are then used to calculate measurements and provide masking and annotations in order to generate the two-dimensional stitched and annotated digital image of the site and/or the structure.

Abstract: A method and apparatus of detection, registration and quantification of an image is described. The method may include obtaining an image of a lithographically created structure, and applying a level set method to an object, representing the structure, of the image to create a mathematical representation of the structure. The method may include obtaining a first dataset representative of a reference image object of a structure at a nominal condition of a parameter, and obtaining second dataset representative of a template image object of the structure at a non-nominal condition of the parameter. The method may further include obtaining a deformation field representative of changes between the first dataset and the second dataset. The deformation field may be generated by transforming the second dataset to project the template image object onto the reference image object. A dependence relationship between the deformation field and change in the parameter may be obtained.

Abstract: An autofocus control device includes a processor. The processor performs an image acquisition process of acquiring an object image captured by an imaging section, a treatment determination process of determining whether or not treatment is being performed based on the object image, a focus evaluation area setting process of setting either a preset area or a treatment area set based on the object image, as a focus evaluation area in the object image based on a determination result of the treatment determination process, and a focus control process of performing focus control of the imaging section based on a focus evaluation value of the focus evaluation area.

Abstract: A facility providing systems and methods for discovering novel features to use in machine learning techniques. The facility receives, for a number of subjects, one or more sets of data representative of some output or condition of the subject over a period of time or capturing some physical aspect of the subject. The facility then extracts or computes values from the data and applies one or more feature generators to the extracted values. Based on the outputs of the feature generators, the facility identifies novel feature generators for use in at least one machine learning process and further mutates the novel feature generators, which can then be applied to the received data to identify additional novel feature generators.

Abstract: An apparatus for calibrating a multiview image may extract feature points from the multiview image and perform image calibration based on the extracted feature points, track corresponding feature points in temporally successive image frames of a first view image, and perform the image calibration based on pairs of corresponding feature points between the feature points tracked from the first view image and feature points of a second view image.

Abstract: An information processing device is configured to: obtain sensing data from an optical sensor; obtain position information of a mobile body which includes the optical sensor; obtain map information; determine, in sensing data, a specific sensing data region corresponding to a specific region in a sensing region of the optical sensor by using the position information and the map information that have been obtained; determine input information to be provided to an object detection model, according to the specific sensing data region; and cause the object detection model to perform object detection processing by using the input information.

Abstract: A scene model constructing method includes the following steps. According to multiple position parameters in multiple scene materials, classifying the scene materials into multiple position groups. According to scene similarities between the scene materials, classifying the scene materials into multiple first similar image sub-groups and multiple second similar image sub-groups. Establishing a first similar image sub-model and a second similar image sub-model respectively according to the first similar image sub-group and the second similar image sub-group. Combining a first similar image sub-model to a first position model, and combining a second similar image sub-model to a second position model. Finally, combining the first position model and the second position model to a scene model.

Abstract: An information processing method includes: acquiring fixed values which are imaging conditions of a first image formed in a state in which a background and a predetermined subject located in front of the background are within an imaging visual field, from the first image; acquiring a learning image as background learning data, wherein the learning image is captured using the fixed values in a second image formed in a state in which the subject is outside of the imaging visual field; extracting a difference image between the background learning data and an input image obtained by capturing the first image using the fixed values; and generating a combined image obtained by combining the difference image with a combination background image.

Abstract: A method includes: executing a first generation process that includes generating a Betti number series corresponding to a contribution rate by performing persistent homology processing on a first point set, the first point set being generated by using a plurality of pieces of time series data and the contribution rate of each of the plurality of pieces of time series data, each of points included in the first point set being represented by coordinates; executing a second generation process that includes generating a characteristic image from a plurality of the Betti number series, the plurality of Betti number series being generated by performing the first generation process on each of the plurality of contribution rates; and executing a third generation process that includes generating machine learning data in which the characteristic image and a classification corresponding to the plurality of pieces of time series data are associated with each other.

Abstract: Provided is a service providing apparatus using satellite imagery. The service providing apparatus includes a satellite image information acquirer configured to acquire a satellite image; an object extractor configured to analyze the satellite image, extract an object from the satellite image, and generate an object image corresponding to the object; a storage configured to store the satellite image and the object image; and a service processing unit configured to provide an object extraction-based service and coding data associated with the object extraction-based service, based on at least one of the satellite image and the object image, and thereby provides a method of identifying and classifying various types of objects and buildings present on the ground surface based on image data on the ground surface.

Abstract: A non-photorealistic image rendering system and related techniques are described herein that train and implement machine learning models to reproduce digital images in accordance with various painting styles and constraints. The image rendering system can include a machine learning system that utilizes actor-critic based reinforcement learning techniques to train painting agents (e.g., models that include one or more neural networks) how to transform images into various artistic styles with minimal loss between the original images and the transformed images. The image rendering system can generate constrained painting agents, which correspond to painting agents that are further trained to reproduce images in accordance with one or more constraints. The constraints may include limitations of the color, width, size, and/or position of brushstrokes within reproduced images. These constrained painting agents may provide users with robust, flexible, and customizable non-photorealistic painting systems.

Abstract: Embodiments may: select a set of training images; extract a first set of features from each training image of the set of training images to generate a first feature tensor for each training image; extract a second set of features from each training image to generate a second feature tensor for each training image; reduce a dimensionality of each first feature tensor to generate a first modified feature tensor for each training image; reduce a dimensionality of each second feature tensor to generate a second modified feature tensor for each training image; construct a first generative model representing the first set of features and a second generative model representing the second set of features of the set of training images; identify a first candidate image; and apply a regression algorithm to the first candidate image and each of the first generative model and the second generative model to determine whether the first candidate image is similar to the set of training images.

Abstract: A method of accelerated iris recognition includes acquiring an image comprising at least an iris and a pupil, segmenting the iris and the pupil using a fully convolutional network (FCN) model, normalizing the segmented iris, encoding the normalized iris, the normalizing and encoding using a rubber sheet model and 1-D log Gabor filter, and masking the encoded iris.

Abstract: Provided is an apparatus for processing image blurring configured to extract a sample image by calculating a blur generation area through scales of a horizontal length and a vertical length of an original image, read a pixel value corresponding to the blur generation area calculated from the original image and perform a bitwise operation on the sample image, and set, at a pixel of the sample image changed by the bitwise operation, a result value of the bitwise operation. In this case, the bitwise operation performed on the sample image includes applying the same blurring value on n pixel regions adjacent to a corresponding pixel of the sample image to reduce the time for removing image noise.

Abstract: An ultrasound apparatus includes a touch screen configured to display, on an ultrasound image, a touch recognition region of an object used as a measurement mark; and a controller configured to move the object and the touch recognition region, in response to an input for touching and dragging the touch recognition region, to detect, from a portion of the ultrasound image which corresponds to the touch recognition region, a line formed by connecting points at which a brightness variation of a pixel is greater than a threshold value, and to move the object to a position of the detected line by using coordinates of the detected line.

Abstract: An apparatus includes at least one processor configured to function as following units including a first difference extraction unit configured to extract a first difference between a plurality of images, an alignment unit configured to correct a position of an image with reference to a predetermined subject within the plurality of images, a second difference extraction unit configured to extract a second difference between the plurality of images after the position of the image is corrected by the alignment unit, and a detection unit configured to detect a moving object area based on the extracted first difference and the extracted second difference.

Abstract: An example method includes receiving a data set, each data point in the data set being associated with an indication of time, and a distance function, determining overlapping intervals over a time period range, identifying subsets of data in each overlapping interval based on the indications of time, applying the distance function to each subset of data to identify groups, constructing a node for each group to create a plurality of nodes, determining if two nodes of the plurality of nodes in adjacent time periods are connected by scoring shared data point membership between the two nodes and comparing a score of the shared data point membership to a threshold, and displaying at least two nodes with an indication of time, the two nodes being connected by a line based on the comparison of the score and the threshold.

Abstract: An image processing method is for detecting the edge of a well where cells are analyzed, from image data obtained by capturing the well and surroundings of the well, and an edge coordinate group for the well is extracted from the image data. If a plurality of edge coordinate groups has been extracted, edge candidates for the well are generated for each of the plurality of edge coordinate groups. Then, an edge candidate that satisfies a predetermined reference value is selected from among the generated edge candidates. If a plurality of edge candidates has been selected, relative evaluations are conducted to determine the edge of the analysis region from among the plurality of edge candidates.

Abstract: A method of encoding images and a method of decoding images. The method of encoding comprises dividing an input image into a first input portion and a plurality of input rings that are concentric with the first input portion, the first input portion and the plurality of input rings being shaped as a simple closed curve; storing the first input portion into a first image; packing the plurality of input rings into a second image, second image having a plurality of rows, a given input ring of input image being packed into a corresponding row of second image; and communicating, to a display apparatus, the first image, the second image and information indicative of a size of the first input portion and sizes of the plurality of input rings.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for neural network-based optical character recognition. An embodiment of the system may generate a set of bounding boxes based on reshaped image portions that correspond to image data of a source image. The system may merge any intersecting bounding boxes into a merged bounding box to generate a set of merged bounding boxes indicative of image data portions that likely portray one or more words. Each merged bounding box may be fed by the system into a neural network to identify one or more words of the source image represented in the respective merged bounding box. The one or more identified words may be displayed by the system according to a standardized font and a confidence score.

Abstract: A method of generating a surface model of a physical environment includes obtaining an image of the physical environment. The method also includes generating a planar polygon mesh from at least the image. The method further includes extracting a boundary polygon of the planar polygon mesh. Moreover, the method includes generating a convex hull for the boundary polygon of the surface mesh. In addition, the method includes generating a minimal area oriented boundary polygon from the convex hull. The method may also include generating a maximal area oriented internal polygon inside of the boundary polygon of the planar polygon mesh.

Abstract: Image processing method, drone, and drone-camera system are provided. The method includes acquiring, according to a current environmental parameter of the drone, a target sky image that matches the current environmental parameter; and determining a direction parameter of the camera device when capturing a to-be-stitched image. The to-be-stitched image is an image captured under the current environmental parameter. The method further includes stitching the target sky image with the to-be-stitched image according to the direction parameter to obtain a panoramic image.

Abstract: Systems and techniques that facilitate real-time and/or offline de-identification of facial regions from regular and/or occluded color video streams obtained during diagnostic medical procedures are provided. A detection component can generate a bounding box substantially around a person in a frame of a video stream, can generate a heatmap showing key points or anatomical masks of the person based on the bounding box, and can localize a face or facial region of the person based on the key points or anatomical masks. An anonymization component can anonymize pixels in the frame that correspond to the face or facial region. A tracking component can track the face or facial region in a subsequent frame based on a structural similarity index between the frame and the subsequent frame being above a threshold.

Abstract: A method of identifying a background type in a photograph includes extracting a background image from a photograph, feeding the background image into a first convolution neural network to obtain a first decision, extracting color features in the background image, transforming the color features into a two-dimensional color feature matrix, feeding the two-dimensional color feature matrix into a second convolution neural network to obtain a second decision by the one or more computer processors, extracting texture features in the background image, transforming the texture features into a two-dimensional texture feature matrix image by the one or more computer processors, feeding the two-dimensional texture feature matrix into a third convolution neural network to obtain a third decision, computing a hybrid decision based on the first decision, the second decision, and the third decision, and identifying a background type in the background image based on the hybrid decision.

Abstract: Examples of an apparatus are disclosed. In some example, an apparatus may include an array of digital pixel cells, each digital pixel cell including a photodiode and a memory device to store a digital output generated based on charge generated by the photodiode in an exposure period. The apparatus may also include an image processor configured to: receive first digital outputs from the memory devices of a first set of digital pixel cells of the array of digital pixel cells; determine, from the first set of digital pixel cells, a second set of digital pixel cells of which the first digital outputs satisfy one or more pre-determined conditions; identify, based on the second set of digital pixel cells, a third set of digital pixel cells; receive the second digital outputs generated by the third set of digital pixel cells; and perform image processing operations based on the second digital outputs.

Abstract: Techniques for mapping size information associated with a client to target brands, garments, sizes, shapes, and styles for which there is no standardized correlation. The size information associated with a client may be generated by modeling client garments, accessing computer aided drawing (CAD) files associated with client garments, or by analyzing a history of garment purchases associated with the client. Information for target garments may be generated in a similar fashion. A system may then create a standardized scale with a set of sizes for a target, and map a client base size to that standardized size scale. Similar matching and mapping may also be done with shape and style considerations. A recommendation based on the mapping may then be communicated to the client.

Abstract: A method of processing a page of a document. A plurality of commands describing graphical objects of the page configured to be reproduced in a first presentation mode are received, the plurality of commands indicating a type of each of the graphical objects, an enclosing region and a drawing order associated with each of the graphical objects. An object significance score is determined for each of the graphical objects using the respective object type and object depth. A significance profile for the page is determined by combining the determined object significance scores according to a page layout, the page layout being determined using the enclosing regions associated with the graphical objects. Logical structure elements of the page are determined using the significance profile. The plurality of commands are processed according to the determined logical structure elements for generating the page of the document in a second presentation mode.

Abstract: An information processing device includes: a memory; and a processor coupled to the memory and configured to: accept specification of a feature region that includes a characteristic portion in a learning image; create first data that indicates a degree of overlap between the feature region and each of divided regions obtained by dividing the learning image; perform image conversion on the learning image by an image classification program in which element filters are combined; calculate an image feature value of each of the divided regions from an image obtained; create second data that indicates the image feature value corresponding to each of the divided regions; calculate a similarity between the first data and the second data; and use a result of evaluating the image classification program on the basis of the similarity, for execution of a genetic programming.

Abstract: A system and a method for counting objects includes the steps of: obtaining a plurality of images representing the objects to be counted in a target area; generating a map for each of the plurality of images representing an identification of each of the corresponding objects; and fusing the plurality of maps being generated to obtain a scene-level density map representing a count of the objects in the target area.

Abstract: A computer implemented method includes supplying to a user at a client device a prompt to contact a matched individual. A proposed communication from the user to the matched individual is monitored. The proposed communication is compared to a set of effective communication policies to selectively identify an effective communication policy violation. A warning is supplied to the user in response to the effective communication policy violation. A signal is received from the user to send a completed communication to the matched individual. Network routing of the completed communication from the client device to the matched individual is enabled.

Abstract: An image processing device includes circuitry configured to: calculate a displacement of each of a plurality of corresponding feature regions between a reference image and a base image; calculate, as a evaluation score, difference value between displacements of two feature regions adjacent to each other in at least one of the up/down direction, the left/right direction, and the oblique 45° direction; determine an abnormal region on the basis of the score; classify other feature regions excluding the abnormal feature region; calculate a projection conversion matrix by using the displacement of the other feature regions and the result of the classification; calculate a degree of alignment of each pixel of the reference image with respect to each pixel of the base image by using the matrix; and generate a combined image by combining the reference image converted based on the degree of alignment with the base image.

Abstract: The present disclosure is directed toward systems, methods, and non-transitory computer readable media for generating a modified digital image by identifying patch matches within a digital image utilizing a Gaussian mixture model. For example, the systems described herein can identify sample patches and corresponding matching portions within a digital image. The systems can also identify transformations between the sample patches and the corresponding matching portions. Based on the transformations, the systems can generate a Gaussian mixture model, and the systems can modify a digital image by replacing a target region with target matching portions identified in accordance with the Gaussian mixture model.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining the identity of a user. In one aspect, a method comprises: obtaining at least one image depicting a reflection of light from a lens that is included in a set of eyeglasses; determining, based on the reflection of light from the lens, a set of features characterizing the lens; and determining an identity of a corresponding user based at least in part on the set of features characterizing the lens.

Abstract: An ultrasound medical imaging method includes: displaying an ultrasound image on a screen; determining a view plane, on which the displayed ultrasound image is captured, among view planes; and setting a region of interest corresponding to the determined view plane on the ultrasound image.

Abstract: Provided herein are a display device and an image processing method thereof. The display device includes an image processor processing original image data including color coordinate values for R, G, and B components in an RGB color space, and output processed original image data as corrected image data, and a display unit outputting an image corresponding to the corrected image data, wherein the image processor sets a corrected color coordinate value for an arbitrary component of the R, G, and B components based on a type of the image, sets corrected color coordinate values for remaining components in accordance with the corrected color coordinate value for the arbitrary component, and generates the corrected image data based on the corrected color coordinate values for the arbitrary component and the remaining components.

Abstract: Mechanisms and processes for enhancing limited datasets for use in training or deep learning models are discussed. Such creation generates synthetic overhead imagery based on cluster sampling and spatial aggregator factors (SAFs). The implementation accomplishes this by generating Synthetic images created by cropping objects from original images and inserting them into uniform, natural or synthetic backgrounds. The objects are selected from clusters based on pixel distribution similarity, and through SAFs mining then used for the synthetic data generation.

Abstract: A method for condition monitoring of an installation with operating devices, in which overview data is detected by a first vehicle with an overview sensor arrangement for optical detection of the facility, and the operating devices are identified in the overview data by an evaluation device and the positions of the operating devices are determined taking into account the position of the first vehicle. Detail shots of the operating devices are produced by a detail camera on-board a second or the first vehicle, which is oriented in relation to the respective positions of the operating devices. There is a corresponding arrangement for carrying out the method. A mode of embodiment relates to the condition monitoring of high-voltage masts with high-voltage free lines that are clamped between the masts. Insulators hang on the transverse members as operating devices.

Abstract: Aspects of the subject disclosure may include, for example, a method performed by a processing system of determining a present orientation of a display region presented at a first time on a display of a video viewer, predicting a future orientation of the display region occurring at a second time based on data collected, to obtain a predicted orientation of the display region to be presented at the second time on the display of the video viewer, identifying, based on the predicted orientation of the display region, a first group of tiles from a video frame of a panoramic video being displayed by the video viewer, wherein the first group of tiles covers the display region in the video frame at the predicted orientation, and a plurality of objects moving in the video frame from the first time to the second time, wherein each object of the plurality of objects is located in a separate spatial region of the video frame at the second time, wherein a second group of tiles collectively covers the separate spatial re

Abstract: An image identification apparatus includes an extraction unit, an excluding unit, and an identification unit. The extraction unit extracts lines from an image. The exclusion unit excludes from objects to be identified a boundary delimiting an entire area of the image among the extracted lines. The identification unit identifies as an object multiple lines that are among the extracted lines and that are not excluded by the exclusion unit if the multiple lines are connected to each other.

Abstract: In various embodiments, the present invention provides a system and associated methods of calibration and use for an interactive imaging environment based on the optimization of parameters used in various segmentation algorithm techniques. These methods address the challenge of automatically calibrating an interactive imaging system, so that it is capable of aligning human body motion, or the like, to a visual display. As such the present invention provides a system and method of automatically and rapidly aligning the motion of an object to a visual display.

Abstract: Multiple detection techniques are used to determine whether the individual pixels in an image are background or foreground. The outputs from the multiple techniques are combined according to a confidence metric associated with each technique, which may vary from pixel to pixel. The resulting blended value for each pixel is compared with a threshold to determine whether the pixel is foreground or background.

Abstract: Techniques are disclosed for deep neural network (DNN) based interactive image matting. A methodology implementing the techniques according to an embodiment includes generating, by the DNN, an alpha matte associated with an image, based on user-specified foreground region locations in the image. The method further includes applying a first DNN subnetwork to the image, the first subnetwork trained to generate a binary mask based on the user input, the binary mask designating pixels of the image as background or foreground. The method further includes applying a second DNN subnetwork to the generated binary mask, the second subnetwork trained to generate a trimap based on the user input, the trimap designating pixels of the image as background, foreground, or uncertain status. The method further includes applying a third DNN subnetwork to the generated trimap, the third subnetwork trained to generate the alpha matte based on the user input.

Abstract: An information processing apparatus having a camera function, including: a display control unit configured to display a live view image acquired via a camera on a display unit; and an image analysis unit configured to perform, when performing an image capturing of an object every area: projective transformation of an image of an already-captured area of the object, for which image capturing has already been completed, onto a plane space of the live view image; and an image analysis to display the image of the already-captured area for which the projective transformation has been performed along with the live view image, and the display control unit displays, in accordance with analysis results by the image analysis unit, the image of the already-captured area for which the projective transformation onto the plane space of the live view image has been performed.

Abstract: A crop generation system determines multiple types of saliency data and multiple crop candidates for an image. Multiple region of interest (“ROI”) ensembles are generated, indicating locations of the salient content of the image. For each crop candidate, the crop generation system calculates an evaluation score. A set of crop candidates is selected based on the evaluation scores.

Abstract: A method and an electronic device for enhancing efficiency of searching for a region of interest in a virtual environment are provided. The virtual environment includes a visible scene and an invisible scene. A picture-in-picture (PIP) is displayed in the visible scene as a directional guidance or distance hint related to the region of interest in the invisible scene, thereby saving time and enhancing efficiency of searching for the region of interest.

Abstract: Techniques are disclosed for image matting. In particular, embodiments decompose the matting problem of estimating foreground opacity into the targeted subproblems of estimating a background using a first trained neural network, estimating a foreground using a second neural network and the estimated background as one of the inputs into the second neural network, and estimating an alpha matte using a third neural network and the estimated background and foreground as two of the inputs into the third neural network. Such a decomposition is in contrast to traditional sampling-based matting approaches that estimated foreground and background color pairs together directly for each pixel. By decomposing the matting problem into subproblems that are easier for a neural network to learn compared to traditional data-driven techniques for image matting, embodiments disclosed herein can produce better opacity estimates than such data-driven techniques as well as sampling-based and affinity-based matting approaches.

Abstract: Systems and methods for permitting a buyer of a mobile home to apply for a mortgage by taking digital photographs of documents with his or her mobile device are disclosed. The borrower's mobile device may include subsystems for processing the image, optimizing it, and converting the image into a file type that may be acceptable by a lender. A loan facilitation platform performs additional processing to determine whether the document may be deemed acceptable by a lender. If so, the processed documents may be sent to a lender. The systems and method disclosed herein improve the mortgage application review and approval process and bring greater transparency to it.

Abstract: Techniques are disclosed for document boundary detection (BD) from an input image using a combination of deep learning model and image processing algorithms. Quadrilaterals approximating the document boundaries in the input image are determined and rated separately using both these approaches: deep leaning using convolutional neural network (CNN) and heuristics using image processing algorithms. Thereafter, the best rated quadrilateral is selected from the quadrilaterals obtained from both the approaches.

Abstract: A system can obtain a labelled data set, including historic video data and labelled events. The system can divide the labelled data set into historic training/testing data sets. The system can determine, using the historic training data set, a plurality of different parameter configurations to be used by a video encoder to encode a video that includes a plurality of video frames. Each parameter configuration can include a group of pictures (“GOP”) size and a scenecut threshold. The system can calculate an accuracy of event detection (“ACC”) and a filtering rate (“FR”) for each parameter configuration. The system can calculate, for each parameter configuration of the plurality of different parameter configurations, a harmonic mean between the ACC and the FR. The system can then select a best parameter configuration of the plurality of different parameter configurations based upon the parameter configuration that has the highest harmonic mean.