Abstract: The present application discloses an image processing method and apparatus, and an electronic device, and pertains to the field of image processing. The method includes: obtaining an inter-frame residual between two adjacent image frames to obtain a residual block; determining, based on the residual block, a target pixel region on which super-resolution processing needs to be performed; and performing super-resolution processing on the target pixel region to obtain a target pixel region. For another pixel region, the super-resolution processing result of an image frame that is in the two image frames and on which super-resolution processing is performed is used. This application reduces high computation costs of super-resolution processing.

Abstract: Systems and methods for generating a panoptic segmentation mask for an input image. The methods include receiving the input image comprising a plurality of pixels, generating a semantic mask and an instance mask from the input image, and combining the semantic mask and the instance mask to generate a panoptic mask for the input image. The semantic mask includes a single-channel mask that associates each pixel in the input image with a corresponding one of a plurality of labels. The instance mask includes a plurality of masks, where each of the plurality of masks identifies an instance of a countable object in the input image, and is associated with an indication of whether that instance of the countable object is hidden behind another object in the input image.

Abstract: In some embodiments, an electronic device presents an option that is selectable to share content with a second electronic device towards which the first electronic device is oriented. In some embodiments, an electronic device presents an indication to change the orientation of the electronic device when the orientation of the electronic device is outside of a range of orientations in which circuitry that identifies another electronic device with which to share content is able to function with desired reliability. In some embodiments, an electronic device presents a sharing user interface within an action user interface of an application. In some embodiments, an electronic device presents one or more options for changing one or more settings associated with an item of content before sharing the content.

Abstract: An apparatus includes: a memory storing one or more instructions; and a processor configured to execute the one or more instructions to: obtain a first image captured by a camera; detect one or more head patterns in the first image; identify a first head pattern, among the one or more head patterns, as a head pattern of a subject closest to the camera based on a size of the first head pattern; obtain a second image based on the identified first head pattern; and display the second image.

Abstract: A computer-implemented method and system for generating a blurred image from an original image. The method and system generate the blurred image using a process that enables fast efficient decoding of the compact encoded blurred image by a client device. The method may include transforming an original image to a block of coefficients in a frequency domain, low-pass filtering the block of coefficients in the frequency domain to produce a block of filtered coefficients, inverse transforming the block of filtered coefficients to produce a blurred image in a pixel domain, encoding the blurred image using a lossy-compression image encoder to produce an encoded blurred image, and transmitting the encoded blurred image to a client device for reconstruction and display by the client device.

Abstract: A degree of freedom in image production regarding tracking of a subject is improved. Designation of a placement position in a display area of a tracking target is received on a first screen in which a predetermined image is displayed in the display area. For example, a user is allowed to designate a position (a position within the display area) in which a tracking target subject is disposed in a state in which image content can be recognized on a display screen.

Abstract: An apparatus including a sensor for setting an exposure time or gain for each of pixel groups including at least one pixel includes an imaging unit including the sensor configured to capture a subject through an optical system to generate an image, an acquisition unit configured to acquire information about a specific image region in the generated image, a determination unit configured to determine a specific pixel region including at least one pixel group in the sensor and corresponding to the specific image region, based on the information about the specific image region, a change unit configured to change at least one of a number, a size, and a shape of pixel groups in the specific pixel region determined by the determination unit, and a control unit configured to control the exposure time or gain for each of the pixel groups.

Abstract: A processing server assists in identifying user consumption of information. The processing server includes a hardware processor, and memory storing computer instructions that when executed perform receiving image data comprising a series of screen image snapshots being presented on a screen of a client device, the screen image snapshots comprising respective timestamps; receiving audio data captured by a microphone of the client device; receiving metadata comprising image metadata, audio metadata, and client device metadata; determining one or more first matches to the image data; determining one or more second matches to the audio data; and aggregating the one or more first matches and the one or more second matches based on the metadata.

Abstract: Methods and a system for pixel-by-pixel correction of diffuse reflected and specular reflected light on a display device of an information handling system. Voltage values of pixels of the display device are measured by sensors. Measured voltage values of a pixel are converted to a digital value. A digital correction value calculated based on whether diffuse reflected light or diffuse reflected light and specular reflected light is found on the pixel. A sigmoid transfer function and discrete sharpening filter is performed on the pixel, if the digital correction value is less than zero.

Abstract: Various aspects of the subject technology relate to systems, methods, and machine-readable media for automating the recording of an evidentiary history (e.g., versions audit trail) of a graphical user interface with an embedded clickwrap agreement. The snapshot server captures and outputs snapshot records of a graphical user interface displaying the clickwrap agreement on an end user computing platform. The snapshot records are created using a virtual machine that emulates an end user computing platform for navigation of an application rendered on the platform. Aspects may also include generating a snapshot record of metadata associated with the captured snapshot image.

Abstract: An image decoding apparatus decodes a transform coefficient on a transform unit basis, decodes a flag scaling_matrix_for_lfnst_disabled_flag indicating whether to apply a quantization matrix during a non-separable transform, scales the transform coefficient by utilizing a scaling list, and performs a non-separable transform in accordance with a non-separable transform index lfnst_idx. In a case that scaling_matrix_for_lfnst_disabled_flag==1 and lfnst_idx!=0 and a size of a transform block is equal to or greater than a prescribed size, instead of scaling using the quantization matrix according to a position of the transform coefficient, uniform quantization not depending on the position of the transform coefficient is performed.

Abstract: A method for operating or interacting with a mobile robot includes determining, using at least one processor, a mapping between a first coordinate system associated with a mobile device and a second coordinate system associated with the mobile robot, in which the first coordinate system is different from the second coordinate system. The method includes providing at the mobile device a user interface to enable a user to interact with the mobile robot in which the interaction involves usage of the mapping between the first coordinate system and the second coordinate system.

Abstract: Certain aspects of the present disclosure provide a method for lane marker detection, including: receiving an input image; providing the input image to a lane marker detection model; processing the input image with a shared lane marker portion of the lane marker detection model; processing output of the shared lane marker portion of the lane marker detection model with a plurality of lane marker-specific representation layers of the lane marker detection model to generate a plurality of lane marker representations; and outputting a plurality of lane markers based on the plurality of lane marker representations.

Abstract: A method for driving display panel includes: for one of adjacent two frames of displayed images, when scanning odd-numbered row of sub-pixels, inputting data signals to the data lines coupled to the data selector in first order by a data selector; when scanning even-numbered row of sub-pixels, inputting data signals to the data lines coupled to the data selector in second order by the data selector; first and second orders each represents an order of inputting data signals to the data lines; first order is opposite to second order; for the other of the adjacent two frames of displayed images, when scanning odd-numbered row of sub-pixels, inputting data signals to the data lines coupled to the data selector in second order by the data selector; when scanning even-numbered row of sub-pixels, inputting data signals to the data lines coupled to the data selector in first order by the data selector.

Abstract: Methods and systems for facilitating generation of electronic advertising messages based on model web pages. A visual content request is received that identifies a model web page. Source code is retrieved that includes patterns that can be matched to identify visual features of the model web page. Visual content information is provided to an advertising message generation service to construct advertising messages that include at least a portion of the identified visual features. Constructed advertising messages are received, including at least one modified advertising message that incorporates a user-selected image extracted from the model web page. The identified visual features of the model web page can include text format, text color, background color, images, and video sequences.

Abstract: The present technology relates to a solid-state imaging device, a signal processing chip, and an electronic apparatus that make it possible to utilize the result of detecting an occurrence of an event in imaging. The solid-state imaging device includes: an event detection unit that detects, as an event, a change in an electrical signal generated by each pixel of a pixel array unit; a region-of-interest detection unit that detects, from a result of detecting the event, a region-of-interest of the pixel array unit; and a pixel signal generation unit that generates a pixel signal constituting an image of a region corresponding to the region-of-interest. The present technology is applicable to, for example, a sensor that detects an event that is a change in an electrical signal of a pixel.

Abstract: A computer-implemented method for reconstruction of medical image data includes receiving medical measuring data, and minimizing a cost value via gradient descent. Minimizing the cost value includes: reconstructing the medical image data by applying a reconstruction function to the received medical measuring data in accordance with reconstruction parameters; determining a cost value by applying a cost function to the reconstructed medical image data; determining a gradient of the cost function with respect to the reconstruction parameters; adjusting the reconstruction parameters based on the gradient of the cost function with respect to the reconstruction parameters and the previous reconstruction parameters; and providing the adjusted reconstruction parameters. The acts of the minimizing are repeated until a termination condition is met. The reconstructed medical image data is provided.

Abstract: A method for designing a material for an aircraft component includes training a neural network to correlate microstructural features of an alloy with material properties of the alloy by at least providing a set of images of the alloy to the neural network. Each of the images in the set of images has varied constituent compositions. The method further includes providing the neural network with a set of determined material properties corresponding to each image, associating the microstructural features of each image with the set of empirically determined data corresponding to the image, and determining non-linear relationships between the microstructural features and corresponding empirically determined material properties via a machine learning algorithm, receiving a set of desired material properties of the alloy for aircraft component, and determining a set of microstructural features capable of achieving the desired material properties of the alloy based on the determined non-linear relationships.

Abstract: A calibrating device of calibrating a real-time image through a dithering process including a receiving unit, a storing unit, a displacing module, a computing module, and an outputting unit is disclosed. The receiving unit receives a real-time image from an image sensor and records a time parameter of the image. The storing unit stores a hash table that records multiple hash values used to calibrate the image. The displacing module shifts the multiple hash values in the hash table to generate an adjusted hash table. The computing module obtains a corresponding hash value from the adjusted hash table for each pixel point of the image in accordance with the coordinates of each pixel point, and respectively adds the corresponding hash value to the pixel value of each pixel point of the image to generate a calibrated image. The outputting unit outputs the calibrated image.

Abstract: There is disclosed in one example a video processor, including: an input buffer to receive an input image; a slicer circuit to divide the input image into a plurality of N vertical slices; N parallel input buffers for de-rasterization; N parallel image scalers, wherein each scaler is hardware configured to scale in a raster form, one of the N vertical slices according to an image scaling algorithm; N parallel output buffers for rerasteriztion; and an output multiplexer to combine the scaled vertical slices into a combined scaled output image.

Abstract: A method for removing compressed Poisson noises in an image, based on deep neural networks, may comprise generating a plurality of block-aggregation images by performing block transform on low-frequency components of an input image; obtaining a plurality of restored block-aggregation images by inputting the plurality of block-aggregation images into a first deep neural network; generating a low-band output image from which noises for the low-frequency components are removed by performing inverse block transform on the plurality of restored block-aggregation images; and generating an output image from which compressed Poisson noises are removed by adding the low-band output image to a high-band output image from which noises for high-frequency components of the input image are removed.

Abstract: An image processing device of the present invention comprises: image processing groups each of which includes modules that perform predetermined image processing on pieces of divided image data obtained by dividing input image data and each of which outputs the pieces of image data processed in the respective modules via a predetermined one of the modules; an obtaining unit to which the image processing groups are connected in parallel and which obtains the pieces of image data processed and outputted from the image processing groups; a detection unit which detects an error module not performing normal processing among the modules; and a control unit which sets a usable group that is usable for the image processing among the image processing groups based on a result detected by the detection unit and which causes the usable group to execute the image processing on the pieces of divided image data.

Abstract: A system and method to reduce weight storage bits for a deep-learning network includes a quantizing module and a cluster-number reduction module. The quantizing module quantizes neural weights of each quantization layer of the deep-learning network. The cluster-number reduction module reduces the predetermined number of clusters for a layer having a clustering error that is a minimum of the clustering errors of the plurality of quantization layers. The quantizing module requantizes the layer based on the reduced predetermined number of clusters for the layer and the cluster-number reduction module further determines another layer having a clustering error that is a minimum of the clustering errors of the plurality of quantized layers and reduces the predetermined number of clusters for the another layer until a recognition performance of the deep-learning network has been reduced by a predetermined threshold.

Abstract: A display control apparatus includes an acquisition unit that acquires an image, a memory that stores multiple images acquired by the acquisition unit, a recognition unit that recognizes a size of a character included in an image to be displayed on a display from among the images stored on the memory, and a display controller that causes the display to display the images stored on the memory while switching from one image to another every set time period. The display controller determines a display setting of the image to be displayed on the display in response to the size of the character included in the image that the recognition unit has recognized and causes the display to display the image in the determined display setting.

Abstract: Evaluating the reliability of a computed tomography (CT) volume image includes acquiring a first CT volume image and a modified CT volume image that are reconstructed from scanned projection images. From the first CT volume image and the modified CT volume image, digitally reconstructed X-ray images are then calculated. A respective similarity with a corresponding one of the scanned projection images is then determined. Based on a comparison of these similarities with one another, the reliability of the CT volume images is then evaluated.

Abstract: A material data collection system allows capturing of material data. For example, the material data collection system may include digital image data for materials. The material data collection system may ensure that captured digital image data is properly aligned, so that material data may be easily recalled for later use, while maintaining the proper alignment for the captured digital image. The material data collection system may include using a capture guide, to provide cues on how to orient a mobile device used with the material data collection system.

Abstract: An apparatus for scaling images is provided that includes at least two input ports, a scaling component coupled to the at least two input ports, the scaling component including a plurality of scalers, the scaling component configurable to map any scaler to any input port of the at least two input ports and configurable to map more than one scaler to any input port, and a memory coupled to the at least two input ports and to outputs of the plurality of scalers, the memory configured to store image data for each input port and scaled image data output by the plurality of scalers.

Abstract: Various implementations disclosed herein include devices, systems, and methods for per-pixel filtering. In some implementations, a method includes obtaining an image data frame. In some implementations, the image data frame includes a plurality of pixels. In some implementations, the method includes generating a respective pixel characterization vector for each of the plurality of pixels. In some implementations, each pixel characterization vector includes an object label indicating an object type that the corresponding pixel of the plurality of pixels represents. In some implementations, the method includes modifying corresponding pixel data of the plurality of pixels having a first object label. In some implementations, the method includes synthesizing a first modified image data frame that includes modified pixel data for the plurality of pixels having the first object label and unmodified pixel data for the plurality of pixels not having the first object label.

Abstract: According to one implementation, a pixel error detection system includes a hardware processor and a system memory storing a software code. The hardware processor is configured to execute the software code to receive an input image, to mask, using an inpainting neural network (NN), one or more patch(es) of the input image, and to inpaint, using the inpainting NN, the masked patch(es) based an input image pixels neighboring each of the masked patch(es). The hardware processor is configured to further execute the software code to generate, using the inpainting NN, a residual image based on differences between the inpainted masked patch(es) and the patch(es) in the input image and to identify one or more anomalous pixel(s) in the input image using the residual image.

Abstract: A control apparatus and method that captures video image includes acquiring a parameter for recognition processing with respect to acquired image data and changing the acquired parameter according to a change in zoom magnification of an image capturing unit.

Abstract: A system and method for calibrating and re-calibrating an imaging device. The image device includes at least one varying intrinsic or extrinsic parameter value based on a view of 3D shapes and a 2D template therefor. The method and system are operable to receive a sequence of images from the imaging device, wherein a planar surface with known geometry is observable from the sequence of images; perform an initial estimation of a set of camera parameters for a given image frame; perform a parameter adjustment operation to minimize a dissimilarity between the template and the sequence of images; perform a parameter adjustment operation to maximize similarities in either the camera's coordinate system or the template's coordinate system; and update an adaptive world template to incorporate an additional stable point from the observed images to the template.

Abstract: An apparatus includes an acquisition unit configured to acquire an input image and a reference image, a region enlargement unit configured to perform, on each of the input image and the reference image, a region enlargement process for widening a region including pixels that satisfy a predetermined condition, and a detection unit configured to detect a corresponding point in the reference image subjected to the region enlargement process, the corresponding point corresponding to a pixel of interest in the input image subjected to the region enlargement process.

Abstract: An image projection apparatus configured to project a first range with a predetermined image quality includes a shifting unit configured to shift a position where a projection image is projected, a determining unit configured to determine whether a target position shifted by the shifting unit is located in a second range different from the first range, and a notifying unit configured to notify a user of a predetermined notice when the target position is located in the second range.

Abstract: An image decoding apparatus decodes a transform coefficient on a transform unit basis, decodes a flag scaling_matrix_for_lfnst_disabled_flag indicating whether to apply a quantization matrix during a non-separable transform, scales the transform coefficient by utilizing a scaling list, and performs a non-separable transform in accordance with a non-separable transform index lfnst_idx. In a case that scaling_matrix_for_lfnst_disabled_flag==1 and lfnst_idx !=0 and a size of a transform block is equal to or greater than a prescribed size, instead of scaling using the quantization matrix according to a position of the transform coefficient, uniform quantization not depending on the position of the transform coefficient is performed.

Abstract: An image capturing device includes an image sensor and processing circuitry. The processing circuitry calculates a pixel value fluctuation amount as a fluctuation amount of each of the pixel values; calculates a line fluctuation amount as an average value of N pixel value fluctuation amounts of N pixels; calculates a variance value of the N pixel value fluctuation amounts from the N pixel value fluctuation amounts and the line fluctuation amount; calculates a movement adaptive weight based on the variance value; calculates a line fluctuation noise correction amount, corresponding to each of the pixel values outputted from the image sensor, from the line fluctuation amount and the movement adaptive weight; and corrects each of the pixel values outputted from the image sensor by using the line fluctuation noise correction amount and thereby generates an image signal after the correction.

Abstract: In one embodiment, a method includes accessing a first image and a second image, where at least part of the first image overlaps with at least part of the second image. The first and second images are divided into portions associated with a first set of grid points, where each grid point in the first set corresponds to a portion of the first image or the second image. Differences in the region of overlap between the first and second images are determined. One or more grid points in the first set and the corresponding portions of the first image or the second image are moved relative to one or more other grid points in the first set based on the determined differences.

Abstract: An image display system includes an acquisition means for acquiring operation information containing a moving direction and a moving amount of an input position in an input operation on a first display object, the input operation being performed when the first display object is displayed on a display device, an extraction means for, when the moving amount of the input position in a predetermined first direction exceeds a predetermined threshold, acquiring a first attribute parameter of the first display object which corresponds to the first direction, and extracting a second display object associated with the first display object and having a first attribute parameter different from the first display object from a storage means where a plurality of display objects are associated with attribute parameters, and a display control means for displaying the second display object extracted by the extraction means, instead of the first display object, on the display device.

Abstract: A method of processing an input image comprises receiving the input image, storing the image in a memory, and accessing, by an image processor, a computer readable medium storing a trained deep learning network. A first part of the deep learning network has convolutional layers providing low-level features extracted from the input image, and convolutional layers providing a residual image. A second part of the deep learning network has convolutional layers for receiving the low-level features and extracting high-level features based on the low-level features. The method feeds the input image to the trained deep learning network, and applies a transformation to the residual image based on the extracted high-level features.

Abstract: A control apparatus includes at least one processor operatively coupled to a memory, serving as a sensing unit configured to sense a tracking target that appears in a sensed video, a recording unit configured to record a size of the tracking target, and a search unit configured to obtain a predicted size of the tracking target in the sensed video, based on the size recorded by the recording unit, for a case of zooming out at a predetermined scaling factor, and, if the predicted size is larger than a predetermined size, to zoom out by the predetermined scaling factor, and then to search for the tracking target in the sensed video after the zoom out.

Abstract: Provided is a system includes: an image forming portion 161, which forms an image related to the imaging of the eye to be inspected E, based on return light of measuring light from the eye to be inspected E; a display control portion 162 which performs control to display the image formed by the image forming portion 161 on a display portion 180; and an area setting portion 163, which sets one of imaging areas, a first imaging area, which is a specified rectangular area, and a second imaging area, which is narrower than the specified rectangular area and includes a curved part based on a maximum imageable area determined based on the focus adjustment performed by the focus adjusting unit 134, as an imaging area of the eye to be inspected E, according to the maximum imageable area.

Abstract: Disclosed herein are system, method, and computer program product embodiments for providing object detection and filtering operations. An embodiment operates by receiving an image comprising a plurality of pixels and pixel information for each pixel. The pixel information indicates a bounding box corresponding to an object within the image associated with a respective pixel and a confidence score associated with the bounding box for the respective pixel. Pixels that do not correspond to a center of at least one of the bounding boxes are iteratively removed from the plurality of pixels until a subset of pixels each of which correspond to a center of at least one of the bounding boxes remains. Based on the subset, a final bounding box associated with each object of the image is determined based on an overlapping of the bounding boxes of the subset of pixels and the corresponding confidence scores.

Abstract: A method for dynamic scaling is disclosed. The method includes identifying first scene information to be rendered for display on an electronic device, the electronic device including a screen with a physical resolution, the first scene information associated with an application. The method also includes generating a scaling factor, the scaling factor controlling a resolution of the first scene information as rendered on the screen independently of the physical resolution of the screen. Additionally, the method includes rendering the first scene information as one or more pixels of a virtual display with a virtual resolution based on the scaling factor.

Abstract: Systems, methods, and non-transitory computer-readable media can receive a source content item. A crop window is automatically determined for the source content item based on framing criteria. A cropped media asset is automatically generated based on the source content item and the crop window. In certain embodiments, an object of interest is automatically identified in the source content item and the crop window is determined based on the object of interest.

Abstract: Provided is an artificial intelligence (AI) encoding apparatus including a memory storing one or more instructions, and a processor configured to execute the one or more instructions stored in the memory to obtain a first image by performing AI down-scaling on an original image through a deep neural network (DNN) for down-scaling, obtain artifact information indicating an artifact region in the first image, perform post-processing to change a pixel value of a pixel in the first image, based on the artifact information, and obtain image data corresponding to a result of encoding of the post-processed first image, and AI data including the artifact information.

Abstract: An information processing apparatus includes an acquisition section that acquires an image of a real object in a real space captured by a predetermined imaging section, and a measurement result of a distance to the real object by a predetermined distance measuring section, and an estimation section that estimates a size of the real object in the real space on the basis of a size of the real object in the image and the measurement result of the distance, and by comparing the estimation result of the size to a plurality of preset size candidates, specifies the size of the real object in the real space.

Abstract: A method and device for double-camera-based imaging are provided. The method includes the following actions. A first image is acquired by a main camera and a second image is acquired by an auxiliary camera. A main image resolution and an auxiliary image resolution are determined according to a determined shooting mode and resolutions of the main camera and the auxiliary camera respectively. The first image is converted into a main image with the main image resolution. The second image is converted into an auxiliary image with the auxiliary image resolution according to the second image. A required target image is obtained according to the main image and the auxiliary image.

Abstract: The present technology relates to an imaging device, an imaging method, and a program capable of setting a resolution based on a distance to a subject. A control unit which changes a resolution of a captured image on the basis of distance information, corresponding to the captured image, regarding a detected distance to a subject included in the image is included. The control unit changes a resolution of a portion of a region of the captured image on the basis of the distance information. The portion of the region is a region distant from another region. The control unit changes the resolution of the portion of the region such that the portion of the region becomes higher than a resolution of another region.

Abstract: In an example, an image classification system is disclosed. The image classification system modifies an image having a first height and a first width to be input to a convolutional neural network for image classification. The image classification system includes an image resizing module that is configured to resize the image so that the resized image comprises a second height and a second width. An aspect ratio of the resized image corresponds to an aspect ratio of the image having the first height and the first width. The image classification system also includes an alignment module that is configured to modify pixels of a feature map corresponding to the resized image based upon a comparison of a desired feature map size and an actual feature map size.

Abstract: A bird's-eye view video generation device includes a video data acquisition unit configured to acquire video data from multiple cameras configured to capture videos of surroundings of a vehicle, a bird's-eye view video generator configured to generate a bird's-eye view video from a virtual viewpoint above the vehicle by performing viewpoint conversion processing on the acquired video data to synthesize the viewpoint-converted videos, an obstacle information acquisition unit configured to acquire information from at least one detector configured to detect at least one obstacle around the vehicle and to specify a position thereof, and a display controller configured to display the bird's-eye view video in a display, wherein, when the position of the obstacle overlaps a synthesis boundary between the videos, the bird's-eye view video generator is further configured to generate a bird's-eye view video obtained by changing the position of the virtual viewpoint of the bird's-eye view video.

Abstract: An aspect of the disclosure provides a processing method for display data applied in a computing device, which processing method includes: determining a region of interest in the display area of the computing device; compressing data of an image in the display area; and transmitting data of an image of the region of interest and the compressed image data in the display area. The disclosure further provides a corresponding processing device and display device.