Abstract: An image correction method is provided. The image correction method includes receiving an input image from a first camera; receiving a guide image from a second camera; generating a corrected image by performing image correction on the input image using the guide image, the image correction being performed by an image generation unit having a pre-learned image generation parameter learned using a training image; generating a quality value of the corrected image by an image evaluation unit having an pre-learned image evaluation parameter learned using the training image; and performing the image correction on the corrected image again when the quality value of the corrected image is less than a set value, and outputting the corrected image as a final image when the quality value of the corrected image is greater than the set value.

Abstract: A computer-implemented method for image processing is provided. The method includes acquiring multiple multi-energy spectral scan datasets and computing basis material images representative of multiple basis materials from the multi-energy spectral scan datasets, wherein the multiple basis material images include correlated noise. The method also includes jointly denoising the multiple basis material images in at least a spectral domain utilizing a deep learning-based denoising network to generate multiple de-noised basis material images.

Abstract: An image anti-aliasing method comprises following steps: receiving an aliasing image; wherein the aliasing image includes a plurality of source pixels; generating a plurality of hash values corresponding to the plurality of source pixels respectively; and performing a filtering processing or a filter generating procedure on the aliasing image according to the plurality of hash values. Each of the plurality of hash values is generated by the following steps: selecting one source pixel from the aliasing image and selecting a window containing the selected source pixel; determining an aliasing strength according to the grayscale values of all the source pixels of a row and a column at which the selected source pixel is located in the window; and determining a hash value of the selected source pixel according to the aliasing strength.

Abstract: An electronic device is provided. The electronic device includes an input interface and a processor that performs noise removal processing on an image input through the input interface, obtains first information on a first texture block among a plurality of first pixel blocks included in the input image, obtains second information on a second texture block among a plurality of second pixel blocks included in the noise-removed image, obtains third information on maximum energy amount among energy amount of each of the plurality of second pixel blocks, and identifies whether the input image is an upscaled image based on the first, second and third information.

Abstract: A pixel filter has a filter module that performs a first recursive filter operation in a first direction through a sequence of pixels to form a first filtered pixel value for each pixel, and performs a second recursive filter operation in a second direction through the sequence of pixels to form a second filtered pixel value for each pixel, the first and second recursive filter operations forming a respective filtered pixel value for a given pixel in dependence on the pixel value at that pixel and the filtered pixel value preceding that pixel in their respective direction of operation. The filtered pixel value of the preceding pixel is scaled by a measure of similarity between data associated with that pixel and its preceding pixel. Filter logic combines the first and second filtered pixel values formed by the first and second recursive filter operations to generate a filter output for the pixel, for each pixel of the sequence.

Abstract: An image processing device includes a processor; and a memory to store the program which performs processing including: measuring a first texture amount indicating luminance variation in image regions, based on the image regions obtained by dividing the captured image and previously determining an image processing target region based on the first texture amount; judging whether the image processing on a current captured image is necessary based on luminance of the image processing target region in the current captured image; calculating a second texture amount indicating luminance variation in the image processing target region, and judging whether the image processing should be performed on the image processing target region or not based on the second texture amount; and performing the image processing on the image processing target region on which the judging based on the second texture amount is that the image processing should be performed.

Abstract: Systems and methods for removing objects from images are disclosed. An image processing application identifies a boundary of each object of a set of objects in an image. The image processing application identifies a completed boundary for each object of the set of objects by providing the object to a trained model. The image processing application determines a set of masks. Each mask corresponds to an object of the set of objects and represents a region of the image defined by an intersection of the boundary of the object and the boundary of a target object to be removed from the image. The image processing application updates each mask by separately performing content filling on the corresponding region. The image processing application creates an output image by merging each of the updated masks with portions of the image.

Abstract: An image processing apparatus that operates in a plurality of modes including a first mode for performing high image quality processing of image data and a second mode for performing high-speed processing of image data, performs the following processing. More specifically, the apparatus performs, in accordance with the mode to be operated, the settings of each of an operation to output image data from a first DMAC (Direct Memory Access Controller) to a common bus, an operation to input the image data from the common bus to an image processing unit, an operation of the image processing unit, an operation to output the image data from the image processing unit to the common bus, and an operation to output the image data from the common bus to a second DMAC.

Abstract: Disclosed are a method and device for processing an image, and a storage medium. The method includes: determining first position information of key points of first type of an object in the image based on the image and a trained model, where the first position information of each key point of first type indicates where each key point of first type is in the image; determining second position information of key points of second type of the object based on the first position information and a preset algorithm, where the second position information of each second type indicates where each key point of second type is in the image; liquefying the object based on the first position information and the second position information by using a liquefying level corresponding to a portion to be processed of the object.

Abstract: One embodiment of the invention provides an image correction method comprising: providing a first image; providing a first image; providing viewpoint information about a viewpoint which observes the first image; dividing the first image into two or more segmented images along a horizontal direction of the first image; and providing a second image converted from the first image by converting each of the two or more segmented images based on the viewpoint information and vertical lengths of each of the segmented images.

Abstract: Various embodiments of systems and methods for adaptive video subsampling for energy-efficient object detection are disclosed herein.

Abstract: Systems, methods, and computer-readable media for feedback on and improving the accuracy of super-resolution imaging. In some embodiments, a low resolution image of a specimen can be obtained using a low resolution objective of a microscopy inspection system. A super-resolution image of at least a portion of the specimen can be generated from the low resolution image of the specimen using a super-resolution image simulation. Subsequently, an accuracy assessment of the super-resolution image can be identified based on one or more degrees of equivalence between the super-resolution image and one or more actually scanned high resolution images of at least a portion of one or more related specimens identified using a simulated image classifier. Based on the accuracy assessment of the super-resolution image, it can be determined whether to further process the super-resolution image. The super-resolution image can be further processed if it is determined to further process the super-resolution image.

Abstract: Embodiments of the present disclosure relate to object defect detection. In an embodiment, a computer-implemented method is disclosed. According to the method, for a test image of at least one part of a target object, a reference image is generated by repeating a periodic pattern detected in the test image, the target object consisting of elements. A differential image is determined by comparing the test image and the reference image. The differential image is superimposed on a predefined grid image to obtain a superimposed image. The grid image comprises grids corresponding to elements of a reference object associated with the target object. The number of defective elements is determined in the at least one part of the target object based on the superimposed image. In other embodiments, a system and a computer program product are disclosed.

Abstract: The invention provides an automatic inspection process for detecting visible defects on a manufactured item. The process includes a set up mode in which images of same-type defect free items, but not images of same-type defected items, are obtained, and an inspection mode in which images of both same-type defect free items and same-type defected items, are obtained and defects are detected. Images of the same-type defect free items are analyzed and based on the analysis the process switches to the inspection mode.

Abstract: Included are: an image acquiring unit acquiring a determination target image in which a target object to be inspected is captured; a learning result acquiring unit acquiring a result of machine learning of forward domain conversion of an image or inverse domain conversion of an image performed using a normal image in which the target object in a normal state is captured as training data; a determination target image analysis unit obtaining a domain-converted image by sequentially performing forward domain conversion and inverse domain conversion on the determination target image using the result of the machine learning; and a determination unit determining whether or not an abnormality is occurring in the target object captured in the determination target image by comparing the determination target image and the domain-converted image.

Abstract: Discussed herein are architectures and techniques for improving execution or training of machine learning techniques. A method can include receiving a request for image data, the request indicating an analysis task to be performed using the requested image data, determining a minimum image quality score for performing the analysis task, issuing a request for image data associated with an image quality at last equal to, or greater than, the determined minimum image quality score, receiving, in response to the request, image data with an image quality score greater than, or equal to, the determined minimum image quality score, and providing the received image data to (a) a machine learning (ML) model executor to perform the image analysis task or (b) an ML model trainer that trains the ML model to perform the image analysis task.

Abstract: A system and method for assessing quality of a received media file may include extracting from the media file a feature; identifying at least one parameter of the feature; calculating a score for the parameter; assigning a weight to the feature; calculating a weighted score for the media file; and determining a quality of the media file based on the calculated weighted score.

Abstract: A system and method for preventing sight deterioration caused by prolonged use of electronic visual displays in low-light conditions is provided. The system includes a camera directed towards a user, a processing circuitry, control circuitry and, optionally, a light sensor. The processing circuitry determines the illuminance of a user's face, and in case it falls outside of a predefined range (putting the user at risk of future sight deterioration and progression of myopia), the device stores the illuminance data and/or sends a control signal to circuitry operative to notify the user. If processing circuitry determines that the illuminance is equal or greater than the predefined illuminance, the circuitry operative can stop the notification. The notification can be modulated by any combination of the illuminance and the time of use.

Abstract: A parameter calculation unit calculates, for camera layout information of the camera placed in the monitored area and environmental object information representing an environmental object including a structural object present in the monitored area and a placed object placed in the structural object, an image processing performance parameter indicating at least one of a hiding level of an object, an orientation of the object, and a movement of the object based on characteristic information representing characteristics of an appearance and a movement of the object determined depending on an environmental object. A suitability calculation unit calculates camera layout suitability based on image processing characteristic information representing a characteristic of the image processing and the image processing performance parameter, the camera layout suitability being an index of a level of suitability of a camera layout represented by the camera layout information for image processing of the object.

Abstract: A method of counting sheet materials applied to a pile of sheet materials, comprising the steps of: receiving an image of the pile of sheet materials; obtaining a grayscale value of a plurality of pixels along a first image axis direction of the image to form an one dimensional first array; performing binarization of the first elements of the first array with a first threshold value to form an one dimensional second array; obtaining the number of the second elements of a first value appearing between two second elements of a second value in the second array to form a third array; dividing the elements of the third array into a first cluster and a second cluster with a second threshold value; counting the number of the third elements belonging to the first cluster and defining said number as the number of the first sheet materials.

Abstract: A micro camera is placed in an appropriate image capturing position therefor on the basis of a center-to-center distance depending on a rotational angle of a holding table. Even in the case where the center C0 of a holding surface and the center C1 of a wafer are displaced out of alignment with each other, allowing a position in X-axis directions of an outer circumference of the wafer to vary as the holding table rotates, a control unit can make an image capturing range of the micro camera follow the varying position of the outer circumference of the wafer. Therefore, the image capturing range of the micro camera can be determined with ease. Both a surface of the wafer and the outer circumference of the wafer can be inspected simply when two cameras are moved along the X-axis directions by a single X-axis moving mechanism.

Abstract: Provided is an analysis method for a crack rate of an electrode active material of an electrode, comprising the steps of: forming an electrode including an electrode active material, a binder, and a conductive material; impregnating the electrode with a resin and visualizing material regions including the electrode active material, the binder, and the conductive material which are included in the electrode, and a pore region; cutting the electrode and forming an electrode cross-section sample; photographing a cross section of the electrode cross-section sample using a scanning electron microscope and obtaining a cross-sectional image; performing primary image processing on the cross-sectional image and extracting total surface area pixels of the electrode active material; performing secondary image processing on the cross-sectional image and extracting total boundary pixels of the electrode active material; and calculating a crack rate of the electrode active material of the electrode in the cross-sectional i

Abstract: A method, related system and related computer program product are provided for monitoring wear of teeth of a drum of a double roll crusher. A processor receives a digital video capturing rotation of the drum and the teeth. For each frame of the digital video, the processor segments the frame into groups of contiguous pixels, wherein each group is representative of one of the teeth. The processor determines parameter indicative of a geometry of at least one of the teeth based on segmented groups of contiguous pixels in at least one of the frames of the digital video. The processor generates a human-readable report based on the parameter indicative of the geometry of the at least one of the teeth.

Abstract: A method for detecting a tumor from images which are required to be shrunken in resolution obtains one or more first images. Then, the method segments or divides the detection images into a number of detection image blocks according to an input size of training data of a convolutional neural network architecture, before segmenting, each of the plurality of detection image blocks comprising coordinate values. The detection image blocks are input into a preset tumor detection model to generate image blocks of a result of the detection images. The method merges the image blocks into a single image according to the coordinate values of each detection image block. Colors of normal areas, abnormal areas, and overlapping areas of the abnormal areas are all different. The method generates a final detection according to color depths in the image. A tumor detection device and a non-transitory storage medium are provided.

Abstract: Aspects of the technology described herein provide a system for improved synthesis of a target domain image from a source domain image. A generator that performs the synthesis is formed based on the texture propagation from the first domain to the second domain with a bidirectional generative adversarial network, which is trained for the texture propagation with a shape prior constraint.

Abstract: A fully image-based framework for CT image, or other medical image, quality evaluation and virtual clinical trial using deep-learning techniques is provided. This framework includes deep learning-based noise insertion, lesion insertion, and model observer, which enable efficient, objective, and quantitative image quality evaluation and virtual clinical trial directly performed on patient images.

Abstract: A method for calculating and reporting image quality properties of an image acquisition device after a subject or object has been scanned consists of a scan quality monitoring system with automated software for receiving scans and radiation dose data from scanners and automated algorithms for analyzing image quality metrics and radiation dose tradeoffs. Image quality assessment methods include algorithms for measuring fundamental imaging characteristics, level and type of image artifacts, and comparisons against large databases of historical data for the scanner and protocols. Image quality reports are further customized to report on expected clinical performance of image detection or measurement tasks.

Abstract: Disclosed is a computer-implemented method of determining a hypersurface image from a tomographic image data set describing a tomographic image of an anatomical body part. The method encompasses a locally depth-of-view-corrected reconstruction of a volumetric data set (pre-operative image data, like CT or MRI image data), in order to e.g. augment volumetric image data onto e.g. a microscope view, or in the head-up display of the microscope. For the depth correction, a surface model of the actual anatomical surface of the anatomical body part is used which encompasses a hypersurface reconstruction pf the volumetric data set. Thus, the correct information related to the tissue at the current visible surface is overlaid.

Abstract: An imaging system combines a probe for obtaining image data in respect of a structure of interest below a surface of a subject, a first camera for obtaining images of the surface of the subject and a second camera for capturing images of the environment. A surface model of the subjects surface is obtained, and the position and/or orientation of the probe is tracked on the surface. Image data acquired at different positions and orientations is stitched based on the tracked position of the probe.

Abstract: An image processing method includes image inputting, auxiliary information inputting, image processing, feature quantity extracting, and discriminating. The image inputting is inputting a cell image. The auxiliary information inputting is inputting auxiliary information on a color of the cell image. The image processing is generating multiple processed images by performing a different image-processing process on the cell image based on the auxiliary information. The feature quantity extracting is extracting a feature quantity of a discrimination target from each of the multiple processed images. The discriminating is discriminating the discrimination target in the cell image based on the feature quantity.

Abstract: A method for obtaining 3-dimensional images from x-ray information for deformed bones, said method comprising the steps of: acquiring an x-ray image of a bone; determining camera model to determine spatial values of source and a spatial value of bone; acquiring contour points and landmark points, in a 2-dimensional co-ordinate system; transforming said contour points and said landmark points from said 2-dimensional co-ordinate system into a 3-dimensional co-ordinate system of an imaging space; importing a pre-created 3-dimensional template along with anatomical values, anatomical regions, anatomical landmarks, and anatomical axes; aligning 3-dimensional template using identified anatomical landmarks and segmented anatomical regions with respect to camera model in order to obtain an aligned template; and deforming said aligned template to reconstruct deformity in said bone of interest, in such a way that its projection on an X-ray image plane in said imaging space matches exactly with said acquired contour poi

Abstract: Systems and methods process images to determine a skin condition severity analysis and to visualize a skin analysis such as using a deep neural network (e.g. a convolutional neural network) where a problem was formulated as a regression task with integer-only labels. Auxiliary classification tasks (for example, comprising gender and ethnicity predictions) are introduced to improve performance. Scoring and other image processing techniques may be used (e.g. in assoc. with the model) to visualize results such as highlighting the analyzed image. It is demonstrated that the visualization of results, which highlight skin condition affected areas, can also provide perspicuous explanations for the model. A plurality (k) of data augmentations may be made to a source image to yield k augmented images for processing. Activation masks (e.g. heatmaps) produced from processing the k augmented images are used to define a final map to visualize the skin analysis.

Abstract: Various methods for the detection and enhanced visualization of a particular structure or pathology of interest in a human eye are discussed in the present disclosure. An example method to visualize a given pathology (e.g., CNV) in an eye includes collecting optical coherence tomography (OCT) image data of the eye from an OCT system. The OCT image data is segmented to identify two or more retinal layer boundaries located in the eye. The two or more retinal layer boundaries are located at different depth locations in the eye. One of the identified layer boundaries is moved and reshaped to optimize visualization of the pathology located between the identified layer boundaries. The optimized visualization is displayed or stored or for a further analysis thereof.

Abstract: An object of the present invention is to provide an image processing device, an endoscope system, and an image processing method capable of efficiently saving a moving image in which a lesion is shown.

Abstract: Methods and systems for detecting a dissection of an elongated structure in a three dimensional medical image. One system includes an electronic processor that receives the three dimensional medical image. The electronic processor determines a first periphery and a second periphery of the elongated structure, the first periphery and the second periphery associated with an enhancing part and a non-enhancing part, respectively, of the elongated structure. The electronic processor determines whether the first periphery or the second periphery best illustrates an outermost periphery of the elongated structure and generate a base image based on whether the first periphery or the second periphery best illustrates an outermost periphery of the elongated structure.

Abstract: A diagnosis support device acquires medical image data representing a medical image obtained by imaging an animal as a subject with a medical image capturing device and type information representing a type which is classified by at least one of a body length or weight of the animal and to which the subject belongs, and determines presence or absence of an abnormality in the medical image of the subject based on the acquired medical image data and type information and a learned model learned in advance using a set of a plurality of pieces of the medical image data for learning and the type information.

Abstract: A diagnosis support device acquires medical image data representing a medical image obtained by imaging an animal as a subject with a medical image capturing device and head species information representing a head species of the subject and determines presence or absence of an abnormality in the medical image of the subject based on the acquired medical image data and head species information and a learned model learned in advance using a set of a plurality of pieces of the medical image data for learning and the head species information.

Abstract: In one embodiment, an automated high-speed X-ray inspection system may generate a first X-ray image of an inspected sample at a first direction substantially orthogonal to a plane of the inspected sample. The first X-ray image may be a high-resolution grayscale image. The system may identify one or more elements of interest of the inspected sample based on the first X-ray image. The first X-ray image may include interfering elements that interfere with the one or more elements of interest in the first X-ray image. The system may determine one or more first features associated with respective elements of interest based on variations of grayscale values in the first X-ray images. The system may determine whether one or more defects are associated with the respective elements of interest based on the one or more first features associated with the element of interest.

Abstract: The moving object tracking apparatus emphasizes an image with specific size in each of fluoroscopic images derived from two or more paired fluoroscopic radiographic devices, obtains a value indicating certainty degree of detecting a candidate position of the object to be tracked on the image subjected to the emphasizing process, extracts the candidate position based on the value indicating the certainty degree of detection, calculates a value indicating a correlation between the candidate position extracted from images picked up from two or more directions, and a position of the fluoroscopic radiation generator, detects the position of the object to be tracked based on the value indicating the certainty degree of detection, and the value indicating the correlation, and controls irradiation of radiation to an irradiation target based on the detected position of the object to be tracked.

Abstract: The album creation application of the present disclosure displays image data, to which trimming is performed, and a template, which includes a slot in which the image data is arranged, so that a slot and image data to be arranged in the slot are selected by use of an input device. Position information of a point of interest in the image to be arranged in the slot is obtained. Composition patterns applicable to the image with designation of the point of interest are presented to the user, and the composition pattern to be applied, which is selected by the user from among the presented composition patterns, is obtained. Trimming is performed based on the point of interest and the selected composition pattern selected. The trimmed images are listed, so that multiple trimmed images are presented to the user as trimming proposals.

Abstract: Described herein are systems and methods of converting media dimensions. A device may identify a set of frames from a video in a first orientation as belonging to a scene. The device may receive a selected coordinate on a frame of the set of frames for the scene. The device may identify a first region within the frame including a first feature corresponding to the selected coordinate and a second region within the frame including a second feature. The device may generate a first score for the first feature and a second score for the second feature. The first score may be greater than the second score based on the first feature corresponding to the selected coordinate. The device may crop the frame to include the first region and the second region within a predetermined display area comprising a subset of regions of the frame in a second orientation.

Abstract: An image generating apparatus includes: a display outputting an image; a memory storing one or more instructions; and a processor. The processor is configured to execute the one or more instructions to detect an object in an image including a plurality of frames, provide a plurality of candidate boundaries for masking the detected object, identify an optimal boundary by assessing the provided plurality of candidate boundaries, and generate a partial moving image with the object moving by using the optimal boundary.

Abstract: A segmentation model is trained with an image reconstruction model that shares an encoding. During application of the segmentation model, the segmentation model may use the encoding and network layers trained for the segmentation without the image reconstruction model. The image reconstruction model may include a probabilistic representation of the image that represents the image based on a probability distribution. When training the model, the encoding layers of the model use a loss function including an error term from the segmentation model and from the autoencoder model. The image reconstruction model thus regularizes the encoding layers and improves modeling results and prevents overfitting, particularly for small training sizes.

Abstract: Methods, systems, apparatus, and computer programs, for processing images through multiple neural networks that are trained to detect a pancreatic ductal adenocarcinoma. In one aspect, a method includes actions of obtaining a first image that depicts a first volume of voxels, performing coarse segmentation of the first image using a first neural network trained (i) to process images having the first volume of voxels and (ii) to produce first output data, determining a region of interest of the first image based on the coarse segmentation, performing multi-stage fine segmentation on a plurality of other images that are each based on the region of interest of the first image to generate output data for each stage of the multi-stage fine segmentation, and determining based on the first output data and the output data of each stage of the multi-stage fine segmentation, whether the first image depicts a tumor.

Abstract: Methods and systems for crowd level estimation are provided. The system includes a plurality of performance modeling modules (206), an input module (202) and a crowd estimation technique integration module. The plurality of performance modeling modules (206) performance model each of a plurality of crowd estimation techniques based on an accuracy thereof at different crowd levels and/or at different locations. The input module (202) receives an image of a crowd. The crowd estimation technique integration module (208) selects one or more of the plurality of crowd estimation techniques in response to the performance modeling of the one or more of the plurality of crowd estimation techniques and an estimated crowd level and/or an estimated location. The crowd estimation technique integration module (208) then estimates a crowd count of the crowd in the received image in accordance with the selected one or more of the plurality of crowd estimation techniques.

Abstract: Systems, methods, and computer software are disclosed for acquiring images during delivery of a radiation beam, the images capturing at least a portion of a shape representative of a radiation field generated by a radiation delivery system that includes a radiation source configured to deliver the radiation beam.

Abstract: Methods of detecting and/or identifying an artificial target within an image are provided. These methods comprise: applying to a region of the image a primary classification algorithm for performing a feature extraction of the image region, the primary classification algorithm being based on a spectral profile defined by one or more spectral signatures with one or more features in at least part of the infrared spectrum; obtaining a relation between the extracted features of the image region and the spectral profile; verifying whether a level of confidence of the obtained relation between the extracted features and the spectral profile is higher than a first predetermined confirmation level; and, in case of positive (or true) result of said verification, determining that the image region corresponds to artificial target to be detected, thereby obtaining a confirmed artificial target. Systems and computer programs are also provided that are suitable for performing said methods.

Abstract: An image processing method that includes obtaining an original image including a cultured cell image with a background image, dividing the original image into blocks, each composed of a predetermined number of pixels, and obtaining a spatial frequency component of an image in each block for each block, and classifying each block as the one belonging to a cell cluster corresponding to the cell or the one belonging to other than the cell cluster in a two-dimensional feature amount space composed of a first feature amount which is a total of intensities of low frequency components having a frequency equal to or lower than a predetermined frequency and a second feature amount which is a total of intensities of high frequency components having a higher frequency than the low frequency component, and segmenting the original image into an area occupied by the blocks classified as the cell cluster and another area.

Abstract: A target tracking method is provided for a computer device. The method includes determining a target candidate region of a current image frame; capturing a target candidate image matching the target candidate region from the current image frame; determining a target region of the current image frame according to an image feature of the target candidate image; determining motion prediction data of a next image frame relative to the current image frame by using a motion prediction model and according to the image feature of the target candidate image; and determining a target candidate region of the next image frame according to the target region and the motion prediction data.

Abstract: A visual search method, a computer device, and a non-transitory computer readable storage medium are provided. An ith image frame is received. The location and the classification of the subject in the ith image frame are extracted. A detection block corresponding to the subject is generated. In subsequent image frames of the ith image frame, the subject is tracked on the basis of the location of the subject in the ith image frame. The detection block is adjusted on the basis of the tracking result.