Abstract: Disclosed herein are systems, methods and computer-program products to create synthetic immunohistochemistry (IHC) stained digital slides generated using artificial neural networks (ANNs). In some implementations, the created digital slides can be used as a ground truth to evaluate a method of analyzing IHC stained tissues.

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing a visual neural network to replace materials in a three-dimensional scene with visually similar materials from a source dataset. Specifically, the disclosed system utilizes the visual neural network to generate source deep visual features representing source texture maps from materials in a plurality of source materials. Additionally, the disclosed system utilizes the visual neural network to generate deep visual features representing texture maps from materials in a digital scene. The disclosed system then determines source texture maps that are visually similar to the texture maps of the digital scene based on visual similarity metrics that compare the source deep visual features and the deep visual features. Additionally, the disclosed system modifies the digital scene by replacing one or more of the texture maps in the digital scene with the visually similar source texture maps.

Abstract: A text partitioning method, a text classifying method, an apparatus, a device and a storage medium, wherein the method includes: parsing a content image, to obtain a target text in a text format; according to a line break in the target text, partitioning the target text into a plurality of text sections; and according to a first data-volume threshold, partitioning sequentially the plurality of text sections into a plurality of text-to-be-predicted sets, wherein a data volume of a last one text section in each of the text-to-be-predicted sets is greater than a second data-volume threshold.

Abstract: An object of the technique of the present disclosure is to obtain a demosaic network whose robustness for noise is high. In the technique of the present disclosure, first, a data set including a set of a teacher image with noise and a pupil image with noise is generated. Then, learning of a demosaic network is performed by using an image pair of the teacher image with noise and the pupil image with noise, to both of which noise is added.

Abstract: Provided is an image processing apparatus including a memory storing one or more instructions and a processor configured to execute the one or more instructions stored in the memory, wherein the processor is further configured to execute the one or more instructions to generate a second image by performing a deconvolution operation on a first image and a kernel comprising one or more weights, set values of the one or more weights based on the second image, and adjust the values of the one or more weights based on positions of the one or more weights in the kernel.

Abstract: Systems, computer-implemented methods, and computer readable media for generating a synthetic image of an anatomical portion based on an origin image of the anatomical portion acquired by an imaging device using a first imaging modality are disclosed. These systems may be configured to receive the origin image of the anatomical portion acquired by the imaging device using the first imaging modality, receive a convolutional neural network model trained for predicting the synthetic image based on the origin image, and convert the origin image to the synthetic image through the convolutional neural network model. The synthetic image may resemble an imaging of the anatomical portion using a second imaging modality differing from the first imaging modality.

Abstract: The contents of totes and the amount a tote container is filled are monitored. A central database stores product dimensions and tote dimensions as well as a percentage of which a tote is to be filled. Image scanners that obtain three-dimensional images are used to determine if the actual dimensions of the tote, the product, and the fill amount are consistent with the expected or optimal values of these characteristics. When there is a discrepancy between measured and expected values, then one or more actions can be taken.

Abstract: An image quality improvement method and an image processing apparatus using the same are provided. Denoising filtering is performed to an original image by a filter to obtain a preliminary processing image. The preliminary processing image is input to a multi-stage convolutional network model to generate an optimization image through the multi-stage convolutional network model. The multi-stage convolutional network model includes multiple convolutional network sub-models, and these convolutional network sub-models respectively correspond to different network architectures.

Abstract: A video processing method and apparatus, a computing device and a computer readable storage medium are disclosed. The video processing method includes obtaining a video frame sequence comprised in a video to be processed, performing scene classification identification on the video frame sequence so as to obtain a scene classification identification result of the video frame sequence, and performing a smoothing process to the video frame sequence based on the scene classification identification result.

Abstract: Embodiments are disclosed for adding lens blur effects to input images. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving a request to apply a lens blur effect to an image an accumulation region of the input image corresponding to a first pixel of an output image, determining a weight for each of the one or more source pixels based at least in part on an iris map for the one or more source pixels and a depth distance value between each of the one or more source pixels and the focal plane, and generating an output pixel value for the first pixel by calculating a weighted sum of the one or more source pixels from the accumulation region.

Abstract: A method for diagnostic imaging with reduced contrast agent dose uses a deep learning network (DLN) [114] that has been trained using zero-contrast [100] and low-contrast [102] images as input to the DLN and full-contrast images [104] as reference ground truth images. Prior to training, the images are pre-processed [106, 110, 118] to co-register and normalize them. The trained DLN [114] is then used to predict a synthesized full-dose contrast agent image [116] from acquired zero-dose and low-dose images.

Abstract: An image processing method includes acquiring a set of image samples for training an attribute recognition model, wherein the set of image samples includes a first subset of image samples with category labels and a second subset of image samples without category labels; training a sample prediction model using the first subset of image samples, and predicting categories of the image samples in the second subset of image samples using the trained sample prediction model; determining a category distribution of the set of image samples based on the category labels of the first subset of image samples and the predicted categories of the second subset of image samples; and acquiring a new image sample if the determined category distribution does not conform to the expected category distribution, and adding the acquired new image sample to the set of image samples.

Abstract: A vehicle position and velocity estimation system based on camera and LIDAR data is disclosed. An embodiment includes: receiving input object data from a subsystem of a vehicle, the input object data including image data from an image generating device and distance data from a distance measuring device, the distance measuring device comprising one or more LIDAR sensors; determining a first position of a proximate object near the vehicle from the image data; determining a second position of the proximate object from the distance data; correlating the first position and the second position by matching the first position of the proximate object detected in the image data with the second position of the same proximate object detected in the distance data; determining a three-dimensional (3D) position of the proximate object using the correlated first and second positions; and using the 3D position of the proximate object to navigate the vehicle.

Abstract: End to end differentiable machine vision systems, training methods, and processor-readable media are disclosed. A differentiable image signal processor (ISP) is disclosed that can be trained, using machine learning techniques, to adapt raw images received from a new sensor into an adapted images of the same type (i.e. in the same visual domain) as the images previously used to train a perception module, without fine-tuning the perception module itself. The differentiable ISP may include functional blocks for performing specific image enhancement operations using a relatively small number of learned parameters corresponding to meaningful characteristics of the image enhancement operations.

Abstract: Detecting cells depicted in an image using RNA segmentation can include obtaining a FISH image of a tissue that depicts multiple cells, obtaining a nuclear stained image of the tissue, and generating a mask that includes multiple areas that each have a position with respect to the tissue by enhancing structures depicted in the FISH image. Edges depicted in the enhanced FISH image are detected to use for the mask, and positions are determined for a first plurality of regions that fit potential nuclei depicted in the nuclear stained image. A second plurality of regions are selected from the first plurality by determining, using the mask, which regions from the first plurality overlap with the position of an area from multiple areas in the mask. Unique nuclei in the tissue are labelled using the second plurality of regions that each indicate a potential nuclei in the tissue.

Abstract: A system comprises a LiDAR sensor and a processor coupled to the LiDAR. The processor is configured to derive a regression line, and generate the outline of the static object by connecting the classified valid points except for the classified removal points. Wherein the processor is further configured to calculate an angle defined by one segment and another segment adjacent to the segment, select an i-lth point, which is a start point of a segment including an ith point, as a start point, when an angle between segments at both sides with respect to the ith point is greater than the reference angle, and select a jth point as an end point, when an angle between segments at both sides with respect to the jth point is less than or equal to the reference angle and when there is the start point before the jth point.

Abstract: Aspects of the present disclosure involve a system and a method for performing operations comprising: receiving a plurality of bone scale coefficients each corresponding to respective bones of a skeleton model; receiving a plurality of joint angle coefficients that collectively define a pose for the skeleton model; generating the skeleton model based on the received bone scale coefficients and the received joint angle coefficients; generating a base surface based on the plurality of bone scale coefficients; generating an identity surface by deformation of the base surface; and generating the 3D body model by mapping the identity surface onto the posed skeleton model.

Abstract: Aspects of the present disclosure relate to object-based image capture. Embodiments include identifying a reference point corresponding to an object in an image of a series of images. Embodiments include comparing a position of the reference point in the image to positions of one or more corresponding reference points in one or more previous images in the series of images. Embodiments include determining a total number of images in the series of images. Embodiments include selecting, based on the comparing and the total number of images in the series of images, between: capturing the image; or declining to capture the image.

Abstract: There is provided with a processing apparatus. A data holder holds at least some of data of a plurality of channels in a target layer among a plurality of layers. Each of a plurality of processors performs, in parallel, a product-sum operation using the data of one channel of the target layer and a coefficient corresponding to the target layer. A selector selects whether to perform first processing or second processing on the basis of information specifying processing in the target layer. The first processing includes inputting the data of one channel of the target layer into one of the plurality of processors. The second processing includes inputting the data of one channel of the target layer to the plurality of processors in parallel.

Abstract: The present invention discloses a method for adaptively detecting chessboard sub-pixel level corner points. Adaptive detection of chessboard sub-pixel level corner points is completed by marking position of an initial unit grid on a chessboard, using a homography matrix H calculated by pixel coordinates of four corner points of the initial unit grid in a pixel coordinate system and world coordinates in a world coordinate system to expand outwards, adaptively adjusting size of an iteration window in the process of expanding outwards, and finally spreading to the whole chessboard region.