A method of processing a given region of interest (ROI) of an X-ray image of a person's breast to determine presence of a malignancy, the X-ray image having X-ray pixels that indicate intensity of X-rays that passed through the breast to generate the image, the method comprising: for each given X-ray pixel in the given ROI and each of a selection of J(r) X-ray pixels at respective pixel radii PR(r), 1≤r≤R, from the given x-ray pixel, determining a binary number that provides a measure X-ray intensity indicated by the selected X-ray pixel relative to X-ray intensity indicated by the given X-ray pixel; using the determined binary numbers for the selected X-ray pixels at each pixel radius PR(r) to determine a decimal number for the pixel radius PR(r); histogramming the frequency of occurrence of values of the determined decimal numbers as a function of pixel radius for the given X-ray pixels in the given ROI; determining a texture feature vector, for the given ROI having components that are equal to the frequencies of occurrence for a selection of M histogrammed values; and processing the histogrammed frequencies of occurrence for the M values to determine whether the given ROI is malignant.

Some embodiments relate to a system and method to increase the speed of a computer determination whether a video contains a particular content. In some embodiments, the quantity of data in the video is first reduced while preserving the searched-for content. Optionally, first, the size of the data is reduced by reducing the resolution, for example resolution may be reduced without searching and/or processing the full data set. Additionally or alternatively, low quality and/or empty data is removed from the dataset. Additionally or alternatively, redundant data may be searched out and/or removed. Optionally, after data reduction, the reduced dataset is analyzed to determine if it contains the searched-for content. Optionally, an estimate is made of the probability of the full dataset containing the searched-for content.

Some embodiments relate to a system and method to increase the speed of a computer determination whether a video contains a particular content. In some embodiments, the quantity of data in the video is first reduced while preserving the searched-for content. Optionally, first, the size of the data is reduced by reducing the resolution, for example resolution may be reduced without searching and/or processing the full data set. Additionally or alternatively, low quality and/or empty data is removed from the dataset. Additionally or alternatively, redundant data may be searched out and/or removed. Optionally, after data reduction, the reduced dataset is analyzed to determine if it contains the searched-for content. Optionally, an estimate is made of the probability of the full dataset containing the searched-for content.

Systems and methods for determining an alignment of a trailer relative to a docking bay or a vehicle bay door using dynamic depth filtering. Image data and position data is captured by a 3D camera system with an at least partially downward-facing field of view. When a trailer is approaching the docking bay or door, the captured image data includes a top surface of the trailer. A dynamic height range is determined based on an estimated height of the top surface of the trailer in the image data and a dynamic depth filter is applied to filter out image data corresponding to heights outside of the dynamic height range. An angular position and/or lateral offset of the trailer is determined based on the depth-filtered image data.

A method comprises displaying, via an interactive interface, a medical scan and a plurality of prompts of each prompt decision tree of a plurality of prompt decision trees in succession, beginning with automatically determined starting prompts of each prompt decision tree, in accordance with corresponding nodes of each prompt decision tree until a leaf node of each prompt decision tree is ultimately selected. Labeling data indicating the ultimately selected leaf node of each prompt decision tree is determined for the medical scan.

A method comprises displaying, via an interactive interface, a medical scan and a plurality of prompts of each prompt decision tree of a plurality of prompt decision trees in succession, beginning with automatically determined starting prompts of each prompt decision tree, in accordance with corresponding nodes of each prompt decision tree until a leaf node of each prompt decision tree is ultimately selected. Labeling data indicating the ultimately selected leaf node of each prompt decision tree is determined for the medical scan.

When performing anisotropic filtering when sampling a texture to provide an output sampled texture value for use when rendering an output in a graphics processing system, an anisotropy direction along which to take samples in the texture is determined by determining X and Y components of a vector of arbitrary length corresponding to the direction of the major axis of an assumed elliptical projection of the sampling point for which the texture is being sampled onto the surface to which the texture is being applied, and then normalising the determined X and Y vector components to provide X and Y components for a unit vector corresponding to the direction of the major axis of the elliptical footprint of the sampling point to be used as the anisotropy direction along which to take samples in the texture.

When performing anisotropic filtering when sampling a texture to provide an output sampled texture value for use when rendering an output in a graphics processing system, an anisotropy direction along which to take samples in the texture is determined by determining X and Y components of a vector of arbitrary length corresponding to the direction of the major axis of an assumed elliptical projection of the sampling point for which the texture is being sampled onto the surface to which the texture is being applied, and then normalising the determined X and Y vector components to provide X and Y components for a unit vector corresponding to the direction of the major axis of the elliptical footprint of the sampling point to be used as the anisotropy direction along which to take samples in the texture.

A method for restoring video data of a pipe based on computer vision is provided. The method includes: performing gray stretching on pipe image/video collected by a pipe robot; processing noise interference by smoothing filtering; extracting an iron chain from the center of a video image as a template for location; performing target recognition on the center of video data by an SIFT corner detection algorithm; detecting ropes on left and right sides of a target by Hough transform; performing gray covering on the iron chain at the center of the video image and the ropes on two sides; and restoring data by an FMM image restoration algorithm.

A method for restoring video data of a pipe based on computer vision is provided. The method includes: performing gray stretching on pipe image/video collected by a pipe robot; processing noise interference by smoothing filtering; extracting an iron chain from the center of a video image as a template for location; performing target recognition on the center of video data by an SIFT corner detection algorithm; detecting ropes on left and right sides of a target by Hough transform; performing gray covering on the iron chain at the center of the video image and the ropes on two sides; and restoring data by an FMM image restoration algorithm.