An automated microscope system is described that detects dicentric chromosomes (DCs) in metaphase cells arising from exposure to ionizing radiation. The radiation dose depends on the accuracy of DC detection. Accuracy is increased using image segmentation methods are used to rank high quality cytogenetic images and eliminate suboptimal metaphase cell data in a sample based on novel quality measures. When a sufficient number of high quality images are detected, the microscope system is directed to terminate metaphase image collection for a sample. The microscope system integrates image selection procedures that control an automated digitally controlled microscope with the analysis of acquired metaphase cell images to accurately determine radiation dose. Early termination of image acquisition reduces sample processing time without compromising accuracy. This approach constitutes a reliable and scalable solution that will be essential for analysis of large numbers of potentially exposed individuals.

A system and method for automatically modeling symmetry planes and principal orientations from three dimensional (3D) segments. The system comprises receiving a set of 3D segments representing a structure from the input source, wherein the set of 3D segments comprises one or more segment pairs. The system then generates symmetry plane data by calculating a symmetry plane for each of the one or more segment pairs. Next, the system accumulates the symmetry plane data in a Hough space. Lastly, the system constructs one or more Hough space symmetry planes from the symmetry plane data and calculates a principal orientation of the structure.

Systems and methods for detecting blind spots using a robotic apparatus are disclosed herein. According to at least one exemplary embodiment, a robot may utilize a plurality of virtual robots or representations to determine intersection points between extended measurements from the robot and virtual measurements from a respective one of the virtual robot or representation to determine blind spots. The robot may additionally consider locations of the blind spots while navigating a route to enhance safety, wherein the robot may perform an action to alert nearby humans upon navigating near a blind spot along the route.

A first set of pixels forming a first set of rows and a first set of columns of a first image acquired by an image acquisition device is received. A first corrected set of pixels forming a first corrected set of rows and a first corrected set of columns is generated from the first set of pixels. Successive pixels of each row from the first corrected set of rows correspond to successive parallel lines in a plane defined by the sheet of light that are equally spaced along a first axis of a world coordinate system. Successive pixels of each column from the first corrected set of columns correspond to successive parallel lines in the plane defined by the sheet of light that are equally spaced along a second axis of the world coordinate system. Based on the first corrected set of pixels, a first set of points of the sheet of light is determined. The first set of points of the sheet of light is used to obtain a three-dimensional profile of the object.

An image matching system for determining visual overlaps between images by using box embeddings is described herein. The system receives two images depicting a 3D surface with different camera poses. The system inputs the images (or a crop of each image) into a machine learning model that outputs a box encoding for the first image and a box encoding for the second image. A box encoding includes parameters defining a box in an embedding space. Then the system determines an asymmetric overlap factor that measures asymmetric surface overlaps between the first image and the second image based on the box encodings. The asymmetric overlap factor includes an enclosure factor indicating how much surface from the first image is visible in the second image and a concentration factor indicating how much surface from the second image is visible in the first image.

A road surface state determination apparatus of the present disclosure includes an acquisition interface configured to acquire an image representing a road surface imaged by a camera, and a controller configured to determine whether the road surface is wet or dry on the basis of a spatial change in luminance of pixels in a continuous region included in the image.

A method of diagnosing breast cancer, the method comprising: acquiring a contrast enhanced region of interest (CE-ROI) comprised in an X-ray image of a patient's breast, the X-ray image comprising X-ray pixels that indicate intensity of X-rays that passed through the breast to generate the image; generating a texture feature vector (TF) having components based on the indications of intensity provided by a plurality of X-ray pixels in the CE-ROI; and using a classifier to classify the texture feature vector TF to determine whether the CE-ROI is malignant.

An image processing apparatus includes a control unit. The control unit performs OCR processing by identifying a specified area of image data as a detection area, detecting line images contained in the detection area, and analyzing the detected line images to identify a character represented by the line images. Furthermore, when failing to identify a character represented by the line images in the OCR processing, the control unit determines whether the line images represent a part of a character and, upon determination that the line images represent a part of a character, expands the detection area in a direction where the other part of the character to be identified is assumed to be present and performs the OCR processing again on the expanded detection area.

A first image is received. An initial label is assigned to at least some pixels in the first image, including by assigning a first label to a first pixel. A determination is made that the first pixel's label should be replaced with a different label. The first pixel's label is updated with the different label.

The present disclosure includes systems, methods, and non-transitory computer readable media that efficiently and accurately identify matching designs and sub-shapes across one or more digital canvases in order to provide one or more development tools for rapid and efficient editing of the digital canvases. In particular, one or more embodiments utilize a transformation-agnostic method of identifying matching designs and sub-shapes between multiple digital canvases. Furthermore, in response to identifying a set of matching designs or sub-shapes, one or more embodiments generate a mapping between the matching designs or sub-shapes. Utilizing this mapping, one or more embodiments provide various tools that enable rapid and efficient development of robust digital canvases, while minimizing system storage burdens.