Abstract: Devices, systems, and methods obtain training images; generate image-alignment data based on the training images; cluster the training images based at least in part on the image-alignment data, thereby generating clusters of training images; and select one or more representative images from the training images based on the clusters of training images.
Abstract: Devices, systems, and methods obtain a reference image; obtain a test image; globally align the test image to the reference image; select subfields in the test image; align the subfields in the test image with respective areas in the reference image; warp the test image based on the aligning of the subfields; select anchor points in the reference image; select anchor-edge points in the reference image; realign the subfields in the warped test image with respective areas in the reference image based on the anchor points in the reference image and on the anchor-edge points in the reference image; and warp the warped test image based on the realigning of the subfields.
Abstract: Devices, systems, and methods obtain respective corresponding feature-detection scores for a plurality of areas in an image; calculate respective corresponding sorting scores for at least some areas of the plurality of areas; for the at least some areas of the plurality of areas, arrange the corresponding feature-detection scores in order of the corresponding sorting scores, thereby generating an order of sorted feature-detection scores; and assign respective detection scores to the at least some areas based on the order of sorted feature-detection scores and on three or more of the following: the respective corresponding feature-detection scores of the areas, a spectral threshold, a spatial threshold, and a neighborhood kernel.
Abstract: Devices, systems, and methods obtain a first image, obtain a second image, calculate respective distances between a histogram from a patch in the first image to respective histograms from patches in the second image, and identify a patch in the second image that is most similar to the patch in the first image based on the respective distances.
Type:
Grant
Filed:
October 25, 2017
Date of Patent:
September 10, 2019
Assignee:
Canon Virginia, Inc.
Inventors:
Hung Khei Huang, Bradley Scott Denney, Yang Yang
Abstract: The present disclosure relates to methods and devices for the separation of blood components including separation by rapid sedimentation, including in an automated fashion.
Type:
Application
Filed:
November 28, 2018
Publication date:
May 30, 2019
Applicant:
Canon Virginia, Inc.
Inventors:
Nabil Mikhaiel, Lindsay Sanford, Kelly Coughenour, Jeremy Schreiber
Abstract: The invention relates to a mechanically-collapsible core device includes a central pin having a plurality of engaging members, a plurality of first collapsible core members each having an engaging member that engages with a respective engaging member of the central pin, a base member having a plurality of engaging members, and a plurality of second collapsible core members each having an engaging member that engages with a respective engaging member of the base member. The pin is retracted from a home position, thereby causing the first core members to collapse inward. The base member is then retracted, thereby causing the second core members to translate inward and linearly. The result is that the core device collapses inward in size so as to permit the device to be removed from the inside of a molded article.
Abstract: An apparatus for forming a number of holes in a medium includes a selector, a hole forming device and a controller. The selector selects the number of holes to be formed in the medium, with the number of holes being selected from at least two predetermined numbers such as two and three. The hole forming device forms the holes in the medium. The controller controls the hole forming device to form in the medium the number of holes selected by the selector.
Abstract: An image forming apparatus selectively forms images on one or two sides of recording media. The apparatus includes an image forming engine, a port, a series of conveying rollers and guides, drivers and a microprocessor. The image forming engine forms images on the recording media. The port selectively receives a refeeder unit for receiving recording media having images formed on one side thereof by the image forming engine or a unit for storing unrecorded recording media. The series of conveying rollers and guides contact and convey the recording media, while the drivers drive the conveying rollers and guides. The microprocessor controls the image forming engine and the drivers of the conveying rollers and guides.