Computer Vision¶

6 domain-specific abstractions whose origin domain is Computer Vision.

Bag-of-words model in computer vision — An image representation that quantizes local visual descriptors into a learned vocabulary and summarizes the image by a histogram of visual-word occurrences.
Image color transfer — A mapping that transforms a source image’s color or tone distribution to resemble that of a target image while aiming to preserve source content.
Image rectification — A geometric transformation that maps images into a common plane so corresponding scene points align along simplified search loci.
Point-set registration — The estimation of a spatial transformation that aligns two or more point sets into a common coordinate frame despite noise, outliers or incomplete overlap.
Shape from focus — A three-dimensional reconstruction method that estimates scene depth from how image focus or defocus changes across a stack of differently focused views.
Visual hull — The maximal three-dimensional shape consistent with a set of calibrated object silhouettes, formed by intersecting their back-projected silhouette cones.