Abstract: Efficient location and identification of documents in images. In an embodiment, at least one quadrangle is extracted from an image based on line(s) extracted from the image. Parameter(s) are determined from the quadrangle(s), and keypoints are extracted from the image based on the parameter(s). Input descriptors are calculated for the keypoints and used to match the keypoints to reference keypoints, to identify classification candidate(s) that represent a template image of a type of document. The type of document and distortion parameter(s) are determined based on the classification candidate(s).

Abstract: A method for detecting holographic elements in a video stream containing images in the form of documents includes: processing of a video stream in which the document image is stabilized; constructing saturation and color tone maps; analyzing color characteristics in image regions; constructing histograms of color characteristics; estimating a change in the color characteristics at least in part based on data obtained by calculating a difference between the histograms of a current and a previous frame; constructing an integrated map of hologram presence estimates by combining calculated estimates for all video stream frames based at least in part on the estimation of the change in color characteristics; and determining final regions of the holographic elements based at least in part on the integrated map of the hologram presence estimates.