Abstract: A method of image processing converts images of different brightness to a common brightness range, the images representing at least partly the same scene. One of images including a local block with movement is selected for forming a composed image from the images. One or more corresponding blocks corresponding to the local block are determined in the images. Each of said one or more corresponding blocks is weighted with at least one of the following: similarity with respect to the local block, a distance from a location of the local block, saturation of the one or more corresponding blocks, and noise of the one or more corresponding blocks. The local block and at least one of the one or more corresponding blocks are combined, or the local block is replaced by at least one of the one or more corresponding blocks based on the weighting for forming the composed image from the images.
Abstract: A method of registering images by adjusting a distribution of spatial frequencies of correlation between spatial frequency functions of images, a number of images being N, where N being an integer equal to or larger than two, and determining at least one shift between the images using the frequency distribution adjusted correlation.
Abstract: An image processing method for improving image quality selects one of a plurality of two-dimensional pixel matrix source images of an imaged target as a reference image. Movement of the target is detected in the source images. The detected movement between the reference image and at least one other image of the source images is compensated differently in at least two different sections of the at least one other source image. The reference image and the movement compensated at least one other image are combined for forming an improved image.
Abstract: An image processing method for improving image quality selects one of a plurality of two-dimensional pixel matrix source images of an imaged target as a reference image. Movement of the target is detected in the source images. The detected movement between the reference image and at least one other image of the source images is compensated differently in at least two different sections of the at least one other source image. The reference image and the movement compensated at least one other image are combined for forming an improved image.
Abstract: A solution for face recognition. The solution includes detecting a face from a digital image constructed of multiple pixels, selecting a neighbor-hood for a pixel under observation, obtaining a combination of pixel values weighted with at least one set of coefficients, and determining information on face similarity between the observed face and at least one face.
Type:
Grant
Filed:
October 4, 2010
Date of Patent:
November 12, 2013
Assignee:
Visidon Oy
Inventors:
Matti Niskanen, Markus Turtinen, Jari Hannuksela
Abstract: A solution for face recognition. The solution includes detecting a face from a digital image constructed of multiple pixels, selecting a neighbor-hood for a pixel under observation, obtaining a combination of pixel values weighted with at least one set of coefficients, and determining information on face similarity between the observed face and at least one face.
Type:
Application
Filed:
October 4, 2010
Publication date:
August 23, 2012
Applicant:
VISIDON OY
Inventors:
Matti Niskanen, Markus Turtinen, Jari Hannuksela
Abstract: There is provided an improved solution for detecting and tracking objects in digital images. The solution comprises selecting a neighborhood for each pixel under observation, the neighborhood being of known size and form, and reading pixel values of the neighborhood. Further the solution comprises selecting at least one set of coefficients for weighting each neighborhood such that each pixel value of each neighborhood is weighted with at least one coefficient; searching for an existence of at least one object feature at each pixel under observation on the basis of a combination of weighted pixel values at each neighborhood; and verifying the existence of the object in the digital image on the basis of the searches of existence of at least one object feature at a predetermined number of pixels.
Type:
Grant
Filed:
October 15, 2009
Date of Patent:
January 24, 2012
Assignee:
Visidon Oy
Inventors:
Matti Niskanen, Markus Turtinen, Jari Hannuksela