CODEWITHSUNDEEP
algorithmimage-processing
Slaven Glumac
Slaven Glumac

Reputation: 553

Image alignment from known features

I want to align image X against image Y. Each image contains circles and Hough transform is used to detect them.

Lets assume Hough transform detects different number of circles in image X and image Y.

I want to find transformation of image X (rotation, translation) such that most circles in image X match some circle in image Y. Can you tell me how would you proceed?

Upvotes: 0

Views: 86

Answers (1)

ChronoTrigger
ChronoTrigger

Reputation: 8617

An approach:

  1. Get some properties from the circles of images X and Y, such as radius or others (color?).
  2. Find putative matches between the circles of X with those of Y. It is to say, two circles with a similar radius are a putative match. You may obtain several matches, correct and incorrect ones.
  3. Use a RANSAC-like algorithm to find the transformation:
    1. Select two random pairs of matching circles and compute the translation and rotation that these define.
    2. Check how many putative matches are ok if you assume the previous transformation (translation + rotation) was ok.
    3. Repeat.
    4. Keep the transformation that maximizes the number of matching circles.

Upvotes: 1

Related Questions