Image registration utility using algorithms based on discrete Fourier transform (DFT, FFT)
imreg_dft is your first-choice Python image registration utility. In plain language, it implements means of guessing translation, rotation and scale variation between two images. The name comes from the fact that it doesn’t work with those images directly, but it works with their spectrum (DFT using FFT), and its log-polar transformation , hence the _dft after imreg.
Basically, if you want to align two images that have different scale and are rotated and shifted against each other, imreg_dft is the tool you want to check out. Get started in five minutes and see how it works for you!
Brno University of Technology, Brno, Czech Republic
Laboratory for Fluorescence Dynamics, University of California, Irvine
2014-2015, Matěj Týč
2011-2014, Christoph Gohlke
imreg_dft is free software, i.e. both free of charge (so it is free as free beer) and you as a user are granted four basic freedoms (so it is also free as free speech).
Generally, you will need numpy and scipy for the algorithm functionality and matplotlib for plotting. For the command-line tool, reading images is useful, so make sure you have pillow (or PIL, which is deprecated).
Check the documentation on readthedocs.ort (bleeding-edge) or pythonhosted.org (with images). Or even better, generate the documentation yourself!
Install the package by running python setup.py install in the project root.
Install packages that are required for the documentation to compile (see the requirements_docs.txt file.
Go to the doc directory and run make html there. The documentation should appear in the _build subfolder, so you may open _build/html/index.html with your web browser to see it.
imreg_dft is based on the code by Christoph Gohlke.
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.