hexfft

A Python package aiming to provide an easy and efficient interface to various implementations of the Hexagonal Fast Fourier Transform.

See this blog post for background.

Get started

Plot hexagonally sampled 2D signals

from hexfft import HexArray
from hexfft.plot import hexshow
import numpy as np

data = np.random.normal(size=(8, 6))
h = HexArray(data)
hexshow(h)

Perform FFT for rectangularly or hexagonally periodic signals

from hexfft import fft, ifft

X = fft(h)

Operate on a 3D stack

from hexfft import FFT

shape = (32, 32)

fftobj = FFT(shape, periodicity="hex") # or "rect"
x = np.random.normal(size=(10, 32, 32))
X = fftobj.forward(x)
xx = fftobj.inverse(X)

...

Example notebooks

1 - HexArray and visualization

2 - FFT with rectangular periodicity

3 - FFT with hexagonal periodicity

4 - Basic filtering example

Install

pip install hexfft

The only dependencies are numpy, scipy, and matplotlib. pytest is required to run the tests.

Developer install

git clone git@github.com:chris-langfield/hexfft.git
pip install -e hexfft/
cd hexfft
pytest tests/

Further reading

---

R. M. Mersereau, "The processing of hexagonally sampled two-dimensional signals," in Proceedings of the IEEE, vol. 67, no. 6, pp. 930-949, June 1979, doi: 10.1109/PROC.1979.11356

J. C. Ehrhardt, “Hexagonal fast Fourier transform with rectangular output,” IEEE Transactions on Signal Processing, vol. 41, no. 3. Institute of Electrical and Electronics Engineers (IEEE), pp. 1469–1472, Mar. 1993. doi: 10.1109/78.205759.