Rotating Kernel Transformation (Lee & Rhodes)

Filter emphasising the shape of the kernel (eg straight line) within an image

You are now following this Submission

The Rotating Kernel Transformation convolves an image with several orientations of a kernel.
For a line-kernel, straight lines are emphasized. For larger kernels, it becomes computationally expensive.

The zip-archive contains 5 files:
1) rktfilt.m ... function for filtering
2) rktkern.m ... for creating a kernel
3) rkttest.m ... script for testing the example
4) rktexample.mat ... sample image
5) example.png ... example screenshot

Please use
'help rktfilt' or 'doc rktfilt',
'help rktkern' or 'doc rktkern'
for help.

Reference:
Lee Y-K, Rhodes WT:
"Nonlinear image processing by a rotating kernel transformation"
Optics Letters, Vol. 15, No. 23, pp. 1383-1385, 1990.

Cite As

Florian Bazant-Hegemark (2026). Rotating Kernel Transformation (Lee & Rhodes) (https://www.mathworks.com/matlabcentral/fileexchange/14977-rotating-kernel-transformation-lee-rhodes), MATLAB Central File Exchange. Retrieved .

General Information

MATLAB Release Compatibility

  • Compatible with any release

Platform Compatibility

  • Windows
  • macOS
  • Linux
Version Published Release Notes Action
1.0.0.0

2 changes to rktfilt.m
1) Convert input to double
-> gets rid of warnings on Matlab 7 versions
2) Use imfilter instead of conv2
-> Quicker

Update inspired by File ID 14995