Edge detection methods based on oriented half kernels

Edge detection methods based on oriented half kernels

Thin filters, rotated in all the desired directions are useful
to detect edges, or extract precisely their orientations.
These kernels are easy to use and reliable in image analysis.
Different filters are implemented in order to build half kernels.

Five methods are provided:

main_HF_Bour : edge extraction using oriented half Bourennane kernels
main_HF_Deriche : edge extraction using oriented half Deriche kernels
main_HF_gaussian : edge extraction using oriented half Gaussian kernels
main_HF_m1_0_1 : edge extraction using oriented half DoB (Difference of Boxes) kernels
main_HF_Shen : edge extraction using oriented half Shen kernels

For more information, read the following paper, and if you use this in published work, please cite:
An Objective Evaluation of Edge Detection Methods based on Oriented Half Kernels
Baptiste Magnier
International Conference on Image and Signal Processing 2018 (ICISP 2018)
2018