energy_gabor

energy_gabor ( ImageGabor, ImageHilbert : Energy : : )

Calculate the energy of a two-channel image.

energy_gabor calculates the local contrast (Energy) of the two input images. The energy of the resulting image is then defined as

     energy = channel1 ^2 + channel2 ^2 .

Often the calculation of the energy is preceded by the convolution of an image with a Gabor filter and the Hilbert transform of the Gabor filter (see convol_gabor). In this case, the first channel of the image passed to energy_gabor is the Gabor-filtered image, transformed back into the spatial domain (see fft_image_inv), and the second channel the result of the convolution with the Hilbert transform, also transformed back into the spatial domain. The local energy is a measure for the local contrast of structures (e.g., edges and lines) in the image.

Parameters

`ImageGabor` (input_object)	image(-array) `->` object : byte / real
1st channel of input image (usually: Gabor image).

`ImageHilbert` (input_object)	image(-array) `->` object : byte / real
2nd channel of input image (usually: Hilbert image).

`Energy` (output_object)	image(-array) `->` object : real
Image containing the local energy.

Example (Syntax: C)

fft_image(Image,&FFT);
gen_gabor(&Filter,1.4,0.4,1.0,1.5,512);
convol_gabor(FFT,Filter,&Gabor,&Hilbert);
fft_image_inv(Gabor,&GaborInv);
fft_image_inv(Hilbert,&HilbertInv);
energy_gabor(GaborInv,HilbertInv,&Energy);

Result

energy_gabor returns 2 (H_MSG_TRUE) if all parameters are correct. If the input is empty the behavior can be set via set_system(::'no_object_result',<Result>:). If necessary, an exception handling is raised.

Parallelization Information

energy_gabor is reentrant and automatically parallelized (on tuple level, domain level).

Possible Predecessors

gen_gabor, convol_gabor, fft_image_inv

Module

Foundation