Fractal Dimension of Maximum Response Filters Applied to Texture Analysis RIBAS, L. C. ; GONÇALVES, D. N. ; ORUÊ, J. P. M. ; GONÇALVES, W. N. Pattern Recognition Letters, v. 6, p. 116-123, 2015
Texture provides fundamental features for several applications in computer vision and it is known to be an important cue for human vision. To improve the description of texture in different viewpoints (e.g., scale and orientation), we propose to extract fractal descriptors from invariant filter responses space. Experimental results on four well-known texture datasets show the effectiveness of the proposed method. In the experiments, FD-MRFt has provided better results than relevant texture methods, including the standard fractal descriptors. In addition, experimental results have shown the robustness of our method in a dataset with high noise.
If you find FD-MRF useful in your research, please consider citing using the bibtex which can be downloaded on the right.
MATLAB (tested with 2015a on MacOs)
Get the FD-MRF source code at `http://...`
If you are using MacOs, you may have the compiled mex file.
If you are using Linux, Windows or you want to compile for MacOs, please run `mex ...`.
Running FD-MRF on an image
Open a grayscale image:>> im = imread('board.tif');
Extract features: >> features = FDMRF(im);
Crie o seu próprio site exclusivo com modelos personalizáveis.