I have a questions which i am trying to solve.
I would like to take a set of 2000 images, find out the HOG descriptors of the images and save the vectors in the form of a jpg for all the images. I have found the following sample which takes a single image and plots the descriptors on the image:
img=(*image*);
dims = ImageDimensions[img];
dirs = ImageData[GradientOrientationFilter[img, 5]];
magnitudes = ImageData[GradientFilter[img, 5]];
orientations =
MapThread[#1 {-Sin[#2], Cos[#2]} &, {magnitudes, dirs}, 2];
Show[img,
ListVectorPlot[
MapIndexed[{{#2[[2]], dims[[2]] - #2[[1]]}, #1} &,
orientations, {2}], VectorColorFunction -> (Yellow &)]]
There are two problems with this, I would like to get an output of only the descriptors (without the image in the background) in the form of a jpg and also i would like to write a loop for 2000 images.
The source of my example is wolfram documentation , Please see the Applications section
http://reference.wolfram.com/language/ref/GradientOrientationFilter.html
Thanks