MatLAB Answers

In this HW, you are asked to implement histogram of oriented gradient (HOG) descriptor from scratch as discussed in class. HOG is not just used in interest point descriptors such as SIFT. It is also a widely used feature for object recognition.

For simplicity, we will ignore the step of finding interest points but simply partition the image into cell/patch and compute the HOG in each cell.



You can use Matlab. (Note that the Matlab demo appears to display the gradient with 90o rotation and thus shows something a bit different.) "

p/s: I NEED the source code and picture result of the (file-20170526-6421-1j3azw3.jpg) image. I uploaded my professor's example images and his resulting picture (gantrycrane.png and hog_result.png) to show you the result I want for the ((file-20170526-6421-1j3azw3.jpg). You can cut half of the picture if it's too big.

assignment is to explore the following matlab functions:

rand, disp, display, size, reshape, max, sum, repmat, ones, zeros, imshow, imhist, rgb2gray

You should write some matlab code to demonstrate the working of each of the above functions. Your matlab code should be written in such a way that any user without any prior knowledge of matlab should be able to read your code and understand exactly what a matlab function is doing in easy-to-understand manner. You may add comments in your code to explain thing in more detail.

If you are using Octave, you may need to add the following line on the top of your code:

pkg load image;

Create a function (prob3_1) that takes an input vector of integers (each between 1 and 100) and will output the number of elements strictly greater than 30 and calculate the sum of all elements in the vector. Do this only with loops and if statements, do not use the SUM function.