Matlab code - xaaaandao/piperaceae-features GitHub Wiki

Requirements

1. Use the institutional e-mail to download the software.
2. After downloading, access the location (via terminal) and execute the commands below.

$ unzip matlab_*_glnxa64.zip
$ cd matlab_*_glnxa64
$ sudo chmod a+x install
$ sudo ./install

• Replace the asterisk for the version downloaded.

3. After the GUI appears, click next until the installation is complete.
4. To run the Matlab, access the terminal and execute the command below.

$ ./matlab

Attention

The images must be in grayscale mode to run this code.

To run

1. Open get_features.m

2. Replace the variable input's value with the images' location and the variable output's value to a folder available.

3. After that, press the F5 or Run buttons to run the code.

Output

• This program will create three folder content four files
  1. lbp+matlab
     • lbp.txt
       • Each line contains 59 columns
       • The last column represents the class.
     • info_lbp.csv, info_levels.csv, info_sample.csv

2. surf64+matlab
   • surf128.txt
     • Each line contains 128 columns
     • The last column represents the class.
     • info_lbp.csv, info_levels.csv, info_sample.csv
3. surf128+matlab
   • surf64.txt
     • Each line contains 257 columns
     • The last column represents the class.
     • info_lbp.csv, info_levels.csv, info_sample.csv

• The main differences between surf64.txt and surf128.txt are:

  • Number of points used to extract features;
  • The number of features.

• info_levels.csv and info_samples.csv are files equal between three folders.

  • It is created for each folder to facilitate the next step (identification).
  • This link contains the mean of each row.

• info_lbp.txt, info_surf64.txt, and info_surf128.txt are files very similar.

  • The difference is the value of each row.
  • This link contains the mean of each row.