Image Segmentation Using Regularized Level Set Method

This is the C++ code for the MATH-233 final Project

Comments/Bugs/Problems: maburidi@ucmerced.edu

November, 2022. Initial release

C++ Code:

Building

This README covers instructions for building the code and using the following example for image segmentation

Dependencies

OpenCV – 4.5.5

OpenCV As of this writing, the version installed from this github github is returning OpenCV 4.5.5

After installing the dependencies. The project can be built using g++, in the terminal run the following:

git clode https://github.com/Maburidi/MATH233_Project.git
cd MATH233_Project 
g++ -o output main.cpp  
 
./output ./input_imgs/img8.bmp  ./output_image.jpg 1. 200 5. -3. 1.5 0.8 0.2 2. 2 24 35 19 25 24 35 39 50
 
 

The argument in the command line above in order is as follows:
1- Image directory to be segmented
2- Directory to save segmented image
3- Time step
4- Number of Iterations
5- $\lambda$

6- $\alpha$

7- $\epsilon$

8- $\sigma$

9- $\mu$.

10- $c_0$

11- Number of 2d squares to be created in the image mask (for initial level set)

12- square 1 corner 1

13- square 1 corner 2

14- square 1 corner 3

15- square 1 corner 4

16- square 2 corner 1

17- square 2 corner 2

18- square 2 corner 3

19- square 2 corner 4

Discriptio of the parameters:

This table defines all the parameters used in the implementation of the model.

Results:

[1] Chunming Li, Chenyang Xu, Changfeng Gui, and Martin D. Fox. Distance regularized level set evolution and its
application to image segmentation. IEEE Transactions on Image Processing, 19(12):3243–3254, 2010


[2]  Chunming Li, Chenyang Xu, Changfeng Gui, and M.D. Fox. Level set evolution without re-initialization: a new
variational formulation. In 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
(CVPR’05), volume 1, pages 430–436 vol. 1, 2005.