GPU Accelerated Edge-Region Based Level Set Evolution Constrained by 2D Gray-Scale Histogram

Here are the serial and the GPU based implementation of our paper IEEE TIP.2013.2255304

Due to its intrinsic nature which allows to easily handle complex shapes and topological changes, the level set method (LSM) has been widely used in image segmentation.Nevertheless, LSM is computationally expensive, which limits its applications in real-time systems. For this purpose, we proposed a new level set algorithm, which uses simultaneously edge, region, and 2D histogram information in order to efficiently segment objects of interest in a given scene. The computational complexity of the proposed LSM is greatly reduced by using the highly parallelizable lattice Boltzmann method (LBM) with a body force to solve the level set equation (LSE). The body force is
the link with image data and is defined from the proposed LSE. The proposed LSM is then implemented using an NVIDIA graphics processing units to fully take advantage of the LBM local nature. The new algorithm is effective, robust against noise, independent to the initial contour, fast, and highly parallelizable. The edge and region information enable to detect objects with and without edges, and the 2D histogram information enable the effectiveness of the method in a noisy environment.

The present Matlab codes are the implementation of our work. The serial implementation can be runned even if you don't have an NVIDIA GPU. But this is not the case of the parallel implementation. Everything is done as simple as possible in order to make the codes easy to use. After decompressing the file, you will find two folders(SERIAL and PARALLEL)and the Pdf of the paper. For each implementation you just need to:

1- Open the main code,
2- Put the adress of the image you want to segment,
3- Run the code (optional : add to path or change the folder)
4- Select the initial contour using the mouse,
5- And finally double click on the initial contour.

If you use any of these codes, please cite the implemented paper as follow

S. Balla-Arabé, X.-B Gao and B. Wang, “GPU Accelerated Edge-Region Based Level Set Evolution Constrained By 2D Gray-scale Histogram”, IEEE Transactions on Image Processing, vol. 22, no. 7, pp. 2688-2698, 2013.

If you have any question please let me know.

E -mail: [e-mail]
Google Scholar link: http://scholar.google.fr/citations?user=dYEIx_IAAAAJ&hl=fr&oi=sra