Image segmentation algorithm based on the second clustering and level set method
Jie Hai, Li Wu, Haiyan Wu, Hailong Du
Available Online December 2016.
- https://doi.org/10.2991/iceeecs-16.2016.218How to use a DOI?
- level set; image segmentation; intelligent algorithm; cluster analysis
- Improve the level set algorithm by Lagrangian particle enhanced replanting algorithm and increase the reduced segmentation accuracy brought about by the algorithm for uneven image pixel for medical CT image. Based on Literature , the combination of Lagrangian particle enhanced replanting algorithm and level set algorithm is adopted, the convergence of velocity field for singular point is promoted through increase of velocity vector and unit normal vector and the medical CT image segmentation method of hybrid level set (LPRLS) based on Lagrangian particle enhanced replanting algorithm is proposed in the Thesis. Calculate the Lagrangian labeled particle before calculating the formula of horizontal set to rebuild the embedded interface in order to improve the mass conservation property of level set algorithm; improve the convergence of velocity field for singular point and topological change point through increasing velocity vector and unit normal vector in order to handle the singularity of interface and complicated geometric correlation. The simulation results of algorithm indicate that the performance of the proposed algorithm is greatly improved compared with the original algorithm. It can be concluded from the simulation results that the existing insufficiency is the proportion of error identification of the algorithm.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
TY - CONF AU - Jie Hai AU - Li Wu AU - Haiyan Wu AU - Hailong Du PY - 2016/12 DA - 2016/12 TI - Image segmentation algorithm based on the second clustering and level set method BT - 2016 4th International Conference on Electrical & Electronics Engineering and Computer Science (ICEEECS 2016) PB - Atlantis Press SN - 2352-538X UR - https://doi.org/10.2991/iceeecs-16.2016.218 DO - https://doi.org/10.2991/iceeecs-16.2016.218 ID - Hai2016/12 ER -