Abstract
Aiming at the shortcomings of the traditional level set model which only has good robustness to the weak boundary and strong noise of the original target image, this paper proposes an improved algorithm based on the no-weight initialization level set model, introducing bilateral filters and using implicit surface level sets to extract and segment the original target image object more accurately, clearly and intuitively in the evolution process. The experimental simulation results show that, compared with the traditional non-reinitialized level set model segmentation method, the improved method can more accurately extract the edge contours of the target image object, and has better edge contour extraction effect, and the original target noise reduction effect of the improved model is better than that of the model before the improvement. The original target image object edge contour takes less time to extract than the conventional non-reinitialized level set model before the improvement.
Funder
department of science and technology of Guizhou province
Science and Technology Program of the Guizhou Provincial Science and Technology Agency
Guizhou Key Laboratory of Big Data Statistical Analysis
Publisher
Public Library of Science (PLoS)
Reference25 articles.
1. Cai Qing. Research on image segmentation and target tracking algorithm based on level set theory[D]. xi’an: Northwestern Polytechnic University, 2019.
2. Ma Chao. Research on 3D segmentation of medical magnetic resonance image body data [D]. Harbin: Harbin Institute of Technology, 2019.
3. Wu Di. Research on typical target detection methods for optical remote sensing images [D]. Harbin: Harbin Institute of Technology, 2019.
4. Mahalanobis distance based on fuzzy clustering algorithm for image segmentation;X. Zhao;Digital Signal Processing,2015