Local Features Based Level Set Method for Segmentation of Images with Intensity Inhomogeneity
Local region-based level set models have recently been recognized as promising methods to segment images with intensity inhomogeneity. In these models, local intensity information in a neighborhood of predetermined size is extracted and then embedded into the energy function, where the local neighborhood intensities are assumed to be rather constant. Complex image characteristics, such as variation in degree of intensity inhomogeneity and noise levels, can lead to severe challenges for accurate image segmentation when using only a fixed scale parameter for local regions. In this paper, we propose a new multi-scale local feature-based level set method based on previous studies of multi-scale image filtering methods. Our novel method can adaptively determine the optimal scale parameter for each pixel during contour evolution, alleviating the challenges caused by severe intensity inhomogeneity. Our experimental results illustrate the good performance of the proposed level set method.
KeywordsIntensity inhomogeneity Level set Local maximum description difference Local region descriptor Multi-scale
This work was supported by the Major Science and Technology Program of Anhui Province (15czz02024), the National Natural Science Foundation of China (81401483), the Youth Innovation Promotion Association of CAS (2014290), Dean’s Fund of Hefei Institute of Physical Science, CAS (YZJJ201525), the Natural Science Fund of Anhui Province (1708085MF141), Development Project of Foreign Expert Recruitment Program of Anhui Province, and John S. Dunn Research Foundation (STCW).
- 3.Kim, D.H., Kim, H.K., Choi, K.S., Ko, S.J., et al.: Multi-scale level set based curve evolution for real-time non-rigid object contour tracking. In: TENCON 2009–2009 IEEE Region 10 Conference, pp. 1–5. IEEE (2009)Google Scholar
- 7.Li, C., Kao, C., Gore, J.C., Ding, Z.: Implicit active contours driven by local binary fitting energy, pp. 1–7 (2007)Google Scholar
- 20.Zhang, K., Zhang, L., Lam, K., Zhang, D.: A level set approach to image segmentation with intensity inhomogeneity. IEEE Trans. Syst. Man Cybern. 46(2), 546–557 (2016)Google Scholar