25 October 2016 Wavelet-based improved Chan-Vese model for image segmentation
Author Affiliations +
Proceedings Volume 10157, Infrared Technology and Applications, and Robot Sensing and Advanced Control; 101570O (2016) https://doi.org/10.1117/12.2244592
Event: International Symposium on Optoelectronic Technology and Application 2016, 2016, Beijing, China
In this paper, a kind of image segmentation approach which based on improved Chan-Vese (CV) model and wavelet transform was proposed. Firstly, one-level wavelet decomposition was adopted to get the low frequency approximation image. And then, the improved CV model, which contains the global term, local term and the regularization term, was utilized to segment the low frequency approximation image, so as to obtain the coarse image segmentation result. Finally, the coarse segmentation result was interpolated into the fine scale as an initial contour, and the improved CV model was utilized again to get the fine scale segmentation result. Experimental results show that our method can segment low contrast images and/or inhomogeneous intensity images more effectively than traditional level set methods.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xiaoli Zhao, Xiaoli Zhao, Pucheng Zhou, Pucheng Zhou, Mogen Xue, Mogen Xue, } "Wavelet-based improved Chan-Vese model for image segmentation", Proc. SPIE 10157, Infrared Technology and Applications, and Robot Sensing and Advanced Control, 101570O (25 October 2016); doi: 10.1117/12.2244592; https://doi.org/10.1117/12.2244592

Back to Top