论文信息 - Adaptive Fuzzy Connectedness-Based Medical Image Segmentation

Adaptive Fuzzy Connectedness-Based Medical Image Segmentation

In this paper, we present an enhancement of the fuzzy connectedness-based image segmentation method based on dynamic computation of adaptive weights for the homogeneity and the directional gradient energy functions. Adaptive weights enhance the performance and robustness of the conventional fuzzy connectedness-based segmentation while decreasing the degree of user interaction. The accuracy of the adaptive fuzzy connectedness-based segmentation of typical fuzzy medical images is assessed with respect to the conventional fuzzy connectedness.

Ioannis A. Kakadiaris | Uday Kurkure | Amol Pednekar

[1] Guido Gerig,et al. Valmet: A New Validation Tool for Assessing and Improving 3D Object Segmentation , 2001, MICCAI.

[2] Supun Samarasekera,et al. Fuzzy Connectedness and Object Definition: Theory, Algorithms, and Applications in Image Segmentation , 1996, CVGIP Graph. Model. Image Process..

[3] F. Frances Yao,et al. Computational Geometry , 1991, Handbook of Theoretical Computer Science, Volume A: Algorithms and Complexity.

[4] Yongmin Kim,et al. A methodology for evaluation of boundary detection algorithms on medical images , 1997, IEEE Transactions on Medical Imaging.

[5] N. Otsu. A threshold selection method from gray level histograms , 1979 .

[6] Jayaram K. Udupa,et al. Scale-Based Fuzzy Connected Image Segmentation: Theory, Algorithms, and Validation , 2000, Comput. Vis. Image Underst..

[7] Supun Samarasekera,et al. Fuzzy connectedness and object definition , 1995, Medical Imaging.