A New Fuzzy Connectedness Relation for Image Segmentation

In the image segmentation field, traditional techniques do not completely meet the segmentation challenges mostly posed by inherently fuzzy images. Fuzzy connectedness and fuzzy clustering are considered as two well-known techniques for introducing fuzzy concepts to the problem of image segmentation. Fuzzy connectedness-based Segmentation methods consider spatial relation of image pixels by "hanging togetherness" a notion based on intensity homogeneity. But, they do not inherently utilize feature information of image pixels. On the other hand, as the segmentation domain of fuzzy clustering-based methods is the feature space they do not consider spatial relations among image pixels. Recently, the authors proposed a new segmentation method based on a combination of fuzzy connectedness and fuzzy clustering called membership connectedness, by which the spatial relation of image pixels is constructed in the related membership domain. In this paper, we have proposed a new fuzzy connectedness relation for image segmentation in membership domain which outperforms the previously defined relation in noisy images. In this relation, we have emphasized on the path length rather than the path strength and have considered shorter paths as more reliable paths in noisy images. Experiments were performed using synthetic as well as brain magnetic resonance image (MRI) datasets. The numerical validation demonstrated the strength of the proposed algorithm especially for medical image segmentation purposes.

[1]  James C. Bezdek,et al.  Pattern Recognition with Fuzzy Objective Function Algorithms , 1981, Advanced Applications in Pattern Recognition.

[2]  Annette Sterr,et al.  MRI fuzzy segmentation of brain tissue using neighborhood attraction with neural-network optimization , 2005, IEEE Transactions on Information Technology in Biomedicine.

[3]  Jayaram K. Udupa,et al.  Iterative relative fuzzy connectedness for multiple objects with multiple seeds , 2007, Comput. Vis. Image Underst..

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

[5]  Dzung L. Pham,et al.  Spatial Models for Fuzzy Clustering , 2001, Comput. Vis. Image Underst..

[6]  Jayaram K. Udupa,et al.  Vectorial scale-based fuzzy-connected image segmentation , 2006, Comput. Vis. Image Underst..

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

[8]  Azriel Rosenfeld,et al.  The fuzzy geometry of image subsets , 1984, Pattern Recognit. Lett..

[9]  Silvana G. Dellepiane,et al.  Extraction of intensity connectedness for image processing , 1995, Pattern Recognit. Lett..

[10]  M. Ibrahim,et al.  Hidden Markov models-based 3D MRI brain segmentation , 2006, Image Vis. Comput..

[11]  Ron Kikinis,et al.  Improved watershed transform for medical image segmentation using prior information , 2004, IEEE Transactions on Medical Imaging.

[12]  Jayaram K. Udupa,et al.  Fuzzy connectedness and image segmentation , 2003, Proc. IEEE.

[13]  Ioannis A. Kakadiaris,et al.  Image segmentation based on fuzzy connectedness using dynamic weights , 2006, IEEE Transactions on Image Processing.

[14]  Verónica Médina-Bañuelos,et al.  Data-driven brain MRI segmentation supported on edge confidence and a priori tissue information , 2006, IEEE Transactions on Medical Imaging.