Symmetric region growing

Of the many proposed image segmentation methods, region growing has been one of the most popular. Research on region growing, however, has focused primarily on the design of feature measures and on growing and merging criteria. Most of these methods have an inherent dependence on the order in which the points and regions are examined. This weakness implies that a desired segmented result is sensitive to the selection of the initial growing points. We define a set of theoretical criteria for a subclass of region-growing algorithms that are insensitive to the selection of the initial growing points. This class of algorithms, referred to as symmetric region growing algorithms, leads to a single-pass region-growing algorithm applicable to any dimensionality of images. Furthermore, they lead to region-growing algorithms that are both memory- and computation-efficient. Results illustrate the method's efficiency and its application to 3D medical image segmentation.

[1]  Rangachar Kasturi,et al.  Machine vision , 1995 .

[2]  Moncef Gabbouj,et al.  Fast watershed algorithms: analysis and extensions , 1994, Electronic Imaging.

[3]  Naokazu Yokoya,et al.  Image segmentation schema for low-level computer vision , 1981, Pattern Recognit..

[4]  Azriel Rosenfeld,et al.  Digital Picture Processing, Volume 1 , 1982 .

[5]  C. L. Liu.  Elements of Discrete Mathematics , 1985 .

[6]  Alan L. Yuille,et al.  Region Competition: Unifying Snakes, Region Growing, and Bayes/MDL for Multiband Image Segmentation , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Shigeki Yokoi,et al.  Basics of algorithms for processing three-dimensional digitized pictures , 1986, Systems and Computers in Japan.

[8]  Peter E. Undrill,et al.  Comparison of 3D split-and-merge segmentation with direct MRI determination of cerebral ventricule volume , 1996, Medical Imaging.

[9]  William E. Higgins,et al.  Extraction and analysis of large vascular networks in 3D micro-CT images , 1999, Medical Imaging.

[10]  William E. Higgins,et al.  Multi-generational analysis and visualization of the vascular tree in 3D micro-CT images , 2002, Comput. Biol. Medicine.

[11]  Theodosios Pavlidis,et al.  Integrating Region Growing and Edge Detection , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  William A. Barrett,et al.  Image segmentation using globally optimal growth in three dimensions with an adaptive feature set , 1994, Other Conferences.

[13]  W.E. Higgins,et al.  Extraction of the hepatic vasculature in rats using 3-D micro-CT images , 2000, IEEE Transactions on Medical Imaging.

[14]  Hao Jiang,et al.  Comparative performance evaluation of segmentation methods based on region growing and division , 1993 .

[15]  E L Ritman,et al.  Extraction of left-ventricular chamber from 3-D CT images of the heart. , 1990, IEEE transactions on medical imaging.

[16]  Azriel Rosenfeld,et al.  Digital Picture Processing , 1976 .

[17]  W.E. Higgins,et al.  System for analyzing high-resolution three-dimensional coronary angiograms , 1996, IEEE Trans. Medical Imaging.

[18]  Andrew Mehnert,et al.  An improved seeded region growing algorithm , 1997, Pattern Recognit. Lett..

[19]  Josef Kittler,et al.  Region growing: a new approach , 1998, IEEE Trans. Image Process..

[20]  Xiaobo Li,et al.  Adaptive image region-growing , 1994, IEEE Trans. Image Process..

[21]  William E. Higgins,et al.  Toward reliable multigenerational analysis of anatomical trees in 3D high-resolution CT images , 2003, SPIE Medical Imaging.

[22]  Jianping Fan,et al.  Automatic image segmentation by integrating color-edge extraction and seeded region growing , 2001, IEEE Trans. Image Process..

[23]  Rolf Adams,et al.  Seeded Region Growing , 1994, IEEE Trans. Pattern Anal. Mach. Intell..