Level Set-Based Fast Multi-phase Graph Partitioning Active Contours Using Constant Memory
We present multi-phase FastGPAC that extends our dramatic improvement of memory requirements and computational complexity on two-class GPAC, into multi-class image segmentation. Graph partitioning active contours GPAC is a recently introduced approach that elegantly embeds the graph-based image segmentation problem within a continuous level set-based active contour paradigm. However, GPAC similar to many other graph-based approaches has quadratic memory requirements. For example, a 1024x1024 grayscale image requires over one terabyte of working memory. Approximations of GPAC reduce this complexity by trading off accuracy. Our FastGPAC approach implements an exact GPAC segmentation using constant memory requirement of few kilobytes and enables use of GPAC on high throughput and high resolution images. Extension to multi-phase enables segmention of multiple regions of interest with different appearances. We have successfully applied FastGPAC on different types of images, particularly on biomedical images of different modalities. Experiments on the various image types, natural, biomedical etc. show promising segmentation results with substantially reduced computational requirements.
Unable to display preview. Download preview PDF.
- 1.Bertelli, L.: GPAC implementation, http://vision.ece.ucsb.edu/~lbertelli/soft_GPAC.html
- 4.Bunyak, F., Palaniappan, K.: Efficient segmentation using feature-based graph partitioning active contours. In: Int’l Conf. Computer Vision (September 2009)Google Scholar
- 10.Malcolm, J., Rathi, Y., Tannenbaum, A.: A graph cut approach to image segmentation in tensor space. In: IEEE Conf. Comp. Vision and Patt. Rec., pp. 1–8 (2007)Google Scholar
- 11.Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: Proc. 8th Int’l Conf. Computer Vision, July 2001, vol. 2, pp. 416–423 (2001)Google Scholar
- 12.Paragios, N., Deriche, R.: Geodesic active regions for motion estimation and tracking. In: Proc. Int. Conf. Computer Vision, Corfu, Greece, pp. 688–694 (1999)Google Scholar
- 15.Sethian, J.: Level Set Methods and Fast Marching Methods: Evolving Interfaces in Computational Geometry. In: Fluid Mechanics, Computer Vision, and Materials Science. Cambridge University Press, Cambridge (1999)Google Scholar
- 17.Sumengen, B., Manjunath, B.S.: Graph partitioning active contours (GPAC) for image segmentation. IEEE Trans. Patt. Anal. Mach. Intell., 509–521 (April 2006)Google Scholar
- 20.Wang, X., He, W., Metaxas, D., Matthew, R., White, E.: Cell segmentation and tracking using texture-adaptive snakes. In: Proc. IEEE Int. Symp. Biomedical Imaging, Washington, DC, April 2007, pp. 101–104 (2007)Google Scholar