Object Detection By K-connected Seed Competition

The notion of "strength of connectedness" between pixels has been successfully used in image segmentation. We present an extension to these works, which can considerably increase the efficiency of object definition tasks. A set of pixels is said a k-connected component with respect to a seed pixel when the strength of connectedness of any pixel in that set with respect to the seed is higher than or equal to a threshold. While the previous approaches either assume no competition with a single threshold for all seeds or eliminate the threshold for seed competition, we found that seed competition with different thresholds can reduce the number of seeds and the need for user interaction during segmentation. We also propose automatic and user-friendly interactive methods for determining the thresholds. The improvements are demonstrated through several segmentation experiments involving medical images. © 2005 IEEE.200597104Beucher, S., Meyer, F., The morphological approach to segmentation: The watershed transformation (1993) Mathematical Morphology in Image Processing, pp. 433-481. , chapter 12, Marcel DekkerFalcão, A.X., Bergo, F.P.G., Interactive volume segmentation with differential image foresting transforms (2004) IEEE Trans. on Medical Imaging, 23 (9), pp. 1100-1108A. X. Falcão, F. P. G. Bergo, and P. A. V. Miranda. Image segmentation by tree pruning. In Proc. of the XV11 Brazillian Symposium on Computer Graphics and Image Processing, pages 65-71. IEEE, Oct 2004Falcão, A.X., Costa, L.F., da Cunha, B.S., Multiscale skeletons by image foresting transform and its applications to neuromorphometry (2002) Pattern Recognition, 35 (7), pp. 1571-1582Falcão, A.X., Stolfi, J., Lotufo, R.A., The image foresting transform: Theory, algorithms, and applications (2004) IEEE Trans. on Pattern Analysis and Machine Intelligence, 26 (1), pp. 19-29Falcão, A.X., Udupa, J.K., Miyazawa, F.K., An ultrafast user-steered image segmentation paradigm: Live-wireon-the-fly (2000) IEEE Trans. on Medical Imaging, 19 (1), pp. 55-62Falcão, A.X., Udupa, J.K., Samarasekera, S., Sharma, S., Hirsch, B.E., Lotufo, R.A., User-steered image segmentation paradigms: Live-wire and live-lane (1998) Graphical Models and Image Processing, 60 (4), pp. 233-260. , JulFelkel, P., Bruckschwaiger, M., Wegenkittl, R., Implementation and complexity of the watershed-from-markers algorithm computed as a minimal cost forest (2001) Computer Graphics Forum (EUROGRAPHICS), 20 (3). , C 26-35Grau, V., Mewes, A.U.J., Alcaniz, M., Kikinis, R., Warfield, S.K., Improved watershed transform for medical image segmentation using prior information (2004) IEEE Trans. on Medical Imaging, 23 (4), pp. 447-458. , AprHerman, G.T., Carvalho, B.M., Multiseeded segmentation using fuzzy connectedness (2001) IEEE Trans. on Pattern Analysis and Machine Intelligence, 23 (5), pp. 460-474Lei, T., Udupa, J.K., Saha, P.K., Odhner, D., Artery-vein separation via MRA - An image processing approach (2001) IEEE Trans. on Medical Imaging, 20 (8)Lotufo, R.A., Falcão, A.X., The ordered queue and the optimality of the watershed approaches (2000) Mathematical Morphology and its Applications to Image and Signal Processing, 18, pp. 341-350. , Kluwer, JunMeijster, A., Wilkinson, M.H.F., A comparison of algorithms tor connected set openings and closings (2002) IEEE Trans. on Pattern Analysis and Machine Intelligence, 24 (4), p. 484494. , AprMoonis, G., Liu, J., Udupa, J.K., Hackney, D.B., Estimation of tumor volume with fuzzy-connectedness segmentation of MR images (2002) American Journal of Neuroradiology, 23, pp. 356-363. , MarNguyen, H.T., Worring, M., van den Boomgaard, R., Watersnakes: Energy-driven watershed segmentation (2003) IEEE Trans. on Pattern Analysis and Machine Intelligence, 25 (3), pp. 330-342. , MarSaha, P.K., Udupa, J.K., Fuzzy connected object delineation: Axiomatic path strength definition and the case of multiple seeds (2001) Computer Vision and Image Understanding, 83, pp. 275-295Saha, P.K., Udupa, J.K., Relative fuzzy connectedness among multiple objects: Theory, algorithms, and applications in image segmentation (2001) Computer Vision and Image Understanding, 82, pp. 42-56Saha, P.K., Udupa, J.K., Odhner, D., Scale-based fuzzy connected image segmentation: Theory, algorithms, and validation (2000) Computer Vision and Image Understanding, 77 (2), pp. 145-174Torres, R.S., Falcão, A.X., Costa, L.F., A graph-based approach for multiscale shape analysis (2004) Pattern Recognition, 37 (6), pp. 1163-1174Udupa, J.K., Samarasekera, S., Fuzzy connectedness and object definition: Theory, algorithms, and applications in image segmentation (1996) Graphical Models and Image Processing, 58, pp. 246-261Vincent, L., Soille, P., Watersheds in digital spaces: An efficient algorithm based on immersion simulations (1991) IEEE Trans. on Pattern Analysis and Machine Intelligence, 13 (6). , Ju