Nilanjan Ray

Professor
Department of Computing Science
University of Alberta, Canada


Automating Active Contours

Active contours or snakes are excellent tools to segment blob-shaped objects, which are not necessarily convex. However, active contours require seeds as a way of initializing the segmentation process. We have worked on automated seed placement, then active contour-based object boundary delineation and verification of segmentations to completely automate active contour-based segmentations.

Related Publications
  • B. Saha, N. Ray. H. Zhang, “Automating snakes for multiple objects detection,” ACCV 2010, Part III, LNCS 6494, pp.39-51, 2011.
  • B. Saha, N. Ray, and H. Zhang, “Snake validation: A PCA-based outlier detection method,” IEEE Signal Processing Letters, vol.16, pp.549-552, 2009.
  • B. Saha, N. Ray, and H. Zhang, “Computing oil sand particle size distribution by snake-PCA algorithm,” Proceedings of IEEE ICASSP 2008, pp.977–980.

Gradient Vector Flow-based Active Contours

During my PhD program, I worked on gradient vector flow (GVF)-based active contours/snakes. In this context, my most significant contribution is to use Dirichlet boundary condition with a partial differential equation to compute GVF. This helped to delineate object boundaries by active contours more accurately. This contribution was recognized as the best student paper prize at IEEE ICIP in 2002.

Related Publications
  • N. Ray and S.T. Acton, “Motion gradient vector flow: An external force for tracking rolling leukocytes with shape and size constrained active contour,” IEEE Trans. Medical Imaging, vol. 23, no. 12, pp. 1466-1478, 2004.
  • N. Ray, S.T. Acton, T. Altes, E.E. de Lange and J.R. Brookeman, “Merging parametric active contours within homogeneous image regions for MRI-based lung segmentation,” IEEE Trans. Medical Imaging, vol.22, no. 1, pp.189-199, 2003.
  • N. Ray and S.T. Acton, “Tracking rolling leukocytes with motion gradient vector flow”, accepted in Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA, November 9-12, 2003.
  • N. Ray and S.T. Acton, “Tracking fast-rolling leukocytes in vivo with active contours,” Proceedings of IEEE ICIP 2002, vol.3, pp.165-168. Won best student paper award from IBM Signal Processing Society.
  • N. Ray, S.T. Acton, K.F. Ley, “Tracking leukocytes in vivo with shape and size constrained active contours,” IEEE Trans. Medical Imaging, special issue on Image Analysis in Drug Discovery and Clinical Trials, vol.21, no. 10, pp. 1222-1235, 2002.
  • N. Ray, S.T. Acton, T. Altes, E.E. de Lange “MRI ventilation analysis by merging parametric active contours,” Proceedings of IEEE ICIP 2001, pp.861-864.

Active Contours: Miscellaneous

It if fair to say that I have started my research career working with active contours. Some of my earliest publications on this topic are listed below.

Related Publications
  • S. Sahoo, N. Ray and S.T. Acton, “Rolling leukocyte detection based on teardrop shape and the gradient inverse coefficient of variation,” International Conference on Medical Information Visualisation - BioMedical Visualisation 2006. MediVis 2006, pp. 29-33, 5-7 July 2006.
  • G. Dong, N. Ray and S.T. Acton, “Intravital leukocyte detection using the gradient inverse coefficient of variation,” IEEE Transactions on Medical Imaging, Vol.24, no.7, pp. 910-924, July 2005.
  • A.K. Chattopadhyay, N. Ray and S.T. Acton, “Universality in the merging dynamics of parametric active contours: a study in MRI based lung segmentation,” New Journal of Physics, vol. 7, pp. 148-159, 2005.
  • S.T. Acton and N. Ray, “Detection and tracking of rolling leukocytes from intravital microscopy,” invited paper in 2004 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Arlington, Virginia, April 15- 18, 2004.
  • N. Ray and S.T. Acton, “Active contours for cell tracking,” In the Proceedings of Southwest Symposium on Image Analysis and Interpretation, sponsored by the IEEE computer society and IEEE Signal Processing Society, Santa Fe, New Mexico, April 7-9, 2002.
  • N. Ray, J. Havlicek, S.T. Acton and M. Pattichis, “Active contour segmentation guided by AM-FM dominant component analysis,” Proceedings of IEEE ICIP 2001, pp.78-81.
  • N. Ray, B. Chanda and J. Das, “A fast and flexible multiresolution snake with a definite termination criterion,” Pattern Recognition, vol. 34, pp.1483-1490, 2001.
  • N. Ray and S.T. Acton, “Image segmentation by curve evolution with clustering,” In the proceedings of 34th Asilomar conference on Signals, Systems and Computers, Pacific Grove, CA, pp.495-498, Oct 29-Nov.1, 2000.