Parallel Feature Extraction - High-Throughput Image Reconstruction and Analysis - page 158

These algorithms were examined from a parallel processing viewpoint, to high-
light the computation and communication requirements. These factors affect the
way domain decomposition is performed.
Our results demonstrate a dramatic speedup in image processing tasks on a
parallel platform. This will be essential in processing the enormous datasets that
are being gathered, ranging in trillions of voxels.
The main message of this chapter is to encourage researchers in image pro-
cessing to write parallel programs to take advantage of increasing computational
resources in order to tackle the problem of dealing with large datasets. This re-
quires a paradigm shift in the field, which is an investment that pays off through
increased productivity.

References

[1] R. Adiga, et al., ''Blue gene/l torus interconnection network,'' IBM J. Research and De-
velopment , 49(2), 2005.
[2] M.B. Alp and Y. Neuvo, ''3-dimensional median filters for image sequence pro-
cessing,'' IEEE International Conference on Acoustics Speech and Signal Processing ,
pp. 2917--2920, 1991.
[3] A. Apostol and F. Peyrin, ''Connectivity analysis in very large 3d microtomographic
images,'' IEEE Trans. on Nuclear Science , 54(1):167--172, 2007.
[4] S. Benini, E. Boniotti, R. Leonardi, and A. Signoroni, ''Interactive segmentation of
biomedical images and volumes using connected operators,'' International Conference
on Image Processing , volume 3, pp. 452--455, 2000.
[5] N. Blow, ''Following the wires,'' Nature Methods , 4(11):975--980, November 2007.
[6] W.W. Boles, M. Kanefsky, and M. Simaan, ''Recursive two-dimensional median filtering
algorithms for fast image root extraction,'' IEEE Transactions on Circuits and Systems ,
35(10):1323--1326, 1988.
[7] H. Cai, et al., ''Repulsive force based snake model to segment and track neuronal axons
in 3d microscopy image stacks,'' Neuroimage , 32(4):1608--1620, 2006.
[8] H. Cai, et al., ''Use mean shift to track neuronal axons in 3d,'' Life Science Systems and
Applications Workshop , pp. 1--2, 2006.
[9] J. Canny, ''A computational approach to edge detection,'' IEEE Transactions on Pattern
Analysis and Machine Intelligence , 8(6):679--698, 1986.
[10] W. Denk and H. Horstmann, ''Serial block-face scanning electron miscroscopy to recon-
struct three-dimensional tissue nanostructure,'' PLOS Biology , 2(11), 2004.
[11] H. Dodt, et al., ''Ultramicroscopy: three-dimensional visualization of neuronal networks
in the whole mouse brain,'' Nature Methods , 4(11):331--336, April 2007.
[12] H. Edelsbrunner and E. P. Mucke, ''Three-dimensional alpha shapes,'' ACM Trans.
Graphics , 13:43--72, 1994.
[13] E. W. Evans, et al., ''Automatic and effective multi-dimensional parallelisation of struc-
tured mesh based codes,'' Parallel Computing , 26(6):677--703, 2000.
[14] M. W. Fahmy and A. H. Namini, ''A survey of parallel nonlinear dynamic analysis
methodologies,'' Computers and Structures , 53(4):1033--1043, 1994.

[15] J. C. Fiala, ''Reconstruct: a free editor for serial section microscopy,'' Journal of Mi-

croscopy , 218:52--61, 2005.

[16] A. R. Forouzan and B. N. Araabi, ''Iterative median filtering for restoration of images

with impulsive noise,'' Proceedings of the IEEE International Conference on Circuits,
Electronics and Systems , volume 1, pp. 232--235, 2003.