Computational Science

COMPUTATIONAL SCIENCE BY BRUCE G. BUCHANAN Department of Computer Science University of Pittsburgh Pittsburgh, Pa. " To segment image data means to separate important parts of the image from the background. Fingerprints are often low-contrast, smudged, and noisy images, and thus offer a good test of segmentation algorithms. A composite of two methods is proposed that gives better performance than either alone. B.M. Mehtre, B. Chatterjee, “Segmentation of fingerprint images—a compo

Written byBruce Buchanan

| 2 min read

Save for Later

Listen with Speechify

0:00

2:00

BY BRUCE G. BUCHANAN
Department of Computer Science
University of Pittsburgh
Pittsburgh, Pa.

" To segment image data means to separate important parts of the image from the background. Fingerprints are often low-contrast, smudged, and noisy images, and thus offer a good test of segmentation algorithms. A composite of two methods is proposed that gives better performance than either alone.

B.M. Mehtre, B. Chatterjee, “Segmentation of fingerprint images—a composite method,” Pattern Recognition, 22(4), 381-5, 1989. (CMC Limited, Secunderabad, India, and Indian Institute of Technology, Kharagpur)

Five different types of data communication are compared by each of six different models of parallel architecture. Hypercubes seem to perform best on most operations with large amounts of data.

Y. Sand, M.H. Schultz, “Data communication in parallel architectures,” Parallel Computing, 11, 13 1-50, 4 August 1989. (Research Institute for Advanced Computer Science, NASA Ames, Moffett Field, Calif.)

With M independent parallel processors, the work ...

Interested in reading more?

Become a Member of

Receive full access to digital editions of The Scientist, as well as TS Digest, feature stories, more than 35 years of archives, and much more!

Join for free today

Already a member?