论文信息 - Parallel Contour Matching and 3D Partial Retrieval in Bio-Image Database

Parallel Contour Matching and 3D Partial Retrieval in Bio-Image Database

Parallel 3D reconstruction and partial retrieval from 2D image slices based on object contour structure are introduced. In this paper, 2D images are segmented into object contours. Related object contours on adjacent image slices are linked together to form the 3D component. Parallel algorithms are designed and implemented for distributing contour matching and partial retrieval tasks among multiple processors. The methods have been implemented in MPI on an SGI Origin 2000 machine. The experimental results show good speedups for sequential object matching and partial 3D component retrieval.

[1] D. Burr,et al. Mach bands are phase dependent , 1986, Nature.

[2] Yi Pan,et al. Parallel bandwidth characteristics calculations for thin avalanche photodiodes on a SGI Origin 2000 supercomputer , 2004, Concurr. Pract. Exp..

[3] Wen-Yen Wu,et al. Two-dimensional object recognition through two-stage string matching , 1999, IEEE Trans. Image Process..

[4] Peter Kovesi,et al. Image Features from Phase Congruency , 1995 .

[5] Michael J. Quinn,et al. Parallel programming in C with MPI and OpenMP , 2003 .

[6] Robyn A. Owens,et al. Feature detection from local energy , 1987, Pattern Recognit. Lett..

[7] Yi Pan,et al. Efficient parallel algorithms for distance maps of 2D binary images using an optical bus , 2002, IEEE Trans. Syst. Man Cybern. Part A.

[8] Remco C. Veltkamp,et al. State of the Art in Shape Matching , 2001, Principles of Visual Information Retrieval.