Optimal geometric algorithms for digitized images on fixed-size linear arrays and scan-line arrays

SummaryLinear arrays are characterized by a small communication bandwidth and a large communication diameter rendering them unsuited to the implementation of global computations. This paper presents efficient data movement and partitioning techniques to overcome several shortcomings of linear arrays. These techniques are used to derive optimal parallel algorithms for several geometric problems onn×n images using a fixed-size linear array withp processors, where 1≤p≤n.O(n2/p) time solutions are presented for labeling connected image regions, computing the convex hull of each region, and computing nearest neighbors. Consequently, a linear array withn processors can solve several image problems inO(n) time which is the same time taken by a two dimensional mesh-connected computer withn2 processors. Limitations of linear arrays are analyzed by presenting a class of image problems which can be solved sequentially inO(n)2) time, but require Ω(n2) time on a linear array, irrespective of the number of processors used and the partitioning of the input image among the processors. An alternate communication-efficient fixed-size organization withp processors is proposed to solve such problems inO(n2/p) time, for 1≤p≤n.

[1]  Russ Miller,et al.  Geometric Algorithms for Digitized Pictures on a Mesh-Connected Computer , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Jeffrey D Ullma.  Computational Aspects of VLSI , 1984 .

[3]  Viktor K. Prasanna,et al.  Information Transfer in Distributed Computing with Applications to VLSI , 1984, JACM.

[4]  Eli Gafni,et al.  Sorting in constant number of row and column phases on a mesh , 2005, Algorithmica.

[5]  Azriel Rosenfeld,et al.  Parallel Image Processing Using Cellular Arrays , 1983, Computer.

[6]  H. T. Kung.  Memory requirements for balanced computer architectures , 1986, ISCA '86.

[7]  Viktor K. Prasanna,et al.  Fast Image Labeling Using Local Operators on Mesh-Connected Computers , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Gérard M. Baudet,et al.  Optimal Sorting Algorithms for Parallel Computers , 1978, IEEE Transactions on Computers.

[9]  Chul E. Kim.  On the Cellular Convexity of Complexes , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  KSHITIJ A. DOSHI,et al.  Optimal Graph Algorithms on a Fixed-Size Linear Array , 1987, IEEE Transactions on Computers.

[11]  Viktor K. Prasanna,et al.  Parallel Geometric Algorithms for Digitized Pictures on Mesh of Trees , 1986, ICPP.

[12]  Allan L. Fisher.  Scan line array processors for image computation , 1986, ISCA 1986.

[13]  I. V. Ramakrishnan,et al.  Modular Matrix Multiplication on a Linear Array , 1984, IEEE Transactions on Computers.

[14]  Sartaj Sahni,et al.  Finding Connected Components and Connected Ones on a Mesh-Connected Parallel Computer , 1980, SIAM J. Comput..

[15]  Michael Ian Shamos,et al.  Computational geometry: an introduction , 1985 .

[16]  Ronald L. Graham,et al.  An Efficient Algorithm for Determining the Convex Hull of a Finite Planar Set , 1972, Inf. Process. Lett..

[17]  H. M. Alnuweiri,et al.  Optimal image computations on reduced VLSI architectures , 1989 .

[18]  Alfred V. Aho,et al.  The Design and Analysis of Computer Algorithms , 1974 .

[19]  Viktor K. Prasanna,et al.  Processor-time optimal parallel algorithms for digitized images on mesh-connected processor arrays , 1991, Algorithmica.

[20]  Sartaj Sahni,et al.  Data broadcasting in SIMD computers , 1981, IEEE Transactions on Computers.

[21]  Russ Miller,et al.  Data Movement Techniques for the Pyramid Computer , 1987, SIAM J. Comput..

[22]  H. T. Kung,et al.  Mapping image processing operations onto a linear systolic machine , 1986, Distributed Computing.

[23]  H. T. Kung.  Memory requirements for balanced computer architectures , 1986, ISCA '86.