Title :
Parallel Processing Approaches to Image Correlation
Author :
Siegel, Leah J. ; Siegel, Howard Jay ; Feather, Arthur E.
Author_Institution :
School of Electrical Engineering, Purdue University
fDate :
3/1/1982 12:00:00 AM
Keywords :
Algorithms; Image correlation is representative of a wide variety of window-based image processing tasks. The way in which multimicroprocessor systems (e.g., PASM) can use SIMD parallelism to perform image correlation is examined. Two fundamental algorithm strategies are explored. In one approach, all of the data that will be needed in a processor are transferred to the processor and operated on there. In the other, each processor performs all possible operations on its local data, generating partial result; PASM; SIMD machines; convolution; image correlation; image processing; multimicroprocessor systems; parallel processing; parallel programming; pattern recognition; Algorithm design and analysis; Convolution; Feathers; Image edge detection; Image processing; Image registration; Multiprocessor interconnection networks; Parallel processing; Parallel programming; Pattern recognition; Algorithms; Image correlation is representative of a wide variety of window-based image processing tasks. The way in which multimicroprocessor systems (e.g., PASM) can use SIMD parallelism to perform image correlation is examined. Two fundamental algorithm strategies are explored. In one approach, all of the data that will be needed in a processor are transferred to the processor and operated on there. In the other, each processor performs all possible operations on its local data, generating partial result; PASM; SIMD machines; convolution; image correlation; image processing; multimicroprocessor systems; parallel processing; parallel programming; pattern recognition;
Journal_Title :
Computers, IEEE Transactions on
DOI :
10.1109/TC.1982.1675976