Hough Transform Implementation by using Parallel Paradigms

Many problems in the field of computer simulation of systems in science and engineering present potential for parallel implementations through one of the three major paradigms of processor farming, geometric parallelism, and algorithmic parallelism. Processor scheduling determines which processes are assigned to specific processors and when. Static process scheduling techniques are successfully used to exploit algorithmic and geometric parallelism, whilst dynamic process scheduling is better suited to dealing with the independent processes inherent in the process farming paradigm. This paper considers the application of multi-computers to a class of problems exhibiting spatial data characteristic of the geometric paradigm. However, by using processor farming paradigm in conjunction with geometric decomposition, a dynamic scheduling technique is developed and compared by varying the network sizes and workload. The specific problem chosen for the investigation is the Hough transform for line detection.