A comparative study of efficient generalised Hough transform techniques

The generalised Hough transform (GHT) is useful for detecting or locating translated two-dimensional objects. However, a weakness of the GHT is its storage requirements and hence the increased computational complexity resulting from the four-dimensional parameter space. In this paper, we present the results of our work which involves investigation of the performance of several efficient GHT techniques including an extension of Thomas's rotation-invariant algorithm. It is shown that our extension of Thomas's algorithm has very low memory requirements and computational complexity, and produces the best results in various tests. (C) 1999 Elsevier Science B.V. All rights reserved.