In defense of the Hough transform

The Hough transform has been a widely used technique Sor geometric primitive extraction. However recently a new family of technique, namely the optimization based one, such as the genetic algorithm [1], the taboo search algorithm [2], rite algorithm based on random samples of minimum subset [3], claimed their superiority over the Hough transform. In this paper, based on a reasonable criterion, namely the expected number of random samples of minimum subset for a single successful primitive extraction, the performance of the two families of technique is compared. We show that the Hough transform generally outperforms optimization based techniques. In particular, based on a large number of and experiments with real images, we show that with a comparable performance, the randomized Hough transform (RHT)[5], a representative of Hough techniques, is about twice as fast as the random sample consensus (RANSAC)[8], a representative of optimization based techniques, in both line extraction and circle extraction.