3. Multi-circle Detection on Images

Hough transform (HT) represents the most common method for circle detection, exhibiting robustness and parallel processing. However, HT adversely demands a considerable computational load and large storage. Alternative approaches may include heuristic methods with iterative optimization procedures for detecting multiple circles. In this chapter a new circle detector for image processing is presented. In the approach, the detection process is therefore assumed as a multi-modal problem which allows multiple circle detection through only one optimization procedure. The algorithm uses a combination of three non-collinear edge points as parameters to determine circles candidates. A matching function (nectar amount) determines if such circle candidates (bee-food-sources) are actually present in the image. Guided by the values of such matching function, the set of encoded candidate circles are evolved through the Artificial Bee Colony (ABC) algorithm so the best candidate (global optimum) can be fitted into an actual circle within the edge-only image. An analysis of the incorporated exhausted-sources memory is executed in order to identify potential local optima i.e. other circles. The overall approach yields a fast multiple-circle detector that locates circular shapes delivering sub-pixel accuracy despite complicated conditions such as partial occluded circles, arc segments or noisy images.