Circular object detection with mathematical morphology and geometric properties

A new method using mathematical morphology and geometric properties is proposed for circular object detection. Firstly, mathematical morphology operators are used to detect edges and the edge points are traced to obtain series of sequential sets. Next, according to the edge point sets, the geometric property parameters are calculated for each object. Then, objects with the feature parameters meeting certain conditions are identified as circular objects. The proposed method is described in detail, and comparison experiments with the randomized Hough transform (RHT) have been made in the two ways of detecting precision and detecting speed. Both synthetic and real images have been tested by the proposed method and the experimental results show that the new method is efficient.