Intelligent Hough Transform With Jaya to Detect the Diameter of Red-Hot Circular Workpiece

Diameter detection plays an important role in the production of circular workpieces. It is very difficult to obtain the accurate measurement of diameter when the circular workpiece is red-hot because of the existence of lots of noise. Although Hough transform (HT) has many advantages for diameter detection of circular workpieces, it has still suffered from some serious problems, which include the requirements of a large amount of computation and memory occupancy. To address these problems, we propose an intelligent Hough transform method with Jaya (IHTJ). The key points are as follows. We analyze the problem of diameter detection for red-hot circular workpieces, which is essentially the problem of ellipse fitting. Then the problem of ellipse fitting with HT is converted into searching optimal solution in parameter space, and we construct the fitness function based on the principle of ellipse fitting with HT. In order to fit the ellipse accurately and rapidly, we introduce Jaya to search the optimal ellipse parameters in parameter space at last, and the computation burden and memory occupancy of HT are greatly reduced. Compared with direct least-square (DLS), randomized Hough transform (RHT) and random sample consistency (RANSAC), IHTJ can fit the ellipse rapidly while the advantages of strong robustness and high accuracy of HT are retained. Some simulations and practical experiments are carried out to verify the effectiveness of IHTJ.