Automatic Landmark Detection through Circular Hough Transform in Cephalometric X-rays

In this paper, a knowledge based algorithm is proposed to detect cephalometric landmarks: Porion (Po), Sella (S), Menton (Me), Pogonion (Pg) and Gnathion (Gn). Our algorithm consists of two main steps: (1) To clarify the image which is frequently used to determine the method of treatment in orthodontics and obtained from the plain X-ray Adaptive Histogram Equalisation (AHE) is applied, (2) To locate the cephalometric landmarks automatically on the processed image, the Circular Hough Transform method is used. The system was tried on 7 cephalometric images and our algorithm accurately locates these 5 cephalometric landmarks.