Mobility estimation and analysis in medical x-ray images using corners and faces contours detection

This paper describes a new segmentation approach used for detecting the location and the orientation of the cervical spinal column in medical x-ray images. A first preprocessing step consists on determining a global polygonal region for each vertebra. After this, we propose two different methods to calculate vertebrae orientation. The first method is based on the four faces detection of each vertebra contour when the second is essentially based on automatic corners localization. A specific goal of the proposed application is to create an efficient semi-automated method of identifying the overall spine curvature and the orientation angles of each vertebra. The final goal is to determine vertebrae motion induced by their movement between two or several positions.