Improving the Detection and Localization of Anatomical Landmark Points in Infrared Images Using Symmetry and Region Specific Constraints

This paper presents a new approach to detect and localize anatomical landmark points on clinical infrared images. It is based on a curvature analysis of contours and takes advantage of the symmetry of body regions to improve the localization of anatomical landmarks, based on region specific constraints. Better localization of anatomical landmarks is a key step in the registration and comparison of images over time, between patients and images from bilateral regions. It is also an important step in the design of automated thermal infrared imaging anomaly detection architecture.