Application of the Laplacian Pyramid Decomposition to the Enhancement of Digital Dental Radiographic Images for the Automatic Person Identification

The paper provides some experimental results on medical images enhancement, namely digital dental radiographic images of entire dentition — pantomograms. This problem is a first step in the process of automatic identification of persons basing on the mentioned kind of images. The most crucial task is the emphasizing of some characteristics, e.g. shapes of the teeth and dental fillings. These features are widely used as an input for the methods of automatic dental identification. In the paper the Laplacian pyramid-based image enhancement approach is utilized. This method has been successfully used for other radiographic images — mammograms and computed tomograms (CTs). Exemplary methods of uniform and non-uniform Laplacian pyramid enhancement are presented along with their influence on a typical image.