Plaque measurement from intra-oral video frames
Stefan Großkopf, Peter J. Neugebauer, Hagen Schumann · 1997
In this paper we present a system for computer assisted evaluation of intra-oral images, in order to measure colored plaque. This system is robust to process images taken under everyday conditions. It implements an image processing pipeline which consists of three processes: specular reflection suppression, tooth contour detection by B-snakes, and plaque classification by discriminate analysis. The result is a quotient of the area of the measured plaque and the area of the tooth. We discuss the applied techniques and examine the reproducibility of the results. In order to enhance the contours of the tooth, to suppress specular-reflections, and to detect plaque pixels, our system makes use of three color transformations (HSV, CIE-Luv, Discrete Karhunen Loeve Transformation). In order to calculate the external energy of the B-snake, we have developed a new method for edge enhancement, based on a modified distance transformation. Finally, we present the interaction techniques of the system which enable the user to fully control the quality of each individual process.