Study on Methods for Computer-aided Tooth Shade Determination

Computer-aided tooth shade determination of the natural tooth is an emerging application area which is still in development. Selecting the correct porcelain type is the key to repair teeth successfully. But the color and shade determined by human observers could not achieve a satisfied result because of the effect of the surrounding light and the limit of human eyes. And the computer-aided tooth color selection methods can resolve this problem. In this paper, principal component analysis (PCA) and two-dimensional principal component analysis (2DPCA) are used to extract the features. And K nearest neighbor (KNN), support vector machine (SVM) and probabilistic neural network (PNN) are used as classifiers for matching the porcelain type. Finally, the experimental results of these methods are compared. It illuminates that the methods presented in this paper are effective on developing the computer-aided tooth shade determination system for producing the porcelain tooth.