Abstract
The paper presents a new method for detection of orthodontic bodies, their separation, enhancement and analysis using their plaster casts models illuminated by different light sources. The proposed method is based upon the processing of the set of two-dimensional images acquired in different illumination conditions using digital de-nosing and gradient image enhancement methods in the preliminary stage.
The region growing method forms the main part of the paper with its results compared to the distance and watershed transforms. Mathematical methods studied include (i) selected computational tools for multi-dimensional analysis in the orthodontic treatment and (ii) segmentation methods based upon illuminated objects allowing the application of the region growing method for image regions classification The proposed set of algorithms is then used for orthodontic bodies segmentation and for comparison of results achieved.
All methods are applied in orthodontics for segmentation of specifie objects to allow the efficien treatment and to simplify the organization of further analysis of treatment results in the electronic form accessible for all specialists in the given area.