Abstrakt
The paper presents a new method for separation of overlapping dental objects allowing more precise analysis of the dental arch using image processing methods and computational intelligence. The methodological part of the paper is devoted to the separation of dental objects using the watershed and region growing methods applied to denoised images of dental bodies.
The main part of the paper is devoted to analysis of image components and to the use of normal vectors to image segments boundaries to detect separate dental arch components in the complex environment of overlapping bodies. Experimental part of the paper is devoted to the application of the proposed method to the processing of real images of dental plaster casts acquired with the different illumination.
Results include the proposed general algorithm for image components separation allowing further evaluation of dental arch parameters during the operation to allow the efficient treatment in the clinical environment.