Detecting Smooth Surface Dental Caries in Frontal Teeth Using Image Processing

Abstract

Dental caries is one of the most common tooth diseases in the world which affects people of all ages. In this study, we developed a model that detects and locates smooth surface carious regions in frontal teeth images using Support Vector Machine and Decision Tree in MATLAB R2018a Classification Learner. A total of 45 images with smooth surface dental caries were used which consists of 30 training images and 15 images for testing and validation. Images are pre-processed using Histogram Equalization and are segmented further into 10x10 blocks where the set of color and texture features such as Intensity, Gradient, Hue, Saturation, and Entropy were extracted. The study showed significant results with an accuracy of 84% and 78% using Decision Tree and SVM respectively which proved the effectivity of the use of image processing techniques on classification and location of dental caries.