Dental plaque quantification using FCM-based classification in HSI color space

Abstract

Detection and quantification of dental plaque is very crucial to both patients and their clinicians. However, traditional dental plaque indices used to measure the dental plaque are subjective, semi-quantitative because the measurements rely primarily on the clinician's ability to demarcate or score areas of disclosed plaque using visual examination. To overcome the shortcomings of traditional indices, this paper presented an approach for quantifying the dental plaque automatically by using fuzzy c-means (FCM) clustering algorithm in HSI (hue, saturation, intensity) color space. The approach was applied to a clinical database consisting of 195 objects. The experimental results shown that this approach provided more objective, and quantitative measurements of dental plaque compared with those of indexed by traditional dental plaque indices.