A Medical Reagent Grade Judgment System Based on Color Intelligent Recognition

Abstract

Dental caries is a common bacterial disease, as well as early detection such as caries activity test (also known as Cariostat test) is essential for caries control. The Cariostat test is used to determine the risk of caries by comparing the indicator color of culture medium in vitro with the standard color card. The purpose of this paper was to design a machine vision aided automatic color recognition system for measuring the Cariostat scores associated etiologically with dental caries. By calculating a widely color characteristics of each class of culture medium images, a standard color card representing each level of diagnosis was established followed by the Cariostat test. The geometric distance between the test picture and the standard color card was calculated, and the caries risk level could be obtained accordingly by the threshold-controlling. Compared with the subjective judgment of the naked eye, the accuracy, effectiveness, and computational efficiency of our system are fully verified.