A Smart Toothbrush with AI-Based Plaque Detection and Real-Time Brushing Guidance

CSEF · 2026 Medicine & Physiology (Junior Division)

Overview

Oral health plays a critical role in overall health and long-term wellness. Maintaining proper brushing technique is essential, yet many people struggle to consistently identify and clean areas with high plaque buildup. To address this challenge, a smart toothbrush has been designed to detect plaque in real time and guide users toward more effective brushing. The toothbrush leverages plaque’s light-induced fluorescence property, in which porphyrins produced by oral bacteria emit red light under blue-violet illumination. The design consists of five core components: light-emitting diode (LED: 395-405 nm), camera, microcontroller, speaker, and rechargeable battery. The LED illuminates dental plaque, triggering its characteristic red fluorescence, while the camera captures intraoral images for analysis. An image classifier, using artificial intelligence (AI) and deployed on the microcontroller, processes these images to detect plaque. The speaker then delivers voice commands directing the user to focus on areas where plaque is detected, and the rechargeable battery powers the entire toothbrush. To evaluate the prototype, fluorescence experiments were conducted on a variety of food samples, leading to the selection of spirulina paste as an artificial plaque substitute due to its similar red fluorescence under LED illumination. Performance was assessed using a confusion matrix. The prototype achieved 91% accuracy, 92% recall, and 89% specificity, indicating reliable plaque detection while minimizing false positives. This smart toothbrush demonstrates how imaging and AI can utilize the biochemical fluorescence of plaque to deliver personalized, data-driven brushing guidance. It helps users more effectively prevent plaque buildup, supporting their long-term oral health.

Competition history

  • CSEF 2026 Medicine & Physiology (Junior Division) · Entry J-15-11

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Browse more like this

Source: California Science & Engineering Fair public projects

Save projects to your library

Sign in with Google to keep track of projects you find interesting, organized into folders. An account also raises your daily allowance for “Has this been done?”, and lets you create a key for the MCP server with a much higher limit than anonymous use. Browsing stays public.

Continue with Google