This project is a web application for skin disease detection built as a thesis under the College of Computer and Information Sciences (CCIS). It uses TensorFlow Lite models to predict skin conditions from uploaded images, achieving high accuracy on common diseases but struggling with rare ones due to class imbalance. The frontend leverages Alpine.js, Tailwind CSS, and Jinja2 templates for interactivity and responsiveness without a build step. Security features include CSRF protection, SRI hashes, rate limiting, and input validation. Deployed on Render's free tier using Gunicorn, the app integrates Groq's multimodal LLM for explanatory text based on image content, enhancing user experience. The project is open-source under MIT license, encouraging contributions to improve models or add new features.
Read the full article at DEV Community
Want to create content about this topic? Use Nemati AI tools to generate articles, social posts, and more.
