X-Ray-Based Quick COVID-19 Detection With Raspberry Pi

The X-Ray-Based Quick COVID-19 Detection system operates by leveraging machine learning models deployed locally on a Raspberry Pi 5 to analyze digital lung X-ray images. At the core of the system is a trained Edge ML model, initially created using tools like Edge Impulse, TensorFlow, or PyTorch, which is optimized to recognize specific pathological patterns associated with COVID-19 infections. The Raspberry Pi board serves as the central processing unit running Raspbian OS and Node.js environments to execute the classification pipeline. When an X-ray image is provided to the system—either captured via a Raspberry Pi Camera or loaded from an image dataset—the Edge Impulse Linux CLI and Python scripts process the pixel data through the neural network. The model evaluates the image features against its trained weights, outputting a classification result that indicates the presence or absence of infection markers. This output is then rendered onto an attached HDMI display or monitor, providing a visual diagnosis in real-time without relying on cloud-based infrastructure. Power is supplied reliably to the single-board computer via an appropriate power supply to sustain the computational load required for edge inference.