Plant Root Analyzer

Software Engineering & Deployment module at BUas, Year 2 Block D. Built individually with a focus on production-ready ML systems, covering model training, API design, containerisation, and cloud deployment.

Deep learning image segmentation pipeline analyzing plant root images using a U-Net CNN. Features CLI, web interface, and REST API, deployed both on-premise and on Azure Container Apps with full CI/CD.

Key Highlights

01.U-Net CNN architecture trained for high-precision semantic segmentation of plant root imagery.
02.Three interfaces shipped: a CLI tool, a web UI, and a documented REST API.
03.Full CI/CD pipeline with automated Pytest suite covering critical model and API components.
04.Dual deployment: on-premise Docker containers and Azure Container Apps for scalable cloud access.
05.Modular codebase enabling independent swapping of model backbone without API changes.