Webcam-Based Face Mask Compliance Monitor

Added Jun 2025 3 design docs

Hospitals, clinics, laboratories, and food production facilities enforce face covering policies for safety, but relying on staff to visually police compliance at every entrance is impractical and inconsistent. An automated check at the door provides continuous coverage and frees people for higher-value work. The intern builds a Flask web application that captures live webcam video, detects faces in each frame with OpenCV, and classifies each detected face as masked or unmasked using a convolutional neural network trained in TensorFlow. The interface streams the annotated video feed to the browser with bounding boxes and prediction labels overlaid in real time, and the intern tunes the pipeline so detection and classification keep pace with the camera frame rate. The finished system is containerized with Docker, making it straightforward to host in the cloud or drop onto a small machine at a facility entrance. The project teaches the full arc of a deployed vision product: assembling and training a CNN classifier, wiring model inference into a live video loop, serving real-time results through a Python web framework, and packaging everything for repeatable deployment. It is a strong portfolio piece showing the intern can move a model from notebook experiment to a working safety tool.

Related projects

Symptom-Based Early UTI Screening Tool for Rural Healthcare

Urinary tract infections are among the most common infections affecting women worldwide, yet in rural and underserved communities they often go unnoticed until they escalate into painful, costly complications. Seeing a clinician for an early assessment is not always practical, so a lightweight screening tool that works from symptom descriptions and basic health data can make a real difference in prompting timely care. The intern builds a complete screening application around this need. A questionnaire-style interface built with streamlit collects symptoms such as burning sensation, urinary frequency, and fever alongside simple health indicators, and a machine-learning classifier written in python estimates the likelihood of a UTI from those inputs. A fastapi backend exposes the trained model as an inference service, validates incoming data, and keeps the interface cleanly separated from the prediction logic. The app also surfaces educational content on symptoms, prevention, and red flags that warrant an urgent doctor visit. Completing the project takes the intern through the full arc of applied machine learning in healthcare: preparing training data, evaluating a classifier honestly, serving it behind an API, and presenting predictions responsibly as guidance rather than diagnosis.

healthcarefastapimachine-learning+2

View project

Medium

Agent-Driven Alert Drafting for Banking Compliance Updates

When regulators publish new rules or amend existing ones, compliance teams at banks must quickly understand what changed, decide who is affected, and circulate clear internal alerts. Doing this by hand for every circular and amendment is slow and error-prone, which makes it a strong candidate for AI-assisted automation. The intern builds a pipeline in python where users paste or upload recent regulatory updates and compliance changes. A workflow defined in langgraph moves each document through stages for parsing, relevance assessment, summarization, and alert drafting, while an agentic-ai layer coordinates the stages and decides when a summary needs another pass. Generative AI through openai models turns dense regulatory language into short, actionable alert messages and longer explanatory summaries, and the system assembles everything into text-based alert reports ready for distribution to affected teams. The project teaches regulatory monitoring practices, faithful AI summarization of high-stakes text, and multi-step workflow automation. The intern finishes able to show a working compliance tool and to explain the safeguards needed when generative AI drafts security-sensitive communications.

bankingsecurityagentic-aigenerative-ai+3

View project

Medium

Agent-Orchestrated Scenario Analysis for Fraud and Compliance

When a bank confronts a new situation, such as a suspected fraud pattern or an unfamiliar compliance question, experienced staff instinctively recall similar past cases and what was done about them. Encoding that instinct in software, so any analyst can ask what a scenario resembles and what actions are advisable, is the goal of this project. The intern builds a python application where users describe or upload hypothetical banking scenarios covering areas like fraud detection and compliance checks. A langgraph workflow structures the analysis: the scenario is parsed, matched against a library of historical cases, and passed to a generation stage where openai models produce recommended actions and rationale. An agentic-ai layer coordinates the matching and generation steps, deciding when a scenario needs clarification or a second comparison pass. The output pairs each input scenario with its closest precedents and a clear, structured set of suggested next steps. Through this build the intern learns scenario analysis, similarity-based reasoning with generative AI, and modular workflow design, and gains a concrete story about how agent-style orchestration supports risk decisions in banking.

bankingsecurityagentic-aigenerative-ai+3

View project