Projects

Featured Work

A selection of projects that demonstrate my approach to solving complex engineering challenges.

AI Case Study
Completed
PythonOpenCVMediaPipeArduino+2

Computer Vision Controlled Robot Arm

This project explores the connection between computer vision and robotics by implementing a robot arm that can be controlled through visual hand-based input. Instead of relying only on traditional controllers, the system uses vision-based detection to interpret user movement and convert it into physical robotic motion. The project helped build practical experience in robotics, hardware control, and real-time AI interaction.

Problem

Architecture

Deploy

CodeSee VideoView Project
AI Case Study
Completed
React.jsFastAPIMySQLWebSocket+8

AI-Powered Smart Parking Management System

This project is a complete intelligent parking management system that combines computer vision, OCR, embedded systems, drone monitoring, and full-stack web technologies. The system detects and recognizes vehicle license plates, monitors parking slot availability in real time, controls a physical gate using hardware components, and displays live system updates through a React-based interface connected to a FastAPI backend.

Problem

Architecture

Deploy

CodeSee VideoView Project
AI Case Study
Completed
PythonOpenCVMediaPipe Face MeshWhisper+5

Speaker Detection, Tracking & AI Summarization System

This project is a multimodal AI system focused on speaker detection, tracking, speech segmentation, transcription, and summarization. It uses MediaPipe Face Mesh to analyze facial landmarks and determine whether a detected person is speaking based on lip movement ratios. The system can identify active speakers in video, segment speaker-specific audio, transcribe speech using Whisper, and generate concise summaries using LangChain. It also supports YouTube videos and PDF documents, allowing users to extract and summarize content from multiple sources.

Problem

Architecture

Deploy

CodeSee VideoView Project
AI Case Study
Completed
PythonOpenCVOCRRegular Expressions+1

OCR-Based Card Field Extraction System

This project focuses on extracting structured information from card images using image processing, OCR, and regular expressions. The system processes images of ID cards, bank cards, and similar field-based cards, extracts visible text, and organizes the detected data into meaningful fields. It demonstrates how OCR can be used as a practical automation layer for document understanding and data entry workflows.

Problem

Architecture

Deploy

CodeSee VideoView Project
AI Case Study
Completed
PythonOpenCVMediaPipeArduino+2

Computer Vision LED Control System

This project demonstrates the integration of computer vision with embedded hardware by allowing LED flashes to be controlled using hand gestures. The system uses MediaPipe’s pre-trained hand detection model to recognize hand signals in real time, then sends the detected commands to an Arduino microcontroller responsible for controlling the LEDs. It was built as a practical exploration of how AI-powered perception can interact with physical electronic components.

Problem

Architecture

Deploy

CodeSee VideoView Project
AI Case Study
Completed
React.jsFastAPIPythonOpenCV+3

Secure Face Recognition Attendance System

This project demonstrates how a face recognition model can be integrated into a real-world attendance application. The system uses a React interface connected to a FastAPI backend to process live frames, verify user identity, and detect whether the presented face is real or spoofed. The prototype highlights how face recognition and anti-spoofing can work together to create a more secure and efficient attendance workflow.

Problem

Architecture

Deploy

CodeSee VideoView Project
AI Case Study
Completed
PythonFastAPIReactTypeScript+11

FireWatch — AI-Powered Wildfire Risk Prediction and Fire/Smoke Detection

FireWatch is a drone-ready wildfire monitoring and decision-support prototype developed for the Karabük region in Türkiye. It combines weather-based wildfire risk prediction with real-time fire and smoke detection from camera or drone-ready video sources. The system uses a two-stage machine learning pipeline. A HistGradientBoostingRegressor predicts the continuous Fire Weather Index from a locked 34-feature weather schema, while a RandomForestClassifier provides a safety-oriented high-risk decision layer. A custom YOLOv8 model detects visible fire and smoke and creates persistent alerts for operator review. The complete platform includes a FastAPI backend, React and TypeScript dashboard, SQLite persistence, scheduled risk checks, live monitoring, detection alerts, system and model information, risk-map context, and drone-ready support.

Problem

Architecture

Deploy

CodeSee VideoView Project
Property Rental Management ERP
AI Case Study
Completed
ReactTypeScriptViteTailwind CSS+14

Property Rental Management ERP

Property Rental Management ERP is a full-stack property rental management ERP built to replace manual notebook-based rent tracking with a structured digital system. The platform allows property owners to manage multiple buildings and apartments, track tenant occupancy, create rental contracts, automatically generate monthly rent obligations, record partial and full payments, detect overdue balances, monitor contract expirations, and view operational analytics from a centralized dashboard. The system also includes audit history, multi-admin attribution, business settings, security hardening, and a visual building explorer that makes apartment occupancy easy to understand.

Problem

Architecture

Deploy

CodeSee VideoView Project