My Projects

Synthetic Airplane Image Generation and ML Model Training

Synthetic Airplane Images

During my internship at Stratom Inc., I worked on an innovative project that leveraged Unity's powerful 3D rendering capabilities to generate synthetic images of various airplane models. These images were then used to train a machine learning model for accurate airplane model detection, significantly enhancing the company's computer vision capabilities.

Key aspects of the project include:

This project demonstrates the power of combining game development tools with machine learning techniques to solve complex computer vision problems, especially in scenarios where real-world data may be limited or difficult to obtain.

Unity C# Python TensorFlow Computer Vision 3D Modeling MMDetection COCO Dataset

Personal Finance Tracker

This interactive Personal Finance Tracker helps you manage your expenses and visualize your spending patterns. Add your transactions and see your financial data come to life with real-time updates and insightful charts. You can also export your data to an Excel file for further analysis.

Key features of this project include:

This project demonstrates proficiency in front-end web development, focusing on creating interactive and data-driven user interfaces. It showcases the power of vanilla JavaScript in building complex applications and highlights the use of modern web APIs and libraries for data visualization, storage, and export.

HTML5 CSS3 JavaScript Chart.js ExcelJS Local Storage API Responsive Design Data Visualization

Real-time Object Detection using Webcam

This project demonstrates real-time object detection using your device's webcam. It utilizes TensorFlow.js and the COCO-SSD (Common Objects in Context - Single Shot MultiBox Detector) model to identify and label objects in the video stream.

Privacy Notice

Important: This application will request access to your device's webcam to perform real-time object detection. Please note:

  • All processing is done locally in your browser. No video data is transmitted or stored on any server.
  • No images or video footage from your webcam are saved or retained in any way.
  • You can stop the webcam feed at any time by closing this webpage or denying camera permissions in your browser settings.
  • This is a demonstration project and is intended for educational purposes only.

By clicking the "Start Object Detection" button, you acknowledge and agree to allow camera access solely for the purpose of demonstrating real-time object detection.

Key features of the project include:

This project showcases the power of modern web technologies in conjunction with machine learning, enabling sophisticated computer vision tasks to be performed directly in the browser.

JavaScript TensorFlow.js WebRTC HTML5 CSS3 Machine Learning Computer Vision