Projects

Face Recognition System is an end-to-end machine learning and computer vision application designed for real-time user identification. The system follows a microservice architecture, where a FastAPI-based ML service uses deep learning (FaceNet via DeepFace) to generate facial embeddings and perform accurate recognition.

A Node.js/Express backend manages user registration, database storage, and real-time recognition through WebSockets, seamlessly communicating with the ML service. The Next.js frontend provides a responsive, camera-enabled interface for face registration and live recognition using face-api.js.

This project demonstrates practical deployment of computer vision models integrated with scalable APIs and modern web technologies.

Blur Face Privacy Tool is a privacy-focused web application that automatically detects and obscures faces in images and videos to protect personal identity. The system uses advanced machine learning-based face detection in the backend and provides adjustable blur intensity for precise privacy control.

A Next.js frontend offers an intuitive interface with drag-and-drop uploads, real-time comparison between original and processed media, and support for both image (JPG, PNG) and video (MP4, WebM) formats. Users can instantly apply face blurring and download results while remaining responsive on desktop and mobile.

This project demonstrates the integration of AI-driven visual processing with modern UI design to deliver a seamless, privacy-enhancing experience.

Real-Time Eye-Blink Anti-Spoof Detection System is a biometric liveness verification project built using advanced computer vision techniques. The FastAPI backend leverages Mediapipe Face Mesh and the Eye Aspect Ratio (EAR) algorithm to detect eye blinks and determine whether a face is live or spoofed through both REST APIs and WebSocket-based real-time streaming.

A blink state machine tracks recent blink patterns for reliable liveness detection. The Next.js frontend provides a responsive, camera-enabled interface that streams video frames to the backend and visualizes blink status, confidence, and counts in real time.

This project demonstrates practical anti-spoofing, biometric security, and real-time AI system deployment.

LogoAi is an innovative AI-powered logo generation platform built with Next.js, designed to help users create unique and professional logos effortlessly. Utilizing the Gemini API for prompt enhancement and Pollinations AI API for generating high-quality logo designs, LogoAi delivers creative branding solutions tailored to user needs.

The app features a seamless user experience with server-side rendering for fast performance and smooth interactions. With MongoDB as the database and Cloudinary for efficient image storage and delivery, users can easily generate, save, and manage their logos in a secure environment.

LogoAi empowers businesses and individuals to quickly craft visually appealing logos without design expertise, making branding accessible to everyone.

Chat with PDFs is an intelligent document assistant built with Next.js, designed to help users upload and interact with their PDF files through natural language queries. By leveraging the Gemini models and Langchain embeddings, the app enables accurate contextual responses drawn directly from uploaded documents.

The platform uses Supabase as a vector database to store and query embeddings, ensuring efficient retrieval and scalability. With Inngest managing background jobs such as file parsing and embedding generation, the application remains fast, responsive, and reliable even when handling large files.

Hosted on Vercel, the app offers seamless file uploads, intelligent query answering, and a clean, responsive interface, making it an essential productivity tool for students, researchers, and professionals working with PDF documents.

FoodHub is a streamlined food ordering application designed to simplify the process of ordering from a single local restaurant. It offers a clean, intuitive, and user-friendly interface that ensures a seamless experience for customers, whether they’re using a mobile device or a desktop.

Built with efficiency in mind, the app incorporates a variety of practical features such as an admin dashboard for restaurant management, a detailed order history for users to track past purchases, and a real-time order status checker.

The responsive design adapts effortlessly to different screen sizes, making it accessible and convenient for all users. Foodman aims to bridge the gap between local eateries and their customers by providing a reliable and straightforward platform for food ordering.

Chatty is a modern chat application built with Next.js and TypeScript, showcasing responsive UI and real-time capabilities. Designed with a clean and scalable structure, it integrates modern frontend patterns and optimized performance for interactive messaging experiences.

The app leverages React's component architecture and efficient state management to deliver seamless navigation and dynamic content rendering. Styled with Tailwind CSS, Chatty emphasizes a polished, user-centric design suitable for messaging interfaces.

This project demonstrates practical skills in frontend engineering, responsive layout implementation, and building extensible client-side applications ready to be enhanced with backend or real-time communication features.

Cozera-store is a responsive e-commerce web application built with modern frontend technologies and intuitive user experience in mind. Developed using React and Create React App, it implements core e-commerce features such as product browsing, cart management, and smooth navigation in a scalable architecture.

The application is designed to deliver fast load times, clean UI, and seamless interaction across devices. It showcases practical skills in frontend development, state management, and building production-ready web interfaces that can be extended with backend services and APIs for complete shopping workflows.

Cozera-store highlights a strong understanding of modern web development patterns and responsive user-centric design.

Travel-Dot is a responsive React-based travel website application that provides users with an engaging platform to explore destinations and travel information. Built with Create React App, it demonstrates practical frontend engineering using modern JavaScript, component-based structure, and responsive design principles.

The project lays the foundation for integrating travel content, user interaction, and dynamic UI features that can be extended with APIs and backend services for full travel workflow support. Travel-Dot highlights skills in building scalable, user-friendly web interfaces with clean architecture and modern tooling, suitable for expanding into complete travel discovery or booking experiences.

Weather App is a straightforward web application that delivers real-time weather updates for any location, powered by the OpenWeather API. Designed with simplicity in mind, it features a user-friendly interface that provides essential weather information, including current conditions and weather alerts.

Built using HTML, CSS, and JavaScript, the app ensures a responsive design that performs well on both web and mobile devices.

Whether users need to plan their day or stay informed about changing weather patterns, Weather App offers a reliable and accessible solution with a focus on usability and performance.

Br Architects is a static website built using Bootstrap to showcase a clean, modern, and responsive design tailored for an architectural firm. The site features a professional layout with key sections such as Home, About, Services, and Contact, making it easy for visitors to explore the firm’s offerings.

Optimized for both mobile and desktop devices, it leverages HTML, CSS, and JavaScript to deliver a fast and visually appealing experience.

With Bootstrap’s framework and subtle animations, Br Architects provides a polished and performance-driven platform that highlights the importance of responsive web design in a competitive digital landscape.