Won 1st Place Overall at BDAA X Lovable Hackathon. Built an AI-powered lost and found platform where finders upload photos and AI automatically generates unique security questions that only the true owner would know. Implemented semantic similarity verification using Google Gemini to prevent fraudulent claims. Uses Mapbox GL for interactive location tagging and Fuse.js for fuzzy search.

Built a Chrome extension using JavaScript and Selenium that reduced product data collection time by 12,500%, cutting task duration from hours to seconds. Used the XLSX library for seamless Excel export and reached 190+ users while ranking among the top 5 Amazon product scrapers on the Chrome Web Store.

Analyzed over 2.15 million traffic accidents and 3,300+ bus stops across NYC using GeoPandas for spatial analysis and proximity mapping. Identified the 10 most dangerous bus shelter locations through comprehensive data modeling. Selected from 400+ applicants to present findings to the Department of Transportation and Federal Highway Administration.

Developed a Flask web application that processes facial images for acne detection using MediaPipe and OpenCV, achieving 94% classification accuracy across 10 common skin conditions on 5,000+ labeled images. Optimized the processing pipeline with image compression to deliver analysis results in under 2 seconds per image, achieving 7x faster performance for high-resolution photos.

Built a real-time camera OCR system that integrates Google Cloud Vision API and Perplexity AI to extract and analyze text from live camera feeds. Features a modern split-screen UI delivering instant text recognition and AI-powered analysis results. Streamlined the workflow from text capture to intelligent search, reducing manual text entry time by 95% while providing contextual insights through advanced AI processing.

Developed a web application that detects and visualizes invisible Unicode characters in text to identify AI-generated content and prevent security exploits. Features advanced zero-width character detection across 65,000+ Unicode symbols, helping users identify hidden malicious content and text obfuscation attempts. Provides instant text analysis and cleanup tools, improving content authenticity verification by 100% while protecting against phishing and filter bypass attacks.