Aaron George — AI & Computer Science
Computer Science undergraduate specializing in Artificial Intelligence, with hands-on experience in AI-based projects. Skilled in programming, machine learning, and computer vision, with working knowledge of cyber security.
/$$$$$$ /$$$$$$ /$$__ $$ /$$__ $$ | $$ \ $$| $$ \__/ | $$$$$$$$| $$ /$$$ | $$__ $$| $$ \ $$ | $$ | $$| $$$$$$/ |__/ |__/ \______/ > projects: 3 > status: building /$$$$$$ /$$$$$$ /$$$$$$$ /$$$$$$ /$$ /$$ /$$__ $$ /$$__ $$| $$__ $$ /$$__ $$| $$$ | $$ | $$ \ $$| $$ \ $$| $$ \ $$| $$ \ $$| $$$$| $$ | $$$$$$$$| $$$$$$$$| $$$$$$$/| $$ | $$| $$ $$ $$ | $$__ $$| $$__ $$| $$__ $$| $$ | $$| $$ $$$$ | $$ | $$| $$ | $$| $$ \ $$| $$ | $$| $$\ $$$ | $$ | $$| $$ | $$| $$ | $$| $$$$$$/| $$ \ $$ |__/ |__/|__/ |__/|__/ |__/ \______/ |__/ \__/ Aaron George > projects loaded: 3 > status: building > focus: AI & Computer Vision
Artifacts
Real-time facial emotion recognition system using CNN-based deep learning. Implements an end-to-end pipeline covering face detection, feature extraction, and emotion classification with OpenCV for real-time video processing.
Advanced RAG PDF processing chatbot with zero-tolerance for hallucination. Answers queries while displaying exact PDF pages and sources, supports any PDF format including Sanskrit texts with OCR capabilities.
MCP-compliant server enabling AI models to interact programmatically with Blender. Exposes scene control, object creation, transformations, and rendering as MCP tools for AI-assisted 3D workflows.
Field Notes
Brief observations, technical findings, and thoughts from the workbench.
Designing an end-to-end pipeline for facial emotion recognition using OpenCV, TensorFlow, and convolutional neural networks.
Implementing semantic search with sentence-transformers and pgvector for accurate, traceable PDF Q&A with exact source citations.
Developing an MCP-compliant server to enable AI models to interact programmatically with Blender for procedural modeling and automation.
Exploring cryptography principles, encryption, hashing, common vulnerabilities, and defensive mechanisms in computing systems.
Work in Progress
Active experiments and prototypes. Things that are being built, broken, and rebuilt.
MCP-compliant server enabling AI models to interact programmatically with Blender for 3D workflows
Real-time facial emotion recognition using CNN-based deep learning with OpenCV
AI-powered PDF preprocessor & chatbot with zero-hallucination RAG and OCR capabilities