Luiz Fernando

Projects

A showcase of my technical projects and contributions across different domains.

Rubber Duck Detection Project Demo

Rubber Duck Detection

Computer Vision

🎯 Intelligent rubber duck detection system powered by YOLO deep learning architecture. Specifically designed for identifying rubber ducks in various environments with high accuracy and real-time processing capabilities.

🚀 Technical Highlights:

  • • YOLO-based object detection for precise rubber duck localization
  • • Character recognition optimized for various environments
  • • Robust to various lighting and weather conditions

🛠️ Technical Stack:

Python YOLO OpenCV Deep Learning
📖 View on GitHub Computer Vision Project
PUMLE Project Demo

PUMLE

Data Engineering

🌍 Innovative data pipeline for geological carbon storage in Brazilian reservoirs. PUMLE transforms complex simulation outputs into streamlined multidimensional arrays, making environmental data accessible and actionable.

✨ Key Features:

  • • Multi-format export (NumPy, Zarr, MAT-files, CSV)
  • • Cloud integration for seamless data sharing
  • • Optimized for large-scale geological simulations
  • • Built for environmental impact analysis

🛠️ Technical Stack:

Python NumPy Zarr Cloud Storage
📖 View on GitHub Open Source Project
Car Plate Detection Project Demo

Car Plate Detection

Computer Vision

🎯 Intelligent license plate recognition system powered by YOLO deep learning architecture. Specifically designed for Brazilian vehicle registration patterns with high accuracy and real-time processing capabilities.

🚀 Technical Highlights:

  • • YOLO-based object detection for precise plate localization
  • • Character recognition optimized for Brazilian formats
  • • Real-time processing with high accuracy rates
  • • Robust to various lighting and weather conditions

🛠️ Technical Stack:

Python YOLO OpenCV Deep Learning
📖 View on GitHub Computer Vision Project
Office Sentence Project Demo

Michael Scott Speak Generator with GPT-2

Natural Language Processing

🎯 Michael Scott Speak Generator system powered by GPT-2 transformers architecture. This project generates text in the style of Michael Scott from "The Office". It leverages advanced natural language processing techniques to create humorous and contextually relevant sentences, capturing the essence of the character's unique speech patterns. It's important to note that this project was built before the LLM's boom and does not utilize cutting-edge models like GPT-4 or Claude 3.

🚀 Technical Highlights:

  • • Text generation tailored to Michael Scott's unique speech patterns
  • • Contextual understanding of "The Office" episodes
  • • NLP techniques for humor generation
  • • Fine-tuning on character-specific dialogue

🛠️ Technical Stack:

Python Transformers PyTorch Deep Learning
📖 View on Hugging Face Natural Language Processing Project
Motion Coach Project Demo

Motion Coach: Gym Assistant

Computer Vision

🎯 Motion Coach is an innovative gym assistant application that leverages computer vision to provide real-time feedback on exercise form and technique. The model had a f1-score of 0.92 on the validation set, demonstrating its effectiveness in detecting and analyzing human poses during workouts.

🚀 Technical Highlights:

  • • Real-time pose detection and tracking
  • • Form analysis using keypoint detection
  • • Feedback system for exercise correction
  • • User-friendly interface for workout guidance

🛠️ Technical Stack:

Python FastAPI PyTorch MediaPipe
📖 View on GitHub Computer Vision Project
Bin Packing Project Demo

Bin Packing Optimizer

Algorithms

⚡ High-performance solution to the Variable-Sized Bin Packing Problem (VSBPP). Built from scratch in C++ to achieve optimal space utilization with minimal computational overhead, perfect for logistics and resource allocation challenges.

💡 Algorithm Features:

  • • Optimized C++ implementation for maximum speed
  • • Variable-sized container support
  • • Multiple heuristic strategies
  • • Scalable for large dataset processing

🛠️ Technical Stack:

C++ Algorithms Optimization Data Structures
📖 View on GitHub Algorithm Implementation
Branch and Bound Project Demo

Branch and Bound

Optimization

🧮 Mathematical optimization powerhouse implementing the classic Branch and Bound algorithm. Designed to solve complex integer linear programming problems with guaranteed optimal solutions, leveraging Python's MIP library for robust performance.

🔬 Mathematical Excellence:

  • • Classic Branch and Bound implementation
  • • Integer linear programming solver
  • • Optimal solution guarantees
  • • Educational and practical applications

🛠️ Technical Stack:

Python MIP Linear Programming Mathematics
📖 View on GitHub Mathematical Algorithm
NumPy from Scratch Project Demo

NumPy from Scratch

Low-Level

🛠️ Ground-up recreation of NumPy's core functionality using pure C programming. This project demonstrates deep understanding of memory management, array operations, and performance optimization in scientific computing libraries.

⚙️ Engineering Excellence:

  • • Pure C implementation for maximum control
  • • High-dimensional array manipulation
  • • Memory-efficient data structures
  • • Core mathematical operations

🛠️ Technical Stack:

C Memory Management Arrays Performance
📖 View on GitHub System Programming Project