Skip to content
View allvaret's full-sized avatar
2 followers · 3 following
  • Brazil

Achievements

Achievement: YOLO

Achievements

Achievement: YOLO

Block or report allvaret

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
allvaret/README.md

Hello, I'm Alvaro 👋

Computer Science student focused on Software Engineering and Artificial Intelligence.

I like projects where software meets real constraints: hardware, latency, noisy data. I choose technologies based on the problem, not the other way around.

LinkedIn • alvarodanko032@gmail.com

Tech Stack

Area Technologies
Languages Python • C++ • Java • JavaScript • SQL
AI & Data OpenCV • PyTorch • TensorFlow • scikit-learn • Pandas • NumPy • spaCy • LLMs • Matplotlib
Embedded & Mobile ESP32 (Arduino framework) • Android (Kotlin, CameraX, Chaquopy) • WebSocket • Serial
Backend & Engineering FastAPI • Git • Modular Architecture • OOP • pytest
Frontend React • HTML • CSS
Currently learning Docker • AI Agents

Featured Projects

🚗 ESP32 Self-Driving Car

Small autonomous car for obstacle avoidance, integrating computer vision, embedded firmware and a mobile app. An Android phone runs a classical vision pipeline (HSV floor segmentation via histogram back-projection, optical flow, edges) at ~18 ms/frame on a Galaxy S9 and decides between free / uncertain / obstacle with hysteresis. An ESP32 drives the motors and runs a safety reflex, using an ultrasonic sensor on a servo to cover what vision cannot, such as a wall the same color as the floor. Phone and ESP32 talk over WebSocket. Vision was validated offline on recorded videos before the car existed, and the project design was partly inspired by a study of Tesla's and Waymo's perception approaches.

Python • OpenCV • C++ (ESP32) • Kotlin • Android (Chaquopy) • WebSocket

📄 Financial Report Processing Pipeline

Modular pipeline for reconstructing financial reports, extracting relevant information and preparing structured data for LLMs.

Python • PyMuPDF • spaCy • LLMs • FastAPI

🧠 Transfer Learning & ML Adaptations

Neural network projects involving transfer learning, custom architectures, dataset preparation and model evaluation.

My favorite:

Image-based recommendation system using visual embeddings

Python • TensorFlow • PyTorch • NumPy • Matplotlib • Pandas • Pillow • OpenCV

🎮 2D Educational Game

Complete Java game exploring object-oriented programming, modular architecture, game loops, physics and asset management.

Java • LibGDX • LWJGL

Pinned Loading

  1. Document_Parsing_Pipeline Document_Parsing_Pipeline Public

    Complete financial report parsing pipeline for structured LLM summarization.

    Python

  2. esp32-self-driving-car esp32-self-driving-car Public

    Self-driving car with classical computer vision: floor segmentation with color histograms in Python on a phone, ESP32 for motors and safety. No neural network or GPU.

    Python

  3. embeddings_similarity_recommendation embeddings_similarity_recommendation Public

    Image-based recommendation system using visual embeddings, FAISS retrieval, and user preference modeling.

    Jupyter Notebook

  4. FaceRecognition_SCRFD_EfficientNetB0 FaceRecognition_SCRFD_EfficientNetB0 Public

    Face recognition pipeline built with SCRFD and EfficientNetB0. Detects, aligns, preprocesses and classifies faces through a modular computer vision pipeline designed for custom identity recognition.

    Jupyter Notebook

  5. CleanCity CleanCity Public

    LibGDX game project with sound system, simple mechanics, and stage progression.

    Java