[🇧🇷 Português] [🇺🇸 English]

🧠 AI/ML Project 1 · Computer Vision · EMNIST Vision Intelligence

End-to-End Handwritten Character Recognition System with PyTorch and Streamlit

✨ Somewhere between scribbles and intelligence, this model takes shape. ✨

AI reading handwriting — confidence not guaranteed. ⚡️

Institution: Pontifical Catholic University of São Paulo (PUC-SP) — FACEI
Course: BSc in Humanistic AI & Data Science — 5th semester — 2026
Subject: Machine Learning for Handwritten Character Recognition
Project: P1 — EMNIST Vision Intelligence Project

Professor: ✨ Rooney Ribeiro Albuquerque Coelho
Authors: Fabiana ⚡️ Campanari e ✨ Pedro Vyctor Almeida

Warning

⚠️ Projects may be publicly shared when permitted.
The focus is on applied, hands-on learning with real datasets in AI governance and security contexts.
All sensitive content remains protected in private repositories when required.

Tip

This repository is part of the flagship ecosystem:

🧠 AI & Machine Learning — Main Hub

Explore the complete collection of projects, notebooks, research materials, analyses, and interactive applications available in the central repository:

🔗 AI & Machine Learning — Hub

🚁 Related Project in this Series

AI/ML Project 2 · Computer Vision · Helipoint Detector

Explore the complementary geospatial intelligence system focused on satellite-based helipad detection:

🔗 Helipoint Detector — Computer Vision Project

✨ Part of the Humanistic AI & Machine Learning Series

Teaching machines to recognize patterns while humans fine-tune both models and patience. ⚡️

Table of Contents

🚧 Project Under Construction 🚧

MLOps Pipeline Architecture

%%{init: {
  "theme": "base",
  "themeVariables": {
    "background": "#020617",
    "primaryColor": "#020617",
    "primaryBorderColor": "#2dd4bf",
    "primaryTextColor": "#ffffff",
    "lineColor": "#2dd4bf",
    "secondaryColor": "#020617",
    "tertiaryColor": "#020617",
    "clusterBkg": "#020617",
    "clusterBorder": "#2dd4bf",
    "fontFamily": "Inter, monospace",
    "fontSize": "16px"
  }
}}%%

flowchart TB

%% =========================
%% STYLE
%% =========================
classDef clean fill:#020617,stroke:#2dd4bf,color:#ffffff,stroke-width:1px;

%% =========================
%% PIPELINE
%% =========================

A["EMNIST Balanced Dataset"]:::clean

B["Handwritten Character Samples"]:::clean

C["Image Preprocessing"]:::clean

D["Grayscale Conversion"]:::clean

E["Resize to 28×28"]:::clean

F["Tensor Transformation"]:::clean

G["Python AI Pipeline"]:::clean

H["PyTorch Deep Learning Model"]:::clean

I["Perceptron Layers"]:::clean

J["Convolutional Neural Networks"]:::clean

K["Dropout Regularization"]:::clean

L["Backpropagation & Optimization"]:::clean

M["TensorBoard Monitoring"]:::clean

N["Accuracy & Loss Evaluation"]:::clean

O["OpenCV Real-Time Processing"]:::clean

P["Character Prediction Engine"]:::clean

Q["Softmax Probability Output"]:::clean

R["Streamlit Interactive Dashboard"]:::clean

S["Drawing Canvas Interface"]:::clean

T["Final AI Inference"]:::clean

%% =========================
%% FLOW
%% =========================

A --> B
B --> C
C --> D
D --> E
E --> F
F --> G

G --> H
H --> I
I --> J
J --> K
K --> L

L --> M
M --> N

N --> O
O --> P
P --> Q

Q --> R
R --> S
S --> T

linkStyle default stroke:#2dd4bf,stroke-width:1px;

Loading

💌 Let the data flow... Ping Me !

🛸๋ My Contacts Hub

────────────── ⊹🔭๋ ──────────────

➣➢➤ Back to Top

Copyright 2026 Mindful-AI-Assistants. Code released under the MIT license.