https://github.com/ritap03/neuralnetwork-shapeclassifier

Feedforward neural network system in MATLAB for geometric shape classification. Includes data preprocessing, network training and evaluation, confusion matrix analysis, and a graphical interface for user interaction and model testing.
https://github.com/ritap03/neuralnetwork-shapeclassifier

ai data-analysis deep-learning feedforward-network gui image-classification machine-learning matlab neural-network pattern-recognition

Last synced: about 1 month ago
JSON representation

Feedforward neural network system in MATLAB for geometric shape classification. Includes data preprocessing, network training and evaluation, confusion matrix analysis, and a graphical interface for user interaction and model testing.

• Host: GitHub
• URL: https://github.com/ritap03/neuralnetwork-shapeclassifier
• Owner: RitaP03
• Created: 2025-10-24T09:38:56.000Z (8 months ago)
• Default Branch: main
• Last Pushed: 2025-10-24T09:47:46.000Z (8 months ago)
• Last Synced: 2025-11-07T13:02:54.796Z (8 months ago)
• Topics: ai, data-analysis, deep-learning, feedforward-network, gui, image-classification, machine-learning, matlab, neural-network, pattern-recognition
• Language: MATLAB
• Homepage:
• Size: 7.36 MB
• Stars: 0
• Watchers: 0
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# 🧠 **Feedforward Neural Network for Shape Classification**

MATLAB project developed for the **Knowledge and Reasoning** course at the Polytechnic Institute of Coimbra (ISEC).  

The goal is to design, train, and evaluate **feedforward neural networks** capable of classifying geometric shapes from images.

---

## ⚙️ **Main Features**

- Image preprocessing (resizing, grayscale conversion, binarization)  

- One-hot encoding for target representation  

- Training and testing of feedforward networks with various topologies  

- Comparative analysis of:

  - Training and activation functions  

  - Data division ratios (train/validation/test)  

  - Model generalization and overfitting  

- Confusion matrix generation and performance visualization  

- Graphical User Interface (GUI) for interactive model training and classification  

---

## 🧩 **Technologies**

- **MATLAB**  

- **Deep Learning Toolbox**  

- **Image Processing Toolbox**

---

## 📊 **Results**

The best models achieved **100% accuracy** on training datasets and strong generalization across different image sets.  

Further experiments revealed the impact of training parameters and dataset diversity on classification performance.

---

## 🖥️ **Graphical Application**

An interactive MATLAB GUI allows the user to:

- Configure network parameters (neurons, layers, functions)

- Train or import models

- Load or draw new images

- Classify shapes and visualize results

---

## 📚 **About**

Developed by **Ana Rita Pessoa** and **João Francisco Claro** (ISEC, 2024/2025).  

This project explores neural networks for image-based classification, bridging concepts of **machine learning**, **pattern recognition**, and **data analysis**.