https://github.com/javaidiqbal11/pattern-recognition-cloths

The goal is to build a model that can classify different clothing patterns, such as stripes, polka dots, plaid, floral, and more.
https://github.com/javaidiqbal11/pattern-recognition-cloths

clothes-detector computer-vision convolutional-neural-networks deep-learning pattern-recognition python

Last synced: 24 days ago
JSON representation

The goal is to build a model that can classify different clothing patterns, such as stripes, polka dots, plaid, floral, and more.

• Host: GitHub
• URL: https://github.com/javaidiqbal11/pattern-recognition-cloths
• Owner: javaidiqbal11
• Created: 2024-07-31T12:35:09.000Z (6 months ago)
• Default Branch: main
• Last Pushed: 2024-12-24T10:05:24.000Z (about 1 month ago)
• Last Synced: 2024-12-24T11:31:12.339Z (about 1 month ago)
• Topics: clothes-detector, computer-vision, convolutional-neural-networks, deep-learning, pattern-recognition, python
• Language: Jupyter Notebook
• Homepage: hppts://www.jtech.com.pk
• Size: 65.2 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Clothes Pattern Recognition 

## Project Overview

This project focuses on cloth pattern recognition using deep learning approaches. The goal is to build a model that can classify different `clothing patterns`, such as `stripes`, `polka dots`, `plaid`, `floral`, and more. By leveraging deep learning techniques, particularly   `Convolutional Neural Networks` (CNNs), we aim to achieve high accuracy in detecting and categorizing various cloth patterns. This application can be integrated into fashion recommendation systems, inventory management, or even fabric production processes.

## Setup

Python 3.10.10 or more

**Install Packages**

```shell

pip install -r requirements.txt

```

**CNN Model**

Train cnn model

```shell

python cnn.py

```

**Kaggle Notebooks**

There are two notebooks available to run the code and check output.

1. fabric-cnn.ipynb 

2. fabric-effiecientnet.ipynb

`optional model training`

**ResNet Model**

Train cnn model

```shell

python resnet.py

```

**GCNN Model**

Check final outcomes 

```shell

python gcnn.py

```

## Model Architecture

The deep learning model is based on Convolutional Neural Networks (CNNs), which are highly effective for image classification tasks. The architecture includes:

- Convolutional layers for feature extraction

- Max-pooling layers for dimensionality reduction

- Fully connected layers for classification

- Softmax activation function for multi-class classification

## Future Improvements

- Enhance dataset: Use a more diverse dataset with more patterns and variations in lighting, orientation, and fabric types.

- Fine-tune the model: Apply transfer learning with a pre-trained model such as ResNet, VGG, or Inception for better performance.

- Real-time detection: Implement real-time pattern recognition using a camera feed.

- Mobile integration: Convert the model to run on mobile devices using TensorFlow Lite or ONNX. Also compatible with real time devices like android and iOS.