https://github.com/subhangisati/hand-gesture-recognition-system
This project implements a hand gesture recognition system using deep learning techniques with TensorFlow and Keras. It involves preprocessing a dataset from Kaggle, building and training a convolutional neural network (CNN) model.
https://github.com/subhangisati/hand-gesture-recognition-system
cnn computer-vision hand-gesture-recognition image-processing image-recognition keras-tensorflow machine-learning python3
Last synced: 3 months ago
JSON representation
This project implements a hand gesture recognition system using deep learning techniques with TensorFlow and Keras. It involves preprocessing a dataset from Kaggle, building and training a convolutional neural network (CNN) model.
- Host: GitHub
- URL: https://github.com/subhangisati/hand-gesture-recognition-system
- Owner: SubhangiSati
- Created: 2024-07-11T17:55:36.000Z (10 months ago)
- Default Branch: main
- Last Pushed: 2024-07-11T17:57:34.000Z (10 months ago)
- Last Synced: 2025-02-21T05:57:24.477Z (3 months ago)
- Topics: cnn, computer-vision, hand-gesture-recognition, image-processing, image-recognition, keras-tensorflow, machine-learning, python3
- Language: Jupyter Notebook
- Homepage:
- Size: 641 KB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: Readme.md
Awesome Lists containing this project
README
# Hand Gesture Recognition using Deep Learning
## Overview
This project implements a hand gesture recognition system using deep learning techniques with TensorFlow and Keras. It involves preprocessing a dataset from Kaggle, building and training a convolutional neural network (CNN) model, and evaluating its performance.
## Dataset
The dataset used in this project is the Leap Gesture Recognition dataset available on Kaggle. It consists of images of hand gestures captured under various conditions.
### Downloading the Dataset
To download the dataset in Google Colab, follow these steps:
```bash
# Install Kaggle API
!pip install kaggle
# Setup Kaggle credentials
!mkdir ~/.kaggle
!mv kaggle.json ~/.kaggle/
!chmod 600 ~/.kaggle/kaggle.json
# Download dataset
!kaggle datasets download gti-upm/leapgestrecog
# Unzip dataset
!unzip /content/leapgestrecog.zip
```
## Getting Started
### Installation
Make sure you have Python 3.x installed along with the following libraries:
```bash
!pip install numpy pandas tensorflow scikit-learn matplotlib seaborn opencv-python
```
### Usage
Data Preprocessing: Images are read, organized, and split into training, validation, and testing sets.
Model Building: A CNN model is constructed using Keras with several convolutional and pooling layers for feature extraction.
Training: The model is trained on the training set and validated on the validation set.
Evaluation: Model performance is evaluated using the testing set, and metrics such as accuracy and a confusion matrix are generated.
## Model Architecture
## Contributor
Subhangi Sati