Skip to content

✋In the Hand Gesture Recognition System project, we aim to develop a comprehensive machine learning pipeline capable of accurately classifying hand gestures into six digits (0 to 5). Our system is designed to handle variations in lighting effects and hand poses, ensuring robust performance in real-world scenarios.

Notifications You must be signed in to change notification settings

norhanreda/neural-project

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

67 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

📝 Table of Contents

About

In the Hand Gesture Recognition System project, we aim to develop a comprehensive machine learning pipeline capable of accurately classifying hand gestures into six digits (0 to 5). Our system is designed to handle variations in lighting effects and hand poses, ensuring robust performance in real-world scenarios.

Description

The project includes the following key modules:

  • Data Acquisition: To train and evaluate our system, we collect a dataset of hand gesture images. We capture images containing a single hand with different gestures, ensuring diversity in lighting conditions and hand poses. The dataset serves as the foundation for subsequent stages of the pipeline.
  • Preprocessing: Preprocess the images to enhance the quality and normalize them. Common preprocessing techniques include resizing the images to a consistent size, converting them to grayscale, applying image filters, and normalizing pixel values.
  • Feature Extraction: Here we used different features and calculate their efficiency in detecting digits, These features serve as input for the subsequent classification module.
  • Classification Model: We train a machine learning model to classify hand gestures into the six digit categories (0 to 5). Various classification algorithms can be employed, such as Support Vector Machines (SVMs), or Random Forests. The model is trained using the preprocessed images and their corresponding labels.
  • Training and Evaluation: We split the dataset into training and validation sets. The model is trained using the training set, and the hyperparameters are fine-tuned to optimize performance. The validation set is used to evaluate the model's accuracy, precision, recall, and F1-score. Iterative training and evaluation help improve the model's performance.

Project Pipeline

image

Hand Mask

image

image

image

Accuracies

image

image

image

Contributors

Asmaa Adel
Asmaa Adel
Asmaa Adel
Samaa Hazem
norhan reda
Norhan reda
HodaGamal
HodaGamal

About

✋In the Hand Gesture Recognition System project, we aim to develop a comprehensive machine learning pipeline capable of accurately classifying hand gestures into six digits (0 to 5). Our system is designed to handle variations in lighting effects and hand poses, ensuring robust performance in real-world scenarios.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages