Skip to content

TheSOV/ASL-Alphabets-DeepLearning-vs-ClassicComputerVision

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

22 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Real-time-detection-of-ASL-Alphabets

Project Description:

Comparation of the performance of Classical Computer Vision vs Deep Learning in signs recognition.

Dataset:

Link to the dataset - https://www.kaggle.com/grassknoted/asl-alphabet

The dataset contains 87000 images with a dimension of 200×200. There are 29 classes in total. 26 of these classes are letters from A-Z. Then there are three more classes that correspond to SPACE, DELETE, and NOTHING. There are 3000 images from each class.

Since the dataset is very large, it will take much more time and resources to train the model. Hence only a subset is used.

Tools used:

  • Pytorch : Creates customised CNN model
  • OpenCV : For processing images and real-time capture

About

Comparative of DeepLearning and Classic Computer Vision in the detection of American Sign language alphabets.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 99.4%
  • Python 0.6%