Overview / Usage

Emojis are ideograms and smileys used in electronic messages and web pages. Emoji exist in various genres, including facial expressions, common objects, places and types of weather, and animals.

This project aims to localize your hand gestures and interpret them to an emoji representation. This technology can be further rendered for translating sign language. Since we are working with a live stream of data, we want to make sure that the predictions are made at runtime. For doing this efficiently, we use several filters to downsize the image that in turn, increases the efficiency. For building a predictive model, we use deep learning technique to train and develop a model which could do the needful consuming the minimum amount of CPU resources.

Methodology / Approach

Procedure

1. First, you have to create a gesture database. For that, run CreateGest.py. Enter the gesture name and you will get 2 frames displayed. Look at the contour frame and adjust your hand to make sure that you capture the features of your hand. Press 'c' for capturing the images. It will take 1200 images of one gesture. Try moving your hand a little within the frame to make sure that your model doesn't overfit at the time of training.
2. Repeat this for all the features you want.
3. Run CreateCSV.py for converting the images to a CSV file
4. If you want to train the model, run 'TrainEmojinator.py'
5. Finally, run Emojinator.py for testing your model via webcam.

Functionalities
- Image processing filters to detect hand.
- CNN for training the model.

Network Used - Convolutional Neural Network

Technologies Used

Hardware Used
- Intel Powered PC (Intel i3).

Technologies Used -
- Intel Optimised Python.
- Intel Optimised TensorFlow.
- Keras
- OpenCV

Repository

https://github.com/akshaybahadur21/Emojinator

Other links

• Portfolio