Our project Drishti is basically a gesture to speech convertor. The general definition of gesture recognition is the ability of a computer to understand gestures and execute commands based on those gestures.
The reason for naming this project Drishti is because we made the use of "Drishti"(Vision) of machines to recognize the hand gestures of the subject (in our case a person) and predict the corresponding alphabet. We have also made the use of text to speech convertor to provide a voice enabled output.
The input for this project is the MNIST Gesture recognition dataset.
The American Sign Language letter database of hand gestures represent a multi-class problem with 24 classes of letters (excluding J and Z which require motion) and follows the same CSV format with labels and pixel values in single rows.
- Creating a deep learning model for hand gesture classification.
- Being able to extract and isolate the hand gestures as images from OpenCV frames and apply the DL model to the images and return the frames.
- Using flask to create the web app for this project.
- Managing the version conflicts in anaconda.
- Python 3.8
- Tensorflow
- Numpy
- Keras
- Flask
- OpenCV
- Mediapipe
- PIL
- Matplotlib
Note : The steps have been mentioned keeping in mind that anaconda is installed on your machine.
- Since, we have made the use of very large input files; Therefore, please the type the following commands on git to ensure that the files are downloaded smoothly.
git lfs install
git lfs track "*.csv"
- Clone this repository using command.
git clone "https://github.com/DedSec-1/Drishti"
- Open anaconda Prompt and type the following commands to create a new environment and activate it.
conda create --name <env_name> python=3.8
conda activate <env_name>
- Now the change the directory to the location of cloned directory using the following command.
cd <directory_path>
- Now install all the dependencies for this project using the command
pip install -r requirements.txt
The dependencies should be installed without any error. If error occurs then manually install the libraries.
- Now run the following command to run the program
python main.py
If everything worked so far then you will be able to see something similar to : LOCALHOST:PORT or 0.0.0.0:8080 or http://127.0.0.1:5000/, etc.
- Copy and paste the link in the browser.
- The output should look like the one given below.