GSSoC'24: Web Application for Deaf Community

[vishuhere]

Is your feature request related to a problem? Please describe.

Communication Barrier: One of the primary challenges faced by the Deaf community is the communication barrier, especially when interacting with hearing individuals or accessing content that relies heavily on audio. A web application tailored to the Deaf community can provide alternative communication methods, such as sign language interpretation, text-based chat, or visual representations of information, enabling more effective communication.

Describe the solution you'd like

Many existing web applications are not fully accessible to Deaf individuals. By creating a web application designed with features that cater to their needs, such as providing sign language interpretation, closed captioning, or visual representations of audio content, I will make digital content more accessible to Deaf users.

Describe alternatives you've considered

🔴 Approach: Finding the movements of hands through pre-trained models like media pipe and VITpose then taking the model with the most precise output and then assigning keywords to every movement of actions.

Custom Dataset: I will use my own specific application, I will collect my own dataset by recording hand gestures using a webcam as I have a specific set of gestures relevant to my use case.

Algorithmic steps involved in developing the model through hand gesture recognition:

1. Data Collection: I will Gather a dataset of hand gesture images or videos along with their corresponding labels.
2. Data Preprocessing: I will Preprocess the dataset to ensure uniformity and compatibility, including tasks like resizing images, normalization, and augmentation to increase dataset variability.
3. Feature Extraction: Extract relevant features from the preprocessed images or videos. This may involve Convolutional Neural Networks (CNNs) technique for automatic feature learning.
4. Model Selection: This part will be handled by Conventional Neural Networks (CNN).
5. Model Training: Training the selected model using the Custom dataset.
6. Model Evaluation: Evaluate the trained model's performance on a separate validation or test dataset to assess its accuracy and precision.
7. Deployment: Integrating the model into the website, or embedded system for real-time recognition.

Additional context

Tech use: Python, Tensorflow, Keras, OpenCV 


[TAHIR0110]

@vishuhere assigned!

[vishuhere]

Pull request Created on #132