Projects / Computer Science / Computer Science project 39

Indian Sign Language to Text Translator

Approx. component budget: Rs. 0 - 2,000

Objective

Help a hearing-impaired person communicate with others, and measure accuracy with signers of different hand sizes.

What you will build

A tool that recognises hand signs for letters, numbers and common words in Indian Sign Language from a webcam and shows the text.

Results you can expect

• Accuracy on a held-out set of signers
• Per-sign confusion table
• Words per minute achievable
• Latency
• And feedback from at least 3 test users

What you will learn

Hand landmarks, sequence models, building a dataset, and designing with the users, not just for them.

Tools and notes

Python, MediaPipe, OpenCV, TensorFlow/Keras (LSTM or a simple MLP). Work with a teacher or a signer for correct signs.

Resume points from this project

• Built and tested Indian Sign Language to Text Translator; objective: help a hearing-impaired person communicate with others, and measure accuracy with signers of different hand sizes.
• Measured and analysed accuracy on a held-out set of signers and per-sign confusion table; wrote the report and presented the results in a viva. Add your own numbers: [x].

Replace [x] with your own measured results. Write only what you really did.

More computer science projects

Back to all projects