Give A Hand

Baggrund

Technology has revolutionized the way we communicate, breaking down barriers across languages and enabling greater connection and understanding, ultimately leading to more inclusion. Together with the American Society for Deaf Children (ASDC) we launched GiveAHand.ai, with the aim to build the world’s largest open-source dataset image library of hands fully tagged with data to help build better machine learning hand models.

Live audio transcription and translation tools have limitations for the deaf and hard-of-hearing due to sign language's complex combination of fast-paced hand gestures, facial expressions, and full body movements. While machine learning models can handle facial expressions and body movements, detecting hand and finger movements remains a challenge. AI is on the rise and democratizing access to data so it can be used in limitless ways. But since most available tools are trained on pre-existing data and images, it’s difficult to build useful machine learning models from sources that aren’t readily available.

Løsning

GiveAHand.ai is using tech for good. One hundred percent crowdsourced, the data collected in the platform will generate a diverse dataset of hands: diverse shapes, colors, backgrounds and gestures.

Now, anyone can put their hands to good use, by contributing and uploading images, helping to build an image library that will help unlock sign language.

1. Users load the website

2. Through their webcam they take a picture of one of their hands and crop the image in the built in image tool

3. We store the fully anonymised image data and manually tag the tracking points in the hand.

4. Once tagged, the image data becomes part of the growing open source dataset and can be browsed on the website by anyone.

5.Researchers will have access to download and use these fully tagged images to improve their machine learning models, truly allowing the detection and translation of the full spectrum of Sign Language.