The goal of this project is to detect and translate American Sign Language (ASL) fingerspelling into text. We will create a model trained on the largest dataset of its kind, released specifically for this project by Google (it is a Kaggle competition). The data includes more than three million fingerspelled characters produced by over 100 Deaf signers captured via the selfie camera of a smartphone with a variety of backgrounds and lighting conditions.

We would be entering the following Kaggle competition: https://www.kaggle.com/competitions/asl-fingerspelling/overview.