American Sign Language (ASL) Detection System using Machine Learning

Abstract

One of the main challenges of communicating with people who have hearing disabilities is to understand their sign language. This paper presents a dedicated research project to investigate the difficulties involved in recognizing characters in American Sign Language (ASL), which is the most widely used sign language in the world. Sign language is essential for communication among people with hearing or speech impairments, but it can be hard for those who are not familiar with it, as the signs made by people with disabilities may look complicated or messy. Effective communication requires a two-way exchange. This paper proposes a Sign Language detection system that uses American Sign Language, where users can take pictures of hand gestures through a web camera and get them analyzed. The system aims to predict and show the name that matches the picture. The proposed research proposes a method for detecting sign language that uses the collaborative features of the OpenCV and MediaPipe frameworks. The Convolutional Neural Network (CNN) is used to train the model and identify the pictures. The proposed methodshows a high detection rate and excellent accuracy. Keywords: American Sign Language, OpenCV, MediaPipe, Convolutional Neural Network

Sign Language Detection Using CNN and LSTM Based Model

“…Convolutional Neural Networks (commonly referred to as CNNs or ConvNets) [6] are a subclass of neural networks that are particularly well-suited for processing data with grid-like topologies, such as image data. A binary representation of visual data is a digital picture.…”

“…

In the context of our current work, we have taken a major step in examining and contrasting the effectiveness of several machine learning models for sign language recognition. Convolutional Neural Network (CNN) model building was the focus of our minor project, which resulted in the successful publication of a research paper [6]. Our method was validated by this model, which showed significant accuracy in recognizing sign language.We wanted to build a Long Short-Term Memory (LSTM) model for the same reason as we moved on to our larger project.

…”