Key points are not available for this paper at this time.
In this paper, a system for enhancing communication between sign language users and non-users is presented. The system recognizes and converts sign language into text and voice using picture data collected by a computer webcam. A masking approach is used to preprocess the picture data, then a Convolutional Neural Network (CNN) algorithm is used for feature extraction and classification. The system was trained using a dataset of masked images representing the 26 letters of the English alphabet, totaling 45500 images for training and 6500 images for testing. The system's goal is to make it simpler for those who use sign language and those who do not to communicate with one another. Keywords: Hand Gesture Recognition, Feature Extraction, Pre-Processing, Classification, CNN.
Harikrishnan et al. (2023) studied this question.