Classification of Electromyographic Hand Gesture Signals Using Modified Fuzzy C-Means Clustering and Two-Step Machine Learning Approach

Very few people understand sign language as it is not an international language. This makes it difficult for the majority of hearing communities to communicate with the deaf community. Hence automatic recognition system is a new way of understanding the meaning of deaf signs without needing the help of expert. This technique can be used to translate signs into texts based on the users‟ needs. In this paper, we are recognizing the signs through the hand gestures using Convolution Neural Network (CNN) from the deep learning and with the help of OpenCV. Here, CNN is used to train the dataset and OpenCV is used to capture the hand gestures. In this proposed model we are mainly recognizing the numerical sign hand gestures.

Keywords: Hand gestures, deep learning, CNN, OpenCV