Search

Sign language is a crucial mode of communication for individuals who are deaf or hard-of-hearing, and a reliable sign language recognition system can greatly aid in bridging the communication gap. According to statistics provided by the Government of India, there are only around 250 accredited sign language interpreters in India, servicing a deaf population of 1.8 million to 7 million individuals. This paper presents a real-time sign language recognition system for Indian Sign Language (ISL) using YOLOv8 for object detection. The system uses a single convolutional neural network (CNN) architecture to process the entire image in one forward pass and predict the bounding boxes and class probabilities for each sign in the image. The results of the study demonstrate the feasibility and potential of the system in revolutionizing communication for the deaf and hard of hearing community and have applications in gesture-controlled robotics, home automation, game control, human-computer interaction, and sign language interpretation. [ABSTRACT FROM AUTHOR]

This paper discusses the importance of communication for human interaction, especially for individuals with hearing impairments who rely on sign language. However, learning sign language is not easy, and not many people are familiar with it. To bridge the communication gap between deaf individuals and the general public, this study focuses on developing a deep convolutional neural network (CNN) model to recognize sign language patterns, specifically SIBI Sign Language used for formal activities. The VGG16 architecture is employed, which has been trained on a sign language dataset with 1440 images. The results show an accuracy of over 98.32% in training data. This research demonstrates how technology, particularly deep learning and computer vision, can help solve communication problems and improve accessibility for individuals with hearing impairments. [ABSTRACT FROM AUTHOR]

Sign language is a method for the dumb and deaf society to connect with the exterior world. The dumb and deaf people find it very difficult to express their feelings to the normal people, since the normal people have the insufficiency knowledge of the sign language used by the mute and deaf people. Thus the development of a system to fill the communication gap in between mute/deaf and the normal people who are well able to speak and hear would be of great utility to the society. A sign language recognition model involves of accurate and effective tool to translate sign language into text/speech. Gesture recognition identifies a significant expressions of a man-made gesture by hands. Gesture identification from video sequences has significant deviations in the field of behavioral understanding and computer vision. This will provides a platform for conversion of predictable gestures in sentences that are cumulative of words used in an approved sequence. With the advance of deep learning, artificial intelligence has completed significant achievement in modern growths in gesture recognition technology for videos based on deep learning. As compare to others gesture recognition methods, dynamic hand gesture recognition using deep learning to progress the recognition accuracy. This paper presents a research gap survey on various hand gesture recognition methods. Hand gestures are categorized in two types-1) Static hand gestures and 2) Dynamic hand gestures. The first type as static hand gesture recognition is the fingerspelling level detection of alphabets, words and numbers. The second type as dynamic hand gesture recognition are used for identification of sign language sentences. Sign language recognition systems using gesture play a significant part in Human-computer interaction (HCI) to establish communication between dumb/deaf societies and normal people. In this paper, a literature review on hand gesture recognition methods are presented. [ABSTRACT FROM AUTHOR]

As a result of different physiological and accidentals causes for the inability of a man to speak. It becomes necessary to develop an efficient user-friendly technique to translate visual sign language into speech. In this paper, a visual-based translator is proposed as a hand gesture classification model. Region of interest (ROI) and hand segmentation is performed using a mask Region-based Convolutional Neural Network (R-CNN). The classification model is trained using a large number of gestures dataset using Convolutional Neural Network (CNN) deep learning and hosted in a web server. The system has realized a high accuracy of 99.79% and a loss of 0.0096. The trained model is loaded from the server to an internet browser using a special JavaScript library. The hand gesture is captured using a smart device camera and applied to the model to provide a real-time prediction. [ABSTRACT FROM AUTHOR]