Continuous Sign Language Recognition (CSLR) is a task which converts a sign language video into a gloss sequence. The existing deep learning based sign language recognition methods usually rely on large-scale training data and rich supervised information. However, current sign language datasets are limited, and they are only annotated at sentence-level rather than frame-level. Inadequate supervision of sign language data poses a serious challenge for sign language recognition, which may result in insufficient training of sign language recognition models. To address above problems, we propose a cross-modal knowledge distillation method for continuous sign language recognition, which contains two teacher models and one student model. One of the teacher models is the Sign2Text dialogue teacher model, which takes a sign language video and a dialogue sentence as input and outputs the sign language recognition result. The other teacher model is the Text2Gloss translation teacher model, which targets to translate a text sentence into a gloss sequence. Both teacher models can provide information-rich soft labels to assist the training of the student model, which is a general sign language recognition model. We conduct extensive experiments on multiple commonly used sign language datasets, i.e., PHOENIX 2014T, CSL-Daily and QSL, the results show that the proposed cross-modal knowledge distillation method can effectively improve the sign language recognition accuracy by transferring multi-modal information from teacher models to the student model. Code is available at https://github.com/glq-1992/cross-modal-knowledge-distillation_new.

Hand gestures are a natural and intuitive form of communication, and integrating this communication method into robotic systems presents significant potential to improve human-robot collaboration. Recent advances in motor neuroscience have focused on replicating human hand movements from synergies also known as movement primitives. Synergies, fundamental building blocks of movement, serve as a potential strategy adapted by the central nervous system to generate and control movements. Identifying how synergies contribute to movement can help in dexterous control of robotics, exoskeletons, prosthetics and extend its applications to rehabilitation. In this paper, 33 static hand gestures were recorded through a single RGB camera and identified in real-time through the MediaPipe framework as participants made various postures with their dominant hand. Assuming an open palm as initial posture, uniform joint angular velocities were obtained from all these gestures. By applying a dimensionality reduction method, kinematic synergies were obtained from these joint angular velocities. Kinematic synergies that explain 98% of variance of movements were utilized to reconstruct new hand gestures using convex optimization. Reconstructed hand gestures and selected kinematic synergies were translated onto a humanoid robot, Mitra, in real-time, as the participants demonstrated various hand gestures. The results showed that by using only few kinematic synergies it is possible to generate various hand gestures, with 95.7% accuracy. Furthermore, utilizing low-dimensional synergies in control of high dimensional end effectors holds promise to enable near-natural human-robot collaboration.

The aim of this study is to develop a practical software solution for real-time recognition of sign language words using two arms. This will facilitate communication between hearing-impaired individuals and those who can hear. We are aware of several sign language recognition systems developed using different technologies, including cameras, armbands, and gloves. However, the system we propose in this study stands out for its practicality, utilizing surface electromyography (muscle activity) and inertial measurement unit (motion dynamics) data from both arms. We address the drawbacks of other methods, such as high costs, low accuracy due to ambient light and obstacles, and complex hardware requirements, which have limited their practical application. Our software can run on different operating systems using digital signal processing and machine learning methods specific to this study. For the test, we created a dataset of 80 words based on their frequency of use in daily life and performed a thorough feature extraction process. We tested the recognition performance using various classifiers and parameters and compared the results. The random forest algorithm emerged as the most successful, achieving a remarkable 99.875% accuracy, while the naïve Bayes algorithm had the lowest success rate with 87.625% accuracy. The new system promises to significantly improve communication for people with hearing disabilities and ensures seamless integration into daily life without compromising user comfort or lifestyle quality.

Flexible strain sensors have been widely researched in fields such as smart wearables, human health monitoring, and biomedical applications. However, achieving a wide sensing range and high sensitivity of flexible strain sensors simultaneously remains a challenge, limiting their further applications. To address these issues, a cross-scale combinatorial bionic hierarchical design featuring microscale morphology combined with a macroscale base to balance the sensing range and sensitivity is presented. Inspired by the combination of serpentine and butterfly wing structures, this study employs three-dimensional printing, prestretching, and mold transfer processes to construct a combinatorial bionic hierarchical flexible strain sensor (CBH-sensor) with serpentine-shaped inverted-V-groove/wrinkling-cracking structures. The CBH-sensor has a high wide sensing range of 150% and high sensitivity with a gauge factor of up to 2416.67. In addition, it demonstrates the application of the CBH-sensor array in sign language gesture recognition, successfully identifying nine different sign language gestures with an impressive accuracy of 100% with the assistance of machine learning. The CBH-sensor exhibits considerable promise for use in enabling unobstructed communication between individuals who use sign language and those who do not. Furthermore, it has wide-ranging possibilities for use in the field of gesture-driven interactions in human-computer interfaces.

Addressing the increasing demand for accessible sign language learning tools, this paper introduces an innovative Machine Learning-Driven Web Application dedicated to Sign Language Learning. This web application represents a significant advancement in sign language education. Unlike traditional approaches, the application\'s unique methodology involves assigning users different words to spell. Users are tasked with signing each letter of the word, earning a point upon correctly signing the entire word. The paper delves into the development, features, and the machine learning framework underlying the application. Developed using HTML, CSS, JavaScript, and Flask, the web application seamlessly accesses the user\'s webcam for a live video feed, displaying the model\'s predictions on-screen to facilitate interactive practice sessions. The primary aim is to provide a learning platform for those who are not familiar with sign language, offering them the opportunity to acquire this essential skill and fostering inclusivity in the digital age.

Sign language recognition technology can help people with hearing impairments to communicate with non-hearing-impaired people. At present, with the rapid development of society, deep learning also provides certain technical support for sign language recognition work. In sign language recognition tasks, traditional convolutional neural networks used to extract spatio-temporal features from sign language videos suffer from insufficient feature extraction, resulting in low recognition rates. Nevertheless, a large number of video-based sign language datasets require a significant amount of computing resources for training while ensuring the generalization of the network, which poses a challenge for recognition. In this paper, we present a video-based sign language recognition method based on Residual Network (ResNet) and Long Short-Term Memory (LSTM). As the number of network layers increases, the ResNet network can effectively solve the granularity explosion problem and obtain better time series features. We use the ResNet convolutional network as the backbone model. LSTM utilizes the concept of gates to control unit states and update the output feature values of sequences. ResNet extracts the sign language features. Then, the learned feature space is used as the input of the LSTM network to obtain long sequence features. It can effectively extract the spatio-temporal features in sign language videos and improve the recognition rate of sign language actions. An extensive experimental evaluation demonstrates the effectiveness and superior performance of the proposed method, with an accuracy of 85.26%, F1-score of 84.98%, and precision of 87.77% on Argentine Sign Language (LSA64).

This article presents an innovative approach for the task of isolated sign language recognition (SLR); this approach centers on the integration of pose data with motion history images (MHIs) derived from these data. Our research combines spatial information obtained from body, hand, and face poses with the comprehensive details provided by three-channel MHI data concerning the temporal dynamics of the sign. Particularly, our developed finger pose-based MHI (FP-MHI) feature significantly enhances the recognition success, capturing the nuances of finger movements and gestures, unlike existing approaches in SLR. This feature improves the accuracy and reliability of SLR systems by more accurately capturing the fine details and richness of sign language. Additionally, we enhance the overall model accuracy by predicting missing pose data through linear interpolation. Our study, based on the randomized leaky rectified linear unit (RReLU) enhanced ResNet-18 model, successfully handles the interaction between manual and non-manual features through the fusion of extracted features and classification with a support vector machine (SVM). This innovative integration demonstrates competitive and superior results compared to current methodologies in the field of SLR across various datasets, including BosphorusSign22k-general, BosphorusSign22k, LSA64, and GSL, in our experiments.

Deaf and hard-of-hearing people mainly communicate using sign language, which is a set of signs made using hand gestures combined with facial expressions to make meaningful and complete sentences. The problem that faces deaf and hard-of-hearing people is the lack of automatic tools that translate sign languages into written or spoken text, which has led to a communication gap between them and their communities. Most state-of-the-art vision-based sign language recognition approaches focus on translating non-Arabic sign languages, with few targeting the Arabic Sign Language (ArSL) and even fewer targeting the Saudi Sign Language (SSL). This paper proposes a mobile application that helps deaf and hard-of-hearing people in Saudi Arabia to communicate efficiently with their communities. The prototype is an Android-based mobile application that applies deep learning techniques to translate isolated SSL to text and audio and includes unique features that are not available in other related applications targeting ArSL. The proposed approach, when evaluated on a comprehensive dataset, has demonstrated its effectiveness by outperforming several state-of-the-art approaches and producing results that are comparable to these approaches. Moreover, testing the prototype on several deaf and hard-of-hearing users, in addition to hearing users, proved its usefulness. In the future, we aim to improve the accuracy of the model and enrich the application with more features.

Sign Language Recognition (SLR) is crucial for enabling communication between the deaf-mute and hearing communities. Nevertheless, the development of a comprehensive sign language dataset is a challenging task due to the complexity and variations in hand gestures. This challenge is particularly evident in the case of Bangla Sign Language (BdSL), where the limited availability of depth datasets impedes accurate recognition. To address this issue, we propose BdSL47, an open-access depth dataset for 47 one-handed static signs (10 digits, from ০ to ৯; and 37 letters, from অ to ँ) of BdSL. The dataset was created using the MediaPipe framework for extracting depth information. To classify the signs, we developed an Artificial Neural Network (ANN) model with a 63-node input layer, a 47-node output layer, and 4 hidden layers that included dropout in the last two hidden layers, an Adam optimizer, and a ReLU activation function. Based on the selected hyperparameters, the proposed ANN model effectively learns the spatial relationships and patterns from the depth-based gestural input features and gives an F1 score of 97.84 %, indicating the effectiveness of the approach compared to the baselines provided. The availability of BdSL47 as a comprehensive dataset can have an impact on improving the accuracy of SLR for BdSL using more advanced deep-learning models.

Sign language is a form of communication medium for speech and hearing disabled people. It has various forms with different troublesome patterns, which are difficult for the general mass to comprehend. Bengali sign language (BdSL) is one of the difficult sign languages due to its immense number of alphabet, words, and expression techniques. Machine translation can ease the difficulty for disabled people to communicate with generals. From the machine learning (ML) domain, computer vision can be the solution for them, and every ML solution requires a optimized model and a proper dataset. Therefore, in this research work, we have created a BdSL dataset and named `KU-BdSL\', which consists of 30 classes describing 38 consonants (\'banjonborno\') of the Bengali alphabet. The dataset includes 1500 images of hand signs in total, each representing Bengali consonant(s). Thirty-nine participants (30 males and 9 females) of different ages (21-38 years) participated in the creation of this dataset. We adopted smartphones to capture the images due to the availability of their high-definition cameras. We believe that this dataset can be beneficial to the deaf and dumb (D&D) community. Identification of Bengali consonants of BdSL from images or videos is feasible using the dataset. It can also be employed for a human-machine interface for disabled people. In the future, we will work on the vowels and word level of BdSL.