Chinese Sign Language Recognition Based on an Optimized Tree-Structure Framework

Novel Wearable System to Recognize Sign Language in Real Time

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.

EchoGest: Soft Ultrasonic Waveguides Based Sensing Skin for Subject-Independent Hand Gesture Recognition

Gesture recognition is crucial for enhancing human-computer interaction and is particularly pivotal in rehabilitation contexts, aiding individuals recovering from physical impairments and significantly improving their mobility and interactive capabilities. However, current wearable hand gesture recognition approaches are often limited in detection performance, wearability, and generalization. We thus introduce EchoGest, a novel hand gesture recognition system based on soft, stretchable, transparent artificial skin with integrated ultrasonic waveguides. Our presented system is the first to use soft ultrasonic waveguides for hand gesture recognition. EcoflexTM 00-31 and EcoflexTM 00-45 Near ClearTM silicone elastomers were employed to fabricate the artificial skin and ultrasonic waveguides, while 0.1 mm diameter silver-plated copper wires connected the transducers in the waveguides to the electrical system. The wires are enclosed within an additional elastomer layer, achieving a sensing skin with a total thickness of around 500 μ m. Ten participants wore the EchoGest system and performed static hand gestures from two gesture sets: 8 daily life gestures and 10 American Sign Language (ASL) digits 0-9. Leave-One-Subject-Out Cross-Validation analysis demonstrated accuracies of 91.13% for daily life gestures and 88.5% for ASL gestures. The EchoGest system has significant potential in rehabilitation, particularly for tracking and evaluating hand mobility, which could substantially reduce the workload of therapists in both clinical and home-based settings. Integrating this technology could revolutionize hand gesture recognition applications, from real-time sign language translation to innovative rehabilitation techniques.

User identification system based on 2D CQT spectrogram of EMG with adaptive frequency resolution adjustment

User identification systems based on electromyogram (EMG) signals, generated inside the body in different signal patterns and exhibiting individual characteristics based on muscle development and activity, are being actively researched. However, nonlinear and abnormal signals constrain conventional user identification using EMG signals in improving accuracy by using the 1-D feature from each time and frequency domain. Therefore, multidimensional features containing time-frequency information extracted from EMG signals have attracted much attention to improving identification accuracy. We propose a user identification system using constant Q transform (CQT) based 2D features whose time-frequency resolution is customized according to EMG signals. The proposed user identification system comprises data preprocessing, CQT-based 2D image conversion, convolutional feature extraction, and classification by convolutional neural network (CNN). The experimental results showed that the accuracy of the proposed user identification system using CQT-based 2D spectrograms was 97.5%, an improvement of 15.4% and 2.1% compared to the accuracy of 1D features and short-time Fourier transform (STFT) based user identification, respectively.

From Forearm to Wrist: Deep Learning for Surface Electromyography-Based Gesture Recognition

Though the forearm is the focus of the prostheses, myoelectric control with the electrodes on the wrist is more comfortable for general consumers because of its unobtrusiveness and incorporation with the existing wrist-based wearables. Recently, deep learning methods have gained attention for myoelectric control but their performance is unclear on wrist myoelectric signals. This study compared the gesture recognition performance of myoelectric signals from the wrist and forearm between a state-of-the-art method, TDLDA, and four deep learning models, including convolutional neural network (CNN), temporal convolutional network (TCN), gate recurrent unit (GRU) and Transformer. It was shown that with forearm myoelectric signals, the performance between deep learning models and TDLDA was comparable, but with wrist myoelectric signals, the deep learning models outperformed TDLDA significantly with a difference of at least 9%, while the performance of TDLDA was close between the two signal modalities. This work demonstrated the potential of deep learning for wrist-based myoelectric control and would facilitate its application into more sections.

Sign Language Recognition Using the Electromyographic Signal: A Systematic Literature Review

The analysis and recognition of sign languages are currently active fields of research focused on sign recognition. Various approaches differ in terms of analysis methods and the devices used for sign acquisition. Traditional methods rely on video analysis or spatial positioning data calculated using motion capture tools. In contrast to these conventional recognition and classification approaches, electromyogram (EMG) signals, which measure muscle electrical activity, offer potential technology for detecting gestures. These EMG-based approaches have recently gained attention due to their advantages. This prompted us to conduct a comprehensive study on the methods, approaches, and projects utilizing EMG sensors for sign language handshape recognition. In this paper, we provided an overview of the sign language recognition field through a literature review, with the objective of offering an in-depth review of the most significant techniques. These techniques were categorized in this article based on their respective methodologies. The survey discussed the progress and challenges in sign language recognition systems based on surface electromyography (sEMG) signals. These systems have shown promise but face issues like sEMG data variability and sensor placement. Multiple sensors enhance reliability and accuracy. Machine learning, including deep learning, is used to address these challenges. Common classifiers in sEMG-based sign language recognition include SVM, ANN, CNN, KNN, HMM, and LSTM. While SVM and ANN are widely used, random forest and KNN have shown better performance in some cases. A multilayer perceptron neural network achieved perfect accuracy in one study. CNN, often paired with LSTM, ranks as the third most popular classifier and can achieve exceptional accuracy, reaching up to 99.6% when utilizing both EMG and IMU data. LSTM is highly regarded for handling sequential dependencies in EMG signals, making it a critical component of sign language recognition systems. In summary, the survey highlights the prevalence of SVM and ANN classifiers but also suggests the effectiveness of alternative classifiers like random forests and KNNs. LSTM emerges as the most suitable algorithm for capturing sequential dependencies and improving gesture recognition in EMG-based sign language recognition systems.

A Novel Event-Driven Spiking Convolutional Neural Network for Electromyography Pattern Recognition

Electromyography (EMG) pattern recognition is an important technology for prosthesis control and human-computer interaction etc. However, the practical application of EMG pattern recognition is hampered by poor accuracy and robustness due to electrode shift caused by repeated wearing of the signal acquisition device. Moreover, the user's acceptability is low due to the heavy training burden, which is caused by the need for a large amount of training data by traditional methods. In order to explore the advantage of spiking neural network (SNN) in solving the poor robustness and heavy training burden problems in EMG pattern recognition, a spiking convolutional neural network (SCNN) composed of cyclic convolutional neural network (CNN) and fully connected modules is proposed and implemented in this study. High density surface electromyography (HD-sEMG) signals collected from 6 gestures of 10 subjects at 6 electrode positions are taken as the research object. Compared to CNN with the same structure, CNN-Long Short Term Memory (CNN-LSTM), linear kernel linear discriminant analysis classifier (LDA) and spiking multilayer perceptron (Spiking MLP), the accuracy of SCNN is 50.69%, 33.92%, 32.94% and 9.41% higher in the small sample training experiment, 6.50%, 4.23%, 28.73%, and 2.57% higher in the electrode shifts experiment respectively. In addition, the power consumption of SCNN is about 1/93 of CNN. The advantages of the proposed framework in alleviating user training burden, mitigating the adverse effect of electrode shifts and reducing power consumption make it very meaningful for promoting the development of user-friendly real-time myoelectric control system.

EMG-FRNet: A feature reconstruction network for EMG irrelevant gesture recognition

With the development of deep learning technology, gesture recognition based on surface electromyography (EMG) signals has shown broad application prospects in various human-computer interaction fields. Most current gesture recognition technologies can achieve high recognition accuracy on a wide range of gesture actions. However, in practical applications, gesture recognition based on surface EMG signals is susceptible to interference from irrelevant gesture movements, which affects the accuracy and security of the system. Therefore, it is crucial to design an irrelevant gesture recognition method. This paper introduces the GANomaly network from the field of image anomaly detection into surface EMG-based irrelevant gesture recognition. The network has a small feature reconstruction error for target samples and a large feature reconstruction error for irrelevant samples. By comparing the relationship between the feature reconstruction error and the predefined threshold, we can determine whether the input samples are from the target category or the irrelevant category. In order to improve the performance of EMG irrelevant gesture recognition, this paper proposes a feature reconstruction network named EMG-FRNet for EMG irrelevant gesture recognition. This network is based on GANomaly and incorporates structures such as channel cropping (CC), cross-layer encoding-decoding feature fusion (CLEDFF), and SE channel attention (SE). In this paper, Ninapro DB1, Ninapro DB5 and self-collected datasets were used to verify the performance of the proposed model. The Area Under the receiver operating characteristic Curve (AUC) values of EMG-FRNet on the above three datasets were 0.940, 0.926 and 0.962, respectively. Experimental results demonstrate that the proposed model achieves the highest accuracy among related research.

Light-Weight Deep Learning Techniques with Advanced Processing for Real-Time Hand Gesture Recognition

In the discipline of hand gesture and dynamic sign language recognition, deep learning approaches with high computational complexity and a wide range of parameters have been an extremely remarkable success. However, the implementation of sign language recognition applications for mobile phones with restricted storage and computing capacities is usually greatly constrained by those limited resources. In light of this situation, we suggest lightweight deep neural networks with advanced processing for real-time dynamic sign language recognition (DSLR). This paper presents a DSLR application to minimize the gap between hearing-impaired communities and regular society. The DSLR application was developed using two robust deep learning models, the GRU and the 1D CNN, combined with the MediaPipe framework. In this paper, the authors implement advanced processes to solve most of the DSLR problems, especially in real-time detection, e.g., differences in depth and location. The solution method consists of three main parts. First, the input dataset is preprocessed with our algorithm to standardize the number of frames. Then, the MediaPipe framework extracts hands and poses landmarks (features) to detect and locate them. Finally, the features of the models are passed after processing the unification of the depth and location of the body to recognize the DSL accurately. To accomplish this, the authors built a new American video-based sign dataset and named it DSL-46. DSL-46 contains 46 daily used signs that were presented with all the needed details and properties for recording the new dataset. The results of the experiments show that the presented solution method can recognize dynamic signs extremely fast and accurately, even in real-time detection. The DSLR reaches an accuracy of 98.8%, 99.84%, and 88.40% on the DSL-46, LSA64, and LIBRAS-BSL datasets, respectively.

A Systematic Review of Sensor Fusion Methods Using Peripheral Bio-Signals for Human Intention Decoding

Humans learn about the environment by interacting with it. With an increasing use of computer and virtual applications as well as robotic and prosthetic devices, there is a need for intuitive interfaces that allow the user to have an embodied interaction with the devices they are controlling. Muscle-machine interfaces can provide an intuitive solution by decoding human intentions utilizing myoelectric activations. There are several different methods that can be utilized to develop MuMIs, such as electromyography, ultrasonography, mechanomyography, and near-infrared spectroscopy. In this paper, we analyze the advantages and disadvantages of different myography methods by reviewing myography fusion methods. In a systematic review following the PRISMA guidelines, we identify and analyze studies that employ the fusion of different sensors and myography techniques, while also considering interface wearability. We also explore the properties of different fusion techniques in decoding user intentions. The fusion of electromyography, ultrasonography, mechanomyography, and near-infrared spectroscopy as well as other sensing such as inertial measurement units and optical sensing methods has been of continuous interest over the last decade with the main focus decoding the user intention for the upper limb. From the systematic review, it can be concluded that the fusion of two or more myography methods leads to a better performance for the decoding of a user's intention. Furthermore, promising sensor fusion techniques for different applications were also identified based on the existing literature.

Evaluation of Fast Sample Entropy Algorithms on FPGAs: From Performance to Energy Efficiency

Entropy is one of the most fundamental notions for understanding complexity. Among all the methods to calculate the entropy, sample entropy (SampEn) is a practical and common method to estimate time-series complexity. Unfortunately, SampEn is a time-consuming method growing in quadratic times with the number of elements, which makes this method unviable when processing large data series. In this work, we evaluate hardware SampEn architectures to offload computation weight, using improved SampEn algorithms and exploiting reconfigurable technologies, such as field-programmable gate arrays (FPGAs), a reconfigurable technology well-known for its high performance and power efficiency. In addition to the fundamental disclosed straightforward SampEn (SF) calculation method, this study evaluates optimized strategies, such as bucket-assist (BA) SampEn and lightweight SampEn based on BubbleSort (BS-LW) and MergeSort (MS-LW) on an embedded CPU, a high-performance CPU and on an FPGA using simulated data and real-world electrocardiograms (ECG) as input data. Irregular storage space and memory access of enhanced algorithms is also studied and estimated in this work. These fast SampEn algorithms are evaluated and profiled using metrics such as execution time, resource use, power and energy consumption based on input data length. Finally, although the implementation of fast SampEn is not significantly faster than versions running on a high-performance CPU, FPGA implementations consume one or two orders of magnitude less energy than a high-performance CPU.

Emerging Wearable Interfaces and Algorithms for Hand Gesture Recognition: A Survey

Hands are vital in a wide range of fundamental daily activities, and neurological diseases that impede hand function can significantly affect quality of life. Wearable hand gesture interfaces hold promise to restore and assist hand function and to enhance human-human and human-computer communication. The purpose of this review is to synthesize current novel sensing interfaces and algorithms for hand gesture recognition, and the scope of applications covers rehabilitation, prosthesis control, sign language recognition, and human-computer interaction. Results showed that electrical, dynamic, acoustical/vibratory, and optical sensing were the primary input modalities in gesture recognition interfaces. Two categories of algorithms were identified: 1) classification algorithms for predefined, fixed hand poses and 2) regression algorithms for continuous finger and wrist joint angles. Conventional machine learning algorithms, including linear discriminant analysis, support vector machines, random forests, and non-negative matrix factorization, have been widely used for a variety of gesture recognition applications, and deep learning algorithms have more recently been applied to further facilitate the complex relationship between sensor signals and multi-articulated hand postures. Future research should focus on increasing recognition accuracy with larger hand gesture datasets, improving reliability and robustness for daily use outside of the laboratory, and developing softer, less obtrusive interfaces.

Hand Gesture Recognition based on Surface Electromyography using Convolutional Neural Network with Transfer Learning Method

This paper presents an effective transfer learning (TL) strategy for the realization of surface electromyography (sEMG)-based gesture recognition with high generalization and low training burden. To realize the idea of taking a well-trained model as the feature extractor of the target networks, 30 hand gestures involving various states of finger joints, elbow joint and wrist joint are selected to compose the source task, and a convolutional neural network (CNN)-based source network is designed and trained as the general gesture EMG feature extraction network. Then, two types of target networks, in the forms of CNN-only and CNN+LSTM (long short-term memory) respectively, are designed with the same CNN architecture as the feature extraction network. Finally, gesture recognition experiments on three different target gesture datasets are carried out under TL and Non-TL strategies respectively. The experimental results verify the validity of the proposed TL strategy in improving hand gesture recognition accuracy and reducing training burden. For both the CNN-only and the CNN+LSTM target networks, on the three target datasets from new users, new gestures and different collection scheme, the proposed TL strategy improves the recognition accuracy by 10%∼38%, reduces the training time to tens of times, and guarantees the recognition accuracy of more than 90% when only 2 repetitions of each gesture are used to fine-tune the parameters of target networks. The proposed TL strategy has important application value for promoting the development of myoelectric control systems.

Gesture Recognition Based on Multiscale Singular Value Entropy and Deep Belief Network

As an important research direction of human–computer interaction technology, gesture recognition is the key to realizing sign language translation. To improve the accuracy of gesture recognition, a new gesture recognition method based on four channel surface electromyography (sEMG) signals is proposed. First, the S-transform is applied to four channel sEMG signals to enhance the time-frequency detail characteristics of the signals. Then, multiscale singular value decomposition is applied to the multiple time-frequency matrix output of S-transform to obtain the time-frequency joint features with better robustness. The corresponding singular value permutation entropy is calculated as the eigenvalue to effectively reduce the dimension of multiple eigenvectors. The gesture features are used as input into the deep belief network for classification, and nine kinds of gestures are recognized with an average accuracy of 93.33%. Experimental results show that the multiscale singular value permutation entropy feature is especially suitable for the pattern classification of the deep belief network.

Movement Trajectory Recognition of Sign Language Based on Optimized Dynamic Time Warping

Movement trajectory recognition is the key link of sign language (SL) translation research, which directly affects the accuracy of SL translation results. A new method is proposed for the accurate recognition of movement trajectory. First, the gesture motion information collected should be converted into a fixed coordinate system by the coordinate transformation. The SL movement trajectory is reconstructed using the adaptive Simpson algorithm to maintain the originality and integrity of the trajectory. The algorithm is then extended to multidimensional time series by using Mahalanobis distance (MD). The activation function of generalized linear regression (GLR) is modified to optimize the dynamic time warping (DTW) algorithm, which ensures that the local shape characteristics are considered for the global amplitude characteristics and avoids the problem of abnormal matching in the process of trajectory recognition. Finally, the similarity measure method is used to calculate the distance between two warped trajectories, to judge whether they are classified to the same category. Experimental results show that this method is effective for the recognition of SL movement trajectory, and the accuracy of trajectory recognition is 86.25%. The difference ratio between the inter-class features and intra-class features of the movement trajectory is 20, and the generalization ability of the algorithm can be effectively improved.

Wearable Sensor-Based Sign Language Recognition: A Comprehensive Review

Sign language is used as a primary form of communication by many people who are Deaf, deafened, hard of hearing, and non-verbal. Communication barriers exist for members of these populations during daily interactions with those who are unable to understand or use sign language. Advancements in technology and machine learning techniques have led to the development of innovative approaches for gesture recognition. This literature review focuses on analyzing studies that use wearable sensor-based systems to classify sign language gestures. A review of 72 studies from 1991 to 2019 was performed to identify trends, best practices, and common challenges. Attributes including sign language variation, sensor configuration, classification method, study design, and performance metrics were analyzed and compared. Results from this literature review could aid in the development of user-centred and robust wearable sensor-based systems for sign language recognition.

A Novel Surface Electromyographic Signal-Based Hand Gesture Prediction Using a Recurrent Neural Network

Surface electromyographic signal (sEMG) is a kind of bioelectrical signal, which records the data of muscle activity intensity. Most sEMG-based hand gesture recognition, which uses machine learning as the classifier, depends on feature extraction of sEMG data. Recently, a deep leaning-based approach such as recurrent neural network (RNN) has provided a choice to automatically learn features from raw data. This paper presents a novel hand gesture prediction method by using an RNN model to learn from raw sEMG data and predict gestures. The sEMG signals of 21 short-term hand gestures of 13 subjects were recorded with a Myo armband, which is a non-intrusive, low cost, commercial portable device. At the start of the gesture, the trained model outputs an instantaneous prediction for the sEMG data. Experimental results showed that the more time steps of data that were known, the higher instantaneous prediction accuracy the proposed model gave. The predicted accuracy reached about 89.6% when the data of 40-time steps (200 ms) were used to predict hand gesture. This means that the gesture could be predicted with a delay of 200 ms after the hand starts to perform the gesture, instead of waiting for the end of the gesture.

Exploration of Chinese Sign Language Recognition Using Wearable Sensors Based on Deep Belief Net

In this paper, deep belief net (DBN) was applied into the field of wearable-sensor based Chinese sign language (CSL) recognition. Eight subjects were involved in the study, and all of the subjects finished a five-day experiment performing CSL on a target word set consisting of 150 CSL subwords. During the experiment, surface electromyography (sEMG), accelerometer (ACC), and gyroscope (GYRO) signals were collected from the participants. In order to obtain the optimal structure of the network, three different sensor fusion strategies, including data-level fusion, feature-level fusion, and decision-level fusion, were explored. In addition, for the feature-level fusion strategy, two different feature sources, which are hand-crafted features and network generated features, and two different network structures, which are fully-connected net and DBN, were also compared. The result showed that feature level fusion could achieve the best recognition accuracy among the three fusion strategies, and feature-level fusion with network generated features and DBN could achieve the best recognition accuracy. The best recognition accuracy realized in this study was 95.1% for the user-dependent test and 88.2% for the user-independent test. The significance of the study is that it applied the deep learning method into the field of wearable sensors-based CSL recognition, and according to our knowledge it's the first study comparing human engineered features with the network generated features in the correspondent field. The results from the study shed lights on the method of using network-generated features during sensor fusion and CSL recognition.

Real-Time Surface EMG Pattern Recognition for Hand Gestures Based on an Artificial Neural Network

In recent years, surface electromyography (sEMG) signals have been increasingly used in pattern recognition and rehabilitation. In this paper, a real-time hand gesture recognition model using sEMG is proposed. We use an armband to acquire sEMG signals and apply a sliding window approach to segment the data in extracting features. A feedforward artificial neural network (ANN) is founded and trained by the training dataset. A test method is used in which the gesture will be recognized when recognized label times reach the threshold of activation times by the ANN classifier. In the experiment, we collected real sEMG data from twelve subjects and used a set of five gestures from each subject to evaluate our model, with an average recognition rate of 98.7% and an average response time of 227.76 ms, which is only one-third of the gesture time. Therefore, the pattern recognition system might be able to recognize a gesture before the gesture is completed.

An Recognition-Verification Mechanism for Real-Time Chinese Sign Language Recognition Based on Multi-Information Fusion

For online sign language recognition (SLR) based on inertial measurement unit (IMU) and a surface electromyography (sEMG) sensor, achieving high-accuracy is a major challenge. The traditional method for that is the segmentation–recognition mechanism, which has two key challenges: (1) it is difficult to design a highly robust segmentation method for online data with inconspicuous segmentation information; and (2) the diversity of input data will increase the burden of the classification. The recognition–verification mechanism was proposed to improve the performance of online SLR. In the recognition stage, we used sliding windows to pull the data, and applied a convolutional neural network (CNN) to classify the sign language signal. In the verification stage, the confidence was evaluated by the Siamese network to judge the correctness of the classification results. The accuracy and rapidity of the classification model were discussed for 86 categories of Chinese sign language. In the experiments for online SLR, the superiority of the recognition–verification mechanism compared to the segmentation–recognition mechanism was verified.

Deep Forest-Based Monocular Visual Sign Language Recognition

Sign language recognition (SLR) is a bridge linking the hearing impaired and the general public. Some SLR methods using wearable data gloves are not portable enough to provide daily sign language translation service, while visual SLR is more flexible to work with in most scenes. This paper introduces a monocular vision-based approach to SLR. Human skeleton action recognition is proposed to express semantic information, including the representation of signs’ gestures, using the regularization of body joint features and a deep-forest-based semantic classifier with a voting strategy. We test our approach on the public American Sign Language Lexicon Video Dataset (ASLLVD) and a private testing set. It proves to achieve a promising performance and shows a high generalization capability on the testing set.

Synergistic Myoelectrical Activities of Forearm Muscles Improving Robust Recognition of Multi-Fingered Gestures

Currently, surface electromyography (sEMG) features of the forearm multi-tendon muscles are widely used in gesture recognition, however, there are few investigations on the inherent physiological mechanism of muscle synergies. We aimed to study whether the muscle synergies could be used for gesture recognition. Five healthy participants executed five gestures of daily life (pinch, fist, open hand, grip, and extension) and the sEMG activity was acquired from six forearm muscles. A non-negative matrix factorization (NMF) algorithm was employed to decompose the pre-treated six-channel sEMG data to obtain the muscle synergy matrixes, in which the weights of each muscle channel determined the feature set for hand gesture classification. The results showed that the synergistic features of forearm muscles could be successfully clustered in the feature space, which enabled hand gestures to be recognized with high efficiency. By augmenting the number of participants, the mean recognition rate remained at more than 96% and reflected high robustness. We showed that muscle synergies can be well applied to gesture recognition.