Using Image Processing Techniques and HD-EMG for Upper Limb Prosthesis Gesture Recognition

Díaz-Amador, Roberto; Ferrer, Carlos A.; Lorenzo-Ginori, Juan V.

doi:10.1007/978-3-030-13469-3_105

Cited by 6 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The high classification accuracy of AIH and AI confirms the robustness of the proposed features in inter-session assessment. To show the superiority of the proposed spatial features, a comparison is made between the performance of the SVM classifier with proposed features (AI, AIH features) and those presented in [53]. The same databases and evaluation procedure of the previous work are used in this experiment.…”

Section: Simulation and Resultsmentioning

confidence: 99%

“…The same databases and evaluation procedure of the previous work are used in this experiment. The researchers in [53] used an instantaneous image from recorded HD-sEMG signals with a K nearest neighbor (KNN) classifier for gesture classification. It is observed that the performance of the SVM classifier with the proposed AI and AIH features is superior to that in [53], as shown in Table II.…”

Section: Simulation and Resultsmentioning

confidence: 99%

“…The researchers in [53] used an instantaneous image from recorded HD-sEMG signals with a K nearest neighbor (KNN) classifier for gesture classification. It is observed that the performance of the SVM classifier with the proposed AI and AIH features is superior to that in [53], as shown in Table II. The True positive rate (TPR) is improved by 5% and 6.3%, the precision is improved by 5.8% and 5.6%, and F1-score is improved by 4.4% and 4.5% for AIH and AI features, respectively.…”

Section: Simulation and Resultsmentioning

confidence: 99%

See 2 more Smart Citations

Incremental Adaptive Gesture Classifier for Upper Limb Prostheses

et al. 2022

View full text Add to dashboard Cite

Myoelectric pattern recognition is widely used to control upper limb prostheses. However, the non-stationary characteristics of electromyography (EMG) signals, caused by physiological changes (e.g. muscle fatigue) or nonphysiological changes (e.g. the electrode-skin impedance), hinder the use of prostheses and deteriorate the performance of the myoelectric control system. In this paper, a set of robust features is proposed to be integrated with adaptive learning techniques in order to improve the myoelectric performance. Four types of features are proposed, namely the H, HI, AI, and AIH features. The H features correspond to the histogram-oriented gradient (HOG) algorithm of the High-Density surface Electromyography map (HD-sEMG map). On the other hand, the HI features are generated by combining the H features and the intensity feature that is evaluated from the HD-sEMG map. AI is the intensity features calculated from the segmented HD-sEMG maps constructed in the individual channel. Finally, AIH features are obtained by combining the H features and AI features. Offline and online adaptive tests are conducted to evaluate the proposed features. The results show that employing the proposed AI features with an adaptive classifier improves the classification accuracy from 91.58% to 97.2% in online classification setups. Results also show that the AI features are more robust against noise than TD features. The average classification accuracy is reduced by 0.7% when additive White Gaussian noise is applied, in comparison to 5.8% reduction in accuracy when TD features is used. The results confirm the robustness of the proposed features extracted from the HD-sEMG map.

show abstract

Section: Simulation and Resultsmentioning

confidence: 99%

Section: Simulation and Resultsmentioning

confidence: 99%

Section: Simulation and Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Incremental Adaptive Gesture Classifier for Upper Limb Prostheses

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Literature [25] builds a semantic hair segmentation model for indoor scenes using RGB-D image information technology based on the improved Faster-RCNN algorithm, which reflects the efficient performance of the model in practical feedback and can clearly segment different scales of physical silhouettes even with poor illumination. Literature [26] introduces a gesture recognition method consisting of high-density EMG image processing technology as the underlying logic, which is experimentally tested and demonstrated to be feasible and superior to traditional gesture recognition methods.…”

Section: Introductionmentioning

confidence: 99%

Research and realization of computer image recognition system based on digital projection technology

2024

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

In this paper, the image Gabor features extracted by Gabor wavelet are fused with the image grayscale map to construct the enhanced Gabor features, and then combined with the characteristics of Gabor wavelet and convolutional layer, the Gabor feature extraction module, parallel convolution module and spatial transformation pooling module are designed. The corresponding Gabor convolutional layer and Gabor convolutional neural network are constructed using the appropriate module in accordance with the image recognition task application scenario. The convex set projection image super-resolution reconstruction method is used in this paper to improve the resolution of images with low resolution. The construction of a computerized image recognition system involves combining a Gabor convolutional neural network and a convex set projection method. This system has been tested and found to have a recognition accuracy of 93.5% for object images. This system’s ability to accurately recognize low-resolution shadow-obscured face images is possible thanks to using the convex set projection method to reconstruct the image and recognize it accurately with an accuracy of up to 93.85%. This system’s recognition performance for complex images has been proven through experiments.

show abstract

“…Some recent efforts have been conducted to utilize various representations of HD-sEMG signals for detecting human intention. Examples are as follows: time-domain representation [22]- [24], imagebased muscle activity heatmap representation [19], [22], [25], and motor unit action potentials (MUAPs) and the corresponding spike trains derived through decomposition of HD-sEMG [26]- [28]. In the literature noted above, HD-sEMG has shown ability to secure high accuracy.…”

Section: Introductionmentioning

confidence: 99%

Deep Heterogeneous Dilation of LSTM for Transient-phase Gesture Prediction through High-density Electromyography: Towards Application in Neurorobotics

Sun

Libby

et al. 2021

Preprint

View full text Add to dashboard Cite

Deep networks have been recently proposed to estimate motor intention using conventional bipolar surface electromyography (sEMG) signals for myoelectric control of neurorobots. In this regard, deepnets are generally challenged by long training times (affecting the practicality and calibration), complex model architectures (affecting the predictability of the outcomes), a large number of trainable parameters (increasing the need for big data), and possibly overfitting. Capitalizing on our recent work on homogeneous temporal dilation in a Recurrent Neural Network (RNN) model, this paper proposes, for the first time, heterogeneous temporal dilation in an LSTM model and applies that to high-density surface electromyography (HD-sEMG), allowing for decoding dynamic temporal dependencies with tunable temporal foci. In this paper, a 128-channel HD-sEMG signal space is considered due to the potential for enhancing the spatiotemporal resolution of human-robot interfaces. Accordingly, this paper addresses a challenging motor intention decoding problem of neurorobots, namely, transient intention identification. The aforementioned problem only takes into account the dynamic and transient phase of gesture movements when the signals are not stabilized or plateaued, addressing which can significantly enhance the temporal resolution of human-robot interfaces. This would eventually enhance seamless real-time implementations. Additionally, this paper introduces the concept of “dilation foci” to modulate the modeling of temporal variation in transient phases. In this work a high number (i.e. 65) of gestures is included, which adds to the complexity and significance of the understudied problem. Our results show state-of-the-art performance for gesture prediction in terms of accuracy, training time, and model convergence.

show abstract

Using Image Processing Techniques and HD-EMG for Upper Limb Prosthesis Gesture Recognition

Cited by 6 publications

References 9 publications

Incremental Adaptive Gesture Classifier for Upper Limb Prostheses

Incremental Adaptive Gesture Classifier for Upper Limb Prostheses

Research and realization of computer image recognition system based on digital projection technology

Deep Heterogeneous Dilation of LSTM for Transient-phase Gesture Prediction through High-density Electromyography: Towards Application in Neurorobotics

Contact Info

Product

Resources

About