DcnnGrasp: Towards Accurate Grasp Pattern Recognition with Adaptive Regularizer Learning

Zhang, Xiaoqin; Huang, Ziwei; Jiao, Z.; Wang, Shuo; Jiang, Xianta

doi:10.48550/arxiv.2205.05218

Cited by 3 publications

(3 citation statements)

References 43 publications

(69 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The regularization coefficient and trainable parameters in the loss function JCEAR and DcnnGrasp were updated by a developed training strategy. From the experiments given in their study, it can be seen that, compared with SOTA methods, DcnnGrasp achieved the best accuracy in most cases (Zhang et al, 2022).…”

Section: Grasp Classification Using the Dualchannel Cnn Modelmentioning

confidence: 99%

Integrating computer vision to prosthetic hand control with sEMG: Preliminary results in grasp classification

et al. 2022

Self Cite

View full text Add to dashboard Cite

The myoelectric prosthesis is a promising tool to restore the hand abilities of amputees, but the classification accuracy of surface electromyography (sEMG) is not high enough for real-time application. Researchers proposed integrating sEMG signals with another feature that is not affected by amputation. The strong coordination between vision and hand manipulation makes us consider including visual information in prosthetic hand control. In this study, we identified a sweet period during the early reaching phase in which the vision data could yield a higher accuracy in classifying the grasp patterns. Moreover, the visual classification results from the sweet period could be naturally integrated with sEMG data collected during the grasp phase. After the integration, the accuracy of grasp classification increased from 85.5% (only sEMG) to 90.06% (integrated). Knowledge gained from this study encourages us to further explore the methods for incorporating computer vision into myoelectric data to enhance the movement control of prosthetic hands.

show abstract

Section: Grasp Classification Using the Dualchannel Cnn Modelmentioning

confidence: 99%

Integrating computer vision to prosthetic hand control with sEMG: Preliminary results in grasp classification

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…While offering a more dynamic approach, processing video data can be computationally intensive compared to single images. Zhang et al [33] introduced DcnnGrasp, a dual-branch convolutional neural network for grasp pattern recognition. DcnnGrasp incorporates object category classification as an auxiliary task to improve grasp pattern recognition.…”

Section: Related Workmentioning

confidence: 99%

Vision-aided grasp classification: design and evaluation of compact CNN for prosthetic hands

Sharma,

Vasamsetti,

Chander

et al. 2024

Biomed. Phys. Eng. Express

View full text Add to dashboard Cite

Powered prosthetic hands capable of executing various grasp patterns are highly sought-after solutions for upper limb amputees. A crucial requirement for such prosthetic hands is the accurate identification of the intended grasp pattern and subsequent activation of the prosthetic digits accordingly. Vision-based grasp classification techniques offer improved coordination between amputees and prosthetic hands without physical contact. Deep learning methods, particularly Convolutional Neural Networks (CNNs), are utilized to process visual information for classification. The key challenge lies in developing a model that can effectively generalize across various object shapes and accurately classify grasp classes. To address this, a compact CNN model named GraspCNet is proposed, specifically designed for grasp classification in prosthetic hands. The use of separable convolutions reduces the computational burden, making it potentially suitable for real-time applications on embedded systems. The GraspCNet model is designed to learn and generalize from object shapes, allowing it to effectively classify unseen objects beyond those included in the training dataset. The proposed model was trained and tested using various standard object data sets. A cross-validation strategy has been adopted to perform better in seen and unseen object class scenarios. The average accuracy achieved was 82.22% and 75.48% in the case of seen, and unseen object classes respectively. In computer-based real-time experiments, the GraspCNet model achieved an accuracy of 69%. A comparative analysis with state-of-the-art techniques revealed that the proposed GraspCNet model outperformed most benchmark techniques and demonstrated comparable performance with the DcnnGrasp method. The compact nature of the GraspCNet model suggests its potential for integration with other sensing modalities in prosthetic hands.

show abstract

“…We used two datasets, RGB-D Object dataset 1 [25], [26] and Hit-GPRec dataset 2 [16] to evaluate our proposed network, where RGB-D Object dataset was proposed for object category classification, and then manually labeled with gestures by Zhang [26]. RGB-D Object dataset contained a total of 300 objects and 207921 images labeled into four gestures (palmar wrist neutral, palmar wrist pronated, pinch, tripod).…”

Section: Experiments a Datasetmentioning

confidence: 99%

DL-Net: Sparsity Prior Learning for Grasp Pattern Recognition

et al. 2023

View full text Add to dashboard Cite

The purpose of grasp pattern recognition is to determine the grasp type for an object to be grasped, which can be applied to prosthetic hand control and ease the burden of amputees. To enhance the performance of grasp pattern recognition, we propose a network DL-Net inspired by dictionary learning. Our method includes two parts: (1) forward propagation for sparsity representation learning and (2) backward propagation for dictionary learning, which utilizes the sparsity prior effectively and learns a discriminative dictionary with stronger expressive ability from a mass of training data. The experiment was performed on two household object datasets, the RGB-D Object dataset, and the Hit-GPRec dataset. The experimental results illustrate that the DL-Net performs better than traditional deep learning methods in grasp pattern recognition.INDEX TERMS Grasp pattern recognition, computer vision, dictionary learning, deep learning.

show abstract

DcnnGrasp: Towards Accurate Grasp Pattern Recognition with Adaptive Regularizer Learning

Cited by 3 publications

References 43 publications

Integrating computer vision to prosthetic hand control with sEMG: Preliminary results in grasp classification

Integrating computer vision to prosthetic hand control with sEMG: Preliminary results in grasp classification

Vision-aided grasp classification: design and evaluation of compact CNN for prosthetic hands

DL-Net: Sparsity Prior Learning for Grasp Pattern Recognition

Contact Info

Product

Resources

About