A Framework for Hand Gesture Recognition Based on Accelerometer and EMG Sensors

Zhang, Xu; Chen, Xiang; Li, Yun; Lantz, Vuokko; Wang, Kongqiao; Yang, Jian

doi:10.1109/tsmca.2011.2116004

Cited by 531 publications

(253 citation statements)

References 32 publications

Supporting

Mentioning

248

Contrasting

Unclassified

Order By: Relevance

“…While research has been conducted on the use of lower dimensional waveform features for classification, such as Mean Absolute Value [5,6] or Fast Fourier Transform [10], this study has shown that a combination of procedural time-domain techniques including filtering, segmentation and temporal scaling can also be effective. Despite this result, it should be noted that further training and testing is required for subjects with movement disorders to be able to properly gauge the potential for this system.…”

Section: Discussionmentioning

confidence: 99%

“…Supervised training was done through backpropagated stochastic gradient descent: (6) where is the Least Squared Error (LSE) cost function:…”

Section: Classificationmentioning

confidence: 99%

“…One study [6] provides a framework for the classification of Chinese Sign Language (CSL) using a hidden Markov model (HMM) while another [7] classifies Greek Sign Language based on intrinsic mode entropy (IMEn) and Mahalanobis distance (both still requiring EMG however). This paper explores the design, testing and optimization of a purely accelerometer based gesture identification system with classification performed by an artificial neural network.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A system for accelerometer-based gesture classification using artificial neural networks

Stephenson

Naik

Chai

2017

2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

View full text Add to dashboard Cite

Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. 4Abstract-A great many people suffer from neurological movement disorders that render typical hardware interface devices ineffective. A need exists for a universal interface device that can be trained to accept a wide range of inputs across varying types and severities of movement disorders. In this regard, this paper details the design, testing and optimization of an accelerometer-based gesture identification system. A Bluetooth-enabled IMU mounted on the wrist provides hand motion trajectory information to a local terminal. Several techniques are applied to decrease the intra-class variance and reduce classifier complexity including filtering, segmentation and temporal scaling. Datasets consisted of 520 training samples, 260 validation samples and a further 520 testing samples. A multi-layer feed forward artificial neural network (ML-FFNN) was used to classify the input space into 26 different classes. Initial system accuracy, using arbitrary hyperparameters was 77.69% with final optimized accuracy at 99.42%.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Supervised training was done through backpropagated stochastic gradient descent: (6) where is the Least Squared Error (LSE) cost function:…”

Section: Classificationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A system for accelerometer-based gesture classification using artificial neural networks

Stephenson

Naik

Chai

2017

2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

View full text Add to dashboard Cite

show abstract

“…And the recognition accuracy rate can be as high as 80%. ARTS Lab of SSA's Cyber hand project and the Italian INIL/RTR center designed of a false hand which is a multi-finger less hand-driven, the use of EMG signals to control the multi-joint fingers, and it could be achieved more accurate crawling function with the simple command [1]. The foreign typical bionic hand such as the Washington University developed exoskeleton robot which can imitate the normal seven freestyle of the action; The European bionic hand could calculate the acquisition of the relevant orders and simple interaction with a perception function; The bionic hand in British had the able to identify the motor instruction issues by the brain, and also had the able to perform the complex finger movement.…”

Section: Introductionmentioning

confidence: 99%

Research on EMG Signal Extraction Based on Biomimetic Hand

Xu¹,

Sun²,

Li³

2017

Proceedings of the 7th International Conference on Management, Education, Information and Control (MEICI 2017)

View full text Add to dashboard Cite

Abstract. EMG is a signal which could reflect the information of human body's movement in residual limb muscle group. As a source of information, it could control the bionic prosthesis to complete the multi-degree of freedom of action. EMG prosthesis controlled the bionic prosthesis through the body's own physiological signal. It is remarkable significant for the disabled users that if the bionic prosthesis could understand the movement of the disabled users will. The purpose of the EMG signal acquisition is driving a bionic hand which could help the hand disabilities to achieve grasping, pushing, taking, holding etc. EMG prosthetic is a complex system, which involving multidisciplinary disciplines. And this paper mainly introduces the method of EMG extraction.

show abstract

“…To be specific, how to develop a universally applicable algorithm which is computationally efficient and suitable for most users is still imperfectly resolved. In gesture segmentation, Xu Zhang et al [4] combine the accelerometer signals and EMG signals to automatically distinguish the valid gestures. But the EMG signals are easily affected by the soft tissue artifacts which contribute to the false gesture segmentation.…”

Section: Introductionmentioning

confidence: 99%

PCA & HMM Based Arm Gesture Recognition Using Inertial Measurement Unit

Zhang

Liang

Tan³

et al. 2013

Proceedings of the 8th International Conference on Body Area Networks

View full text Add to dashboard Cite

This paper presents a novel arm gesture recognition approach that is capable of recognizing seven commonly used sequential arm gestures based upon the outputs from Inertial Measurement Unit (IMU) integrated with 3-D accelerometer and 3-D gyroscope. Unlike the traditional gesture recognition methods where the states in the gesture sequence are irrelevant, our proposed recognition system is intentionally designed to recognize the meaningful gesture sequence where each gesture state relates to the contiguous states which is applicable in the specific occasions such as the police directing the traffic and the arm-injured patients performing a set of arm gestures for effective rehabilitation. In the proposed arm gesture recognition system, the waveforms of the inertial outputs, i.e., 3-D accelerations and 3-D angular rates are automatically segmented for each arm gesture trace at first. Then we employ the Principal Component Analysis (PCA) -a computationally efficient feature selection method characteristic of compressing the inertial data and minimizing the influences of gesture variations. These selected features from PCA are compared with those standard features stored in pattern templates to acquire the gesture observation sequence that satisfy the Markov property. Finally, the Hidden Markov Model is applied in deducing the most likely arm gesture sequence. The experimental results show that our arm gesture classifier achieves up to 93% accuracy. By comparing with the other published recognition methods, our approach verifies the robustness and feasibility in arm gesture recognition using wearable MEMS sensors.

show abstract

A Framework for Hand Gesture Recognition Based on Accelerometer and EMG Sensors

Cited by 531 publications

References 32 publications

A system for accelerometer-based gesture classification using artificial neural networks

A system for accelerometer-based gesture classification using artificial neural networks

Research on EMG Signal Extraction Based on Biomimetic Hand

PCA & HMM Based Arm Gesture Recognition Using Inertial Measurement Unit

Contact Info

Product

Resources

About