User-independent real-time hand gesture recognition based on surface electromyography

Kerber, Frederic; Puhl, Michael; Krüger, Antonio

doi:10.1145/3098279.3098553

Cited by 52 publications

(17 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A setup consisting of both a pair and a single Myo was tested against other setups, with the Myo obtaining good results, similar to those obtained by much more expensive devices. Kerber, Puhl and Kruger [22] also developed a system for recognizing gestures using the Myo armband with an accuracy of 95%, using a Support Vector Machine as their machine learning algorithm.…”

Section: Device and Technologymentioning

confidence: 99%

FarMyo: A Serious Game for Hand and Wrist Rehabilitation Using a Low-Cost Electromyography Device

Batista

Machado²,

Valença³

et al. 2019

IJSG

View full text Add to dashboard Cite

One of the strategies used in recent years to increase the commitment and motivation of patients undergoing rehabilitation is the use of graphical systems, such as virtual environments and serious games. In addition to contributing to the motivation, these systems can simulate real life activities and provide means to measure and assess user performance. The use of natural interaction devices, originally conceived for the game market, has allowed the development of low cost and minimally invasive rehabilitation systems. With the advent of natural interaction devices based on electromyography, the user's electromyographic data can also be used to build these systems. This paper shows the development of a serious game focused on aiding the rehabilitation process of patients with hand motor problems, targeting to solve problems related to cost, adaptability and patient motivation in this type of application. The game uses an electromyography device to recognize the gestures being performed by the user. A gesture recognition system was developed to detect new gestures, complementing the device's own recognition system, which is responsible for interpreting the signals. An initial evaluation of the game was conducted with professional physiotherapists.

show abstract

Section: Device and Technologymentioning

confidence: 99%

FarMyo: A Serious Game for Hand and Wrist Rehabilitation Using a Low-Cost Electromyography Device

Batista

Machado²,

Valença³

et al. 2019

IJSG

View full text Add to dashboard Cite

show abstract

“…They applied the models evaluating standard 2D gestures drown using an on-screen interactive pen [6]. Kerber et al (2017) implemented a custom Python program to read, filter and process electromyogram data extracted from the commercially available armband device called Myo. Authors trained a machine learning model based on SVM, to classify and accurately (95%) detect 40 different gestures.…”

Section: Related Workmentioning

confidence: 99%

“…Authors trained a machine learning model based on SVM, to classify and accurately (95%) detect 40 different gestures. Those gestures are based on the Myo standard hand dispositions, also different finger configurations [16].…”

Section: Related Workmentioning

confidence: 99%

A Machine Learning Approach to Violin Bow Technique Classification

Dalmazzo

Tassani

Ramírez

2018

Proceedings of the 5th International Workshop on Sensor-Based Activity Recognition and Interaction

View full text Add to dashboard Cite

Motion Capture (MOCAP) Systems have been used to analyze body motion and postures in biomedicine, sports, rehabilitation, and music. With the aim to compare the precision of low-cost devices for motion tracking (e.g. Myo) with the precision of MOCAP systems in the context of music performance, we recorded MOCAP and Myo data of a top professional violinist executing four fundamental bowing techniques (i.e. Détaché, Martelé, Spiccato and Ricochet). Using the recorded data we applied machine learning techniques to train models to classify the four bowing techniques. Despite intrinsic differences between the MOCAP and low-cost data, the Myo-based classifier resulted in slightly higher accuracy than the MOCAPbased classifier. This result shows that it is possible to develop music-gesture learning applications based on low-cost technology which can be used in home environments for self-learning practitioners.

show abstract

“…Approximately 95% of the signal power was below 400–500 Hz, which required the sampling rate to reach 1000 Hz in order to gather all the information according to the Nyquist sampling theory [ 38 , 39 , 40 ]. However, studies employing a low sampling rate device still obtained a decent accuracy with different approaches applied [ 41 , 42 , 43 ]. Some of other studies only carried the experiment on single participant and developed systems which had high accuracy [ 44 , 45 , 46 ].…”

Section: Introductionmentioning

confidence: 99%

Development of Sign Language Motion Recognition System for Hearing-Impaired People Using Electromyography Signal

Tateno

Liu

2020

Sensors

View full text Add to dashboard Cite

Sign languages are developed around the world for hearing-impaired people to communicate with others who understand them. Different grammar and alphabets limit the usage of sign languages between different sign language users. Furthermore, training is required for hearing-intact people to communicate with them. Therefore, in this paper, a real-time motion recognition system based on an electromyography signal is proposed for recognizing actual American Sign Language (ASL) hand motions for helping hearing-impaired people communicate with others and training normal people to understand the sign languages. A bilinear model is applied to deal with the on electromyography (EMG) data for decreasing the individual difference among different people. A long short-term memory neural network is used in this paper as the classifier. Twenty sign language motions in the ASL library are selected for recognition in order to increase the practicability of the system. The results indicate that this system can recognize these twenty motions with high accuracy among twenty participants. Therefore, this system has the potential to be widely applied to help hearing-impaired people for daily communication and normal people to understand the sign languages.

show abstract

User-independent real-time hand gesture recognition based on surface electromyography

Cited by 52 publications

References 20 publications

FarMyo: A Serious Game for Hand and Wrist Rehabilitation Using a Low-Cost Electromyography Device

FarMyo: A Serious Game for Hand and Wrist Rehabilitation Using a Low-Cost Electromyography Device

A Machine Learning Approach to Violin Bow Technique Classification

Development of Sign Language Motion Recognition System for Hearing-Impaired People Using Electromyography Signal

Contact Info

Product

Resources

About