Real-Time Hand Gesture Recognition Using Temporal Muscle Activation Maps of Multi-Channel Semg Signals

Silva, Ashwin De; Perera, Malsha V.; Wickramasinghe, Kithmin; A, Naim; Lalitharatne, Thilina Dulantha; Kappel, Simon L.

doi:10.1109/icassp40776.2020.9054227

Cited by 12 publications

(7 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using the developed sEMG sensors, we were able to obtain classification accuracies above 80%. The accuracies were generally lower than comparable results obtained by De Silva et al [15] and Crepin et al [5]. The lower accuracies could be caused by a lower signal quality, which might be related to the biopotential amplifier that was used to perform the study.…”

Section: A Real-time Finger Gesture Classificationcontrasting

confidence: 48%

“…The classification algorithm uses temporal muscle activation (TMA) maps, and was trained and tested on an individual subject basis. The data collection protocol and classification algorithm are detailed in [15].…”

Section: B Experimental Setupmentioning

confidence: 99%

“…7 shows the sEMG signals (black) obtained for flexion and extension of the hand closure gesture using four sensors, along with the signal envelope used for real-time finger gesture classification (dashed red). b The classification of the finger gesture was not considered in [15] as the muscles pertaining to the finger motion are not easily accessible by the sEMG acquisition device used in the study.…”

Section: A Real-time Finger Gesture Classificationmentioning

confidence: 99%

“…The sensor was developed to be a part of a wearable sEMG acquisition system, which enables multichannel recording of low noise sEMG signals. The signal quality of the developed sensor was evaluated experimentally with the real-time finger gesture recognition algorithm described by De Silva et al [15]. In addition, the CMRR of the sensor was characterized to ensure that there are no substantial performance limitation of the sensor due to its active circuitry.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Low-cost Active Dry-Contact Surface EMG Sensor for Bionic Arms

Naim,

Wickramasinghe,

De Silva

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Surface electromyography (sEMG) is a popular bio-signal used for controlling prostheses and finger gesture recognition mechanisms. Myoelectric prostheses are costly, and most commercially available sEMG acquisition systems are not suitable for real-time gesture recognition. In this paper, a method of acquiring sEMG signals using novel low-cost, active, drycontact, flexible sensors has been proposed. Since the active sEMG sensor was developed to be used along with a bionic arm, the sensor was tested for its ability to acquire sEMG signals that could be used for real-time classification of five selected gestures. In a study of 4 subjects, the average classification accuracy for real-time gesture classification using the active sEMG sensor system was 85%. The common-mode rejection ratio of the sensor was measured to 59 dB, and thus the sensor's performance was not substantially limited by its active circuitry. The proposed sensors can be interfaced with a variety of amplifiers to perform fully wearable sEMG acquisition. This satisfies the need for a low-cost sEMG acquisition system for prostheses.

show abstract

Section: A Real-time Finger Gesture Classificationcontrasting

confidence: 48%

Section: B Experimental Setupmentioning

confidence: 99%

Section: A Real-time Finger Gesture Classificationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Low-cost Active Dry-Contact Surface EMG Sensor for Bionic Arms

Naim,

Wickramasinghe,

De Silva

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Methodology described in the paper for real-time hand gesture recognition is surface electromyography (sEMG) signals [12]. Temporal muscle activation (TMA) map represents hand gesture.…”

Section: Survey On Hand Gesture Segmentationmentioning

confidence: 99%

A Study on Hand Gesture Segmentation Approaches

Sunuwar

Borah

Agarwal

et al. 2021

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Computer vision is the study of making machines capable of understanding the input image and video using some algorithms or techniques. As for humans, understanding a scene given in an image or video is not a difficult task. Humans are blessed to understand images and videos effortlessly without knowing the complexities behind the process of image and video understanding. Making machines also capable of understanding their input image and video is not that simple. With ongoing research for making human-computer interaction more natural and realistic, lots of advancements have been done in different components of computer vision. The paper focuses on the image segmentation process used in computer vision and image processing which is a very crucial component while processing images and video. Image segmentation is the process of extracting only relevant content or information while removing irreverent content or information. Image segmentation is the most researched topic in image processing and computer vision. It is one of the major activities that will help the later process to ease its operation by filtering unnecessary and irrelevant contents. The paper aims to describe the segmentation process and highlight different types of segmentation approaches used in recent trends comparing their performances.

show abstract