A framework for hand gesture recognition based on fusion of Flex, Contact and accelerometer sensor

Pathak, Vishal; Mongia, Sushant; Chitranshi, Gaurav

doi:10.1109/iciip.2015.7414787

Cited by 24 publications

(9 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many existing SBR methods are data-driven. A common feature of some SBR-based techniques is that they are based on wearable sensors such as PPG sensors [9], flex sensors [10], and EMG sensors [11] for attaining high recognition accuracy. However, the systems with wearable sensors demand users to take extra devices for gesture recognition.…”

Section: Related Workmentioning

confidence: 99%

“…Gesture recognition has been found to be effective for applications such as devices control, entertainment, health care, and education. Hand gesture recognition approaches can be separated into two classes: Vision-Based Recognition (VBR) algorithms [1][2][3][4] and Sensor-Based Recognition (SBR) algorithms [5][6][7][8][9][10][11][12][13][14][15][16]. The VBR algorithms perform gesture recognition from images captured by a camera.…”

Section: Introductionmentioning

confidence: 99%

“…The SBR algorithms are based on sensors other than camera. Commonly used sensors include accelerometers [5,6], gyroscopes [7,8], photoplethysmography (PPG) [9], flex sensors [10], electromyography (EMG) [11], Radio Frequency IDentification (RFID) [12,13], WiFi Channel State Information (CSI) [14][15][16], and the fusion of these sensors. In some SBR-based studies, high classification accuracy for gesture recognition has been observed.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Recognition of Hand Gesture Sequences by Accelerometers and Gyroscopes

Chu

Jhang²,

Tai³

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

The objective of this study is to present novel neural network (NN) algorithms and systems for sensor-based hand gesture recognition. The algorithms are able to classify accurately a sequence of hand gestures from the sensory data produced by accelerometers and gyroscopes. They are the extensions from the PairNet, which is a Convolutional Neural Network (CNN) capable of carrying out simple pairing operations with low computational complexities. Three different types of feedforward NNs, termed Residual PairNet, PairNet with Inception, and Residual PairNet with Inception are proposed for the extension. They are the PairNet operating in conjunction with short-cut connections and/or inception modules for achieving high classification accuracy and low computation complexity. A prototype system based on smart phones for remote control of home appliances has been implemented for the performance evaluation. Experimental results reveal that the PairNet has superior classification accuracy over its basic CNN and Recurrent NN (RNN) counterparts. Furthermore, the Residual PairNet, PairNet with Inception, and Residual PairNet with Inception are able to further improve classification hit rate and/or reduce recognition time for hand gesture recognition.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Recognition of Hand Gesture Sequences by Accelerometers and Gyroscopes

Chu

Jhang²,

Tai³

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Sensor-based gesture recognition (SGR) [7] techniques have been found to be effective alternatives to VGR techniques. Examples of sensors adopted for SGR techniques include electromyography, accelerometers, gyroscopes, flex, and/or photoplethysmography [8,9,10,11]. Some of these sensors can be deployed in embedded devices with low computation capacity for sensory data capturing and processing.…”

Section: Introductionmentioning

confidence: 99%

“…Some existing SGR techniques [10,11] for hand gesture recognition have the shortcoming that only a single gesture can be recognized at a time. These techniques may not be directly applicable for continuous gesture recognition requiring the classification of a sequence of gestures.…”

Section: Introductionmentioning

confidence: 99%

Continuous Finger Gesture Recognition Based on Flex Sensors

Chuang

Hwang

Tai

et al. 2019

Sensors

View full text Add to dashboard Cite

The goal of this work is to present a novel continuous finger gesture recognition system based on flex sensors. The system is able to carry out accurate recognition of a sequence of gestures. Wireless smart gloves equipped with flex sensors were implemented for the collection of the training and testing sets. Given the sensory data acquired from the smart gloves, the gated recurrent unit (GRU) algorithm was then adopted for gesture spotting. During the training process for the GRU, the movements associated with different fingers and the transitions between two successive gestures were taken into consideration. On the basis of the gesture spotting results, the maximum a posteriori (MAP) estimation was carried out for the final gesture classification. Because of the effectiveness of the proposed spotting scheme, accurate gesture recognition was achieved even for complicated transitions between successive gestures. From the experimental results, it can be observed that the proposed system is an effective alternative for robust recognition of a sequence of finger gestures.

show abstract

Hand Gesture-Based Control of Electronic Appliances Using Internet of Things

Paul

Joshi

2017

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

A framework for hand gesture recognition based on fusion of Flex, Contact and accelerometer sensor

Cited by 24 publications

References 10 publications

Recognition of Hand Gesture Sequences by Accelerometers and Gyroscopes

Recognition of Hand Gesture Sequences by Accelerometers and Gyroscopes

Continuous Finger Gesture Recognition Based on Flex Sensors

Hand Gesture-Based Control of Electronic Appliances Using Internet of Things

Contact Info

Product

Resources

About