Bi-channel sensor fusion for automatic sign language recognition

Kim, Jong-Hwa; Wagner, Johannes; Rehm, Matthias; André, Elisabeth

doi:10.1109/afgr.2008.4813341

Cited by 39 publications

(19 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their experiments using 10 subjects demonstrate that it is preferable to add an accelerometer to a two-site sEMG system rather than a third electrode. Related to the context of prosthetic control, the integration of accelerometers and sEMG has also proven useful for sign language recognition [7], [8]. For example, the information fusion framework proposed by Zhang, Chen, Li, et al [8] classified 72 Chinese sign language words with more than 95% accuracy, largely due to the complementary nature of both modalities.…”

Section: Introductionmentioning

confidence: 99%

Exploiting accelerometers to improve movement classification for prosthetics

Gijsberts

Caputo

2013

2013 IEEE 13th International Conference on Rehabilitation Robotics (ICORR)

View full text Add to dashboard Cite

Abstract-Recent studies have explored the integration of additional input modalities to improve myoelectric control of prostheses. Arm dynamics in particular are an interesting option, as these can be measured easily by means of accelerometers. In this work, the benefit of accelerometer signals is demonstrated on a large scale movement classification task, consisting of 40 hand and wrist movements obtained from 20 subjects. The results demonstrate that the accelerometer modality is indeed highly informative and even outperforms surface electromyography in terms of classification accuracy. The highest accuracy, however, is obtained when both modalities are integrated in a multi-modal classifier.

show abstract

Section: Introductionmentioning

confidence: 99%

Exploiting accelerometers to improve movement classification for prosthetics

Gijsberts

Caputo

2013

2013 IEEE 13th International Conference on Rehabilitation Robotics (ICORR)

View full text Add to dashboard Cite

show abstract

“…There exist several sensor gloves designed for sign language translation. Kim et al [16], for example, applied a combination of a tri-axial accelerometer and an electromyogram (EMG) sensor for the recognition of seven words in German sign language. The sensors were attached on the arm and signals were transmitted wirelessly via Bluetooth.…”

Section: Introductionmentioning

confidence: 99%

“…The sensor-based techniques, especially wireless sensors [1,7,16], can provide users with enhanced mobility. The devices are usually more expensive and can be cumbersome in some cases.…”

Section: Introductionmentioning

confidence: 99%

Design of an Assistive Communication Glove Using Combined Sensory Channels

Tanyawiwat

Thiemjarus

2012

2012 Ninth International Conference on Wearable and Implantable Body Sensor Networks

View full text Add to dashboard Cite

This paper presents a new design of a wireless sensor glove developed for American Sign Language fingerspelling gesture recognition. Five contact sensors are installed on the glove, in addition to five flex sensors on the fingers and a 3D accelerometer on the back of the hand. Each pair of flex and contact sensors are combined into the same input channel on the BSN node in order to save the number of channels and the installation area. After which, the signal is analyzed and separated back into flex and contact features by software. With electrical contacts and wirings made of conductive fabric and threads, the glove design has become thinner and more flexible. For validation, ASL fingerspelling gesture recognition experiments have been performed on signals collected from six speech-impaired subjects and a normal subject. With the new sensor glove design, the experimental results have shown a significant increase in classification accuracy.

show abstract

“…Kim et al [10] proposed a system which combined sensor data from accelerometers and an Electromyogram (EMG) which was used to measure the electrical activity produced by the hand muscles. It was shown that the information added by the EMG greatly improved the recognition rate of signs.…”

Section: Fig22 Hand Gesture Experimental Setup With Four Electrodes mentioning

confidence: 99%