Dynamic Hand Gesture Recognition Based on a Leap Motion Controller and Two-Layer Bidirectional Recurrent Neural Network
Dynamic hand gesture recognition is one of the most significant tools for human–computer interaction. In order to improve the accuracy of the dynamic hand gesture recognition, in this paper, a two-layer Bidirectional Recurrent Neural Network for the recognition of dynamic hand gestures from a Leap M...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/7/2106 |
| _version_ | 1797571137359577088 |
|---|---|
| author | Linchu Yang Ji’an Chen Weihang Zhu |
| author_facet | Linchu Yang Ji’an Chen Weihang Zhu |
| author_sort | Linchu Yang |
| collection | DOAJ |
| description | Dynamic hand gesture recognition is one of the most significant tools for human–computer interaction. In order to improve the accuracy of the dynamic hand gesture recognition, in this paper, a two-layer Bidirectional Recurrent Neural Network for the recognition of dynamic hand gestures from a Leap Motion Controller (LMC) is proposed. In addition, based on LMC, an efficient way to capture the dynamic hand gestures is identified. Dynamic hand gestures are represented by sets of feature vectors from the LMC. The proposed system has been tested on the American Sign Language (ASL) datasets with 360 samples and 480 samples, and the Handicraft-Gesture dataset, respectively. On the ASL dataset with 360 samples, the system achieves accuracies of 100% and 96.3% on the training and testing sets. On the ASL dataset with 480 samples, the system achieves accuracies of 100% and 95.2%. On the Handicraft-Gesture dataset, the system achieves accuracies of 100% and 96.7%. In addition, 5-fold, 10-fold, and Leave-One-Out cross-validation are performed on these datasets. The accuracies are 93.33%, 94.1%, and 98.33% (360 samples), 93.75%, 93.5%, and 98.13% (480 samples), and 88.66%, 90%, and 92% on ASL and Handicraft-Gesture datasets, respectively. The developed system demonstrates similar or better performance compared to other approaches in the literature. |
| first_indexed | 2024-03-10T20:36:00Z |
| format | Article |
| id | doaj.art-91e07f92ee8c4d7a8db8c702b4154d38 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T20:36:00Z |
| publishDate | 2020-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-91e07f92ee8c4d7a8db8c702b4154d382023-11-19T21:02:57ZengMDPI AGSensors1424-82202020-04-01207210610.3390/s20072106Dynamic Hand Gesture Recognition Based on a Leap Motion Controller and Two-Layer Bidirectional Recurrent Neural NetworkLinchu Yang0Ji’an Chen1Weihang Zhu2Department of Mechanical Engineering; Jiangsu University of Science and Technology, Zhenjiang 212003, ChinaDepartment of Mechanical Engineering; Jiangsu University of Science and Technology, Zhenjiang 212003, ChinaDepartment of Engineering Technology; University of Houston, Houston, TX 77204, USADynamic hand gesture recognition is one of the most significant tools for human–computer interaction. In order to improve the accuracy of the dynamic hand gesture recognition, in this paper, a two-layer Bidirectional Recurrent Neural Network for the recognition of dynamic hand gestures from a Leap Motion Controller (LMC) is proposed. In addition, based on LMC, an efficient way to capture the dynamic hand gestures is identified. Dynamic hand gestures are represented by sets of feature vectors from the LMC. The proposed system has been tested on the American Sign Language (ASL) datasets with 360 samples and 480 samples, and the Handicraft-Gesture dataset, respectively. On the ASL dataset with 360 samples, the system achieves accuracies of 100% and 96.3% on the training and testing sets. On the ASL dataset with 480 samples, the system achieves accuracies of 100% and 95.2%. On the Handicraft-Gesture dataset, the system achieves accuracies of 100% and 96.7%. In addition, 5-fold, 10-fold, and Leave-One-Out cross-validation are performed on these datasets. The accuracies are 93.33%, 94.1%, and 98.33% (360 samples), 93.75%, 93.5%, and 98.13% (480 samples), and 88.66%, 90%, and 92% on ASL and Handicraft-Gesture datasets, respectively. The developed system demonstrates similar or better performance compared to other approaches in the literature.https://www.mdpi.com/1424-8220/20/7/2106hand gesture recognitionleap motion controller (LMC)recurrent neural network (RNN) |
| spellingShingle | Linchu Yang Ji’an Chen Weihang Zhu Dynamic Hand Gesture Recognition Based on a Leap Motion Controller and Two-Layer Bidirectional Recurrent Neural Network Sensors hand gesture recognition leap motion controller (LMC) recurrent neural network (RNN) |
| title | Dynamic Hand Gesture Recognition Based on a Leap Motion Controller and Two-Layer Bidirectional Recurrent Neural Network |
| title_full | Dynamic Hand Gesture Recognition Based on a Leap Motion Controller and Two-Layer Bidirectional Recurrent Neural Network |
| title_fullStr | Dynamic Hand Gesture Recognition Based on a Leap Motion Controller and Two-Layer Bidirectional Recurrent Neural Network |
| title_full_unstemmed | Dynamic Hand Gesture Recognition Based on a Leap Motion Controller and Two-Layer Bidirectional Recurrent Neural Network |
| title_short | Dynamic Hand Gesture Recognition Based on a Leap Motion Controller and Two-Layer Bidirectional Recurrent Neural Network |
| title_sort | dynamic hand gesture recognition based on a leap motion controller and two layer bidirectional recurrent neural network |
| topic | hand gesture recognition leap motion controller (LMC) recurrent neural network (RNN) |
| url | https://www.mdpi.com/1424-8220/20/7/2106 |
| work_keys_str_mv | AT linchuyang dynamichandgesturerecognitionbasedonaleapmotioncontrollerandtwolayerbidirectionalrecurrentneuralnetwork AT jianchen dynamichandgesturerecognitionbasedonaleapmotioncontrollerandtwolayerbidirectionalrecurrentneuralnetwork AT weihangzhu dynamichandgesturerecognitionbasedonaleapmotioncontrollerandtwolayerbidirectionalrecurrentneuralnetwork |