Semi-Supervised Joint Learning for Hand Gesture Recognition from a Single Color Image
Hand gesture recognition and hand pose estimation are two closely correlated tasks. In this paper, we propose a deep-learning based approach which jointly learns an intermediate level shared feature for these two tasks, so that the hand gesture recognition task can be benefited from the hand pose es...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-02-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/3/1007 |
id |
doaj-2fe9bb879d83474e9a24992945a6d63d |
---|---|
record_format |
Article |
spelling |
doaj-2fe9bb879d83474e9a24992945a6d63d2021-02-03T00:04:43ZengMDPI AGSensors1424-82202021-02-01211007100710.3390/s21031007Semi-Supervised Joint Learning for Hand Gesture Recognition from a Single Color ImageChi Xu0Yunkai Jiang1Jun Zhou2Yi Liu3School of Automation, China University of Geosciences, Wuhan 430074, ChinaSchool of Automation, China University of Geosciences, Wuhan 430074, ChinaSchool of Automation, China University of Geosciences, Wuhan 430074, ChinaCRRC Zhuzhou Electric Locomotive Co., Ltd. 1 TianXin Road, Zhuzhou 412000, ChinaHand gesture recognition and hand pose estimation are two closely correlated tasks. In this paper, we propose a deep-learning based approach which jointly learns an intermediate level shared feature for these two tasks, so that the hand gesture recognition task can be benefited from the hand pose estimation task. In the training process, a semi-supervised training scheme is designed to solve the problem of lacking proper annotation. Our approach detects the foreground hand, recognizes the hand gesture, and estimates the corresponding 3D hand pose simultaneously. To evaluate the hand gesture recognition performance of the state-of-the-arts, we propose a challenging hand gesture recognition dataset collected in unconstrained environments. Experimental results show that, the gesture recognition accuracy of ours is significantly boosted by leveraging the knowledge learned from the hand pose estimation task.https://www.mdpi.com/1424-8220/21/3/1007hand gesture recognitionhand pose estimationjoint learningshared feature |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Chi Xu Yunkai Jiang Jun Zhou Yi Liu |
spellingShingle |
Chi Xu Yunkai Jiang Jun Zhou Yi Liu Semi-Supervised Joint Learning for Hand Gesture Recognition from a Single Color Image Sensors hand gesture recognition hand pose estimation joint learning shared feature |
author_facet |
Chi Xu Yunkai Jiang Jun Zhou Yi Liu |
author_sort |
Chi Xu |
title |
Semi-Supervised Joint Learning for Hand Gesture Recognition from a Single Color Image |
title_short |
Semi-Supervised Joint Learning for Hand Gesture Recognition from a Single Color Image |
title_full |
Semi-Supervised Joint Learning for Hand Gesture Recognition from a Single Color Image |
title_fullStr |
Semi-Supervised Joint Learning for Hand Gesture Recognition from a Single Color Image |
title_full_unstemmed |
Semi-Supervised Joint Learning for Hand Gesture Recognition from a Single Color Image |
title_sort |
semi-supervised joint learning for hand gesture recognition from a single color image |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2021-02-01 |
description |
Hand gesture recognition and hand pose estimation are two closely correlated tasks. In this paper, we propose a deep-learning based approach which jointly learns an intermediate level shared feature for these two tasks, so that the hand gesture recognition task can be benefited from the hand pose estimation task. In the training process, a semi-supervised training scheme is designed to solve the problem of lacking proper annotation. Our approach detects the foreground hand, recognizes the hand gesture, and estimates the corresponding 3D hand pose simultaneously. To evaluate the hand gesture recognition performance of the state-of-the-arts, we propose a challenging hand gesture recognition dataset collected in unconstrained environments. Experimental results show that, the gesture recognition accuracy of ours is significantly boosted by leveraging the knowledge learned from the hand pose estimation task. |
topic |
hand gesture recognition hand pose estimation joint learning shared feature |
url |
https://www.mdpi.com/1424-8220/21/3/1007 |
work_keys_str_mv |
AT chixu semisupervisedjointlearningforhandgesturerecognitionfromasinglecolorimage AT yunkaijiang semisupervisedjointlearningforhandgesturerecognitionfromasinglecolorimage AT junzhou semisupervisedjointlearningforhandgesturerecognitionfromasinglecolorimage AT yiliu semisupervisedjointlearningforhandgesturerecognitionfromasinglecolorimage |
_version_ |
1724290263871913984 |