A Static Hand Gesture Recognition Model based on the Improved Centroid Watershed Algorithm and a Dual-Channel CNN

Xude Dong, Yuanping Xu, Zhijie Xu, Jian Huang, Jun Lu, Chaolong Zhang, Li Lu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In order to achieve static hand gesture recognization within complex skin-like background regions in an effective and intelligent manner, this study proposed an integrated hand gesture recognition model based on the improved centroid watershed algorithm (ICWA) and a dual-channel convolutional neural network (DCCNN) structure. The effectiveness of this approach stemmed from more accurate segmentation of hand gestures from an original image by using the ICWA. The segmented image and the corresponding Local Binary Patterns (LBP) features extracted from the original image then serve as inputs for two channels of the devised DCCNN respectively for classification. The contributions of this study included an innovative method for reducing the image gradient difference while segmenting in the YCrCb color space, and the fusion of both Principal Component Analysis (PCA) for dimension reduction and a convexity detection process for identifying the secant line between the palm and arm. The devised DCCNN enables significant improvement on the static hand gesture classification accuracy by employing independent dual-convolution neural network framework for dealing with richer features at different scales. Tests and evaluations on benchmarking databases demonstrated that the devised models and techniques outperform classic methods with distinctive advantages when operating under challenging skin-like background conditions.

LanguageEnglish
Title of host publication2018 24th IEEE International Conference on Automation and Computing (ICAC 2018)
Subtitle of host publicationImproving Productivity through Automation and Computing
EditorsXiandong Ma
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages6
ISBN (Electronic)9781862203419
ISBN (Print)9781538648919
DOIs
Publication statusPublished - 1 Jul 2019
Event24th IEEE International Conference on Automation and Computing: Improving Productivity through Automation and Computing - Newcastle University, Newcastle upon Tyne, United Kingdom
Duration: 6 Sep 20187 Sep 2018
Conference number: 24
https://ieeexplore.ieee.org/xpl/conhome/8742895/proceeding (Website Containing the Proceedings)
http://www.cacsuk.co.uk/index.php/conferences/icac (Link to Conference Information)

Conference

Conference24th IEEE International Conference on Automation and Computing
Abbreviated titleICAC 2018
CountryUnited Kingdom
CityNewcastle upon Tyne
Period6/09/187/09/18
Internet address

Fingerprint

Hand Gesture Recognition
Gesture recognition
Centroid
Watersheds
Gesture
Neural Networks
Model-based
Neural networks
Skin
Color Space
Dimension Reduction
Benchmarking
Chord or secant line
Convolution
Network Structure
Principal component analysis
Principal Component Analysis
Convexity
Fusion
Fusion reactions

Cite this

Dong, X., Xu, Y., Xu, Z., Huang, J., Lu, J., Zhang, C., & Lu, L. (2019). A Static Hand Gesture Recognition Model based on the Improved Centroid Watershed Algorithm and a Dual-Channel CNN. In X. Ma (Ed.), 2018 24th IEEE International Conference on Automation and Computing (ICAC 2018): Improving Productivity through Automation and Computing [8749063] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/IConAC.2018.8749063
Dong, Xude ; Xu, Yuanping ; Xu, Zhijie ; Huang, Jian ; Lu, Jun ; Zhang, Chaolong ; Lu, Li. / A Static Hand Gesture Recognition Model based on the Improved Centroid Watershed Algorithm and a Dual-Channel CNN. 2018 24th IEEE International Conference on Automation and Computing (ICAC 2018): Improving Productivity through Automation and Computing. editor / Xiandong Ma. Institute of Electrical and Electronics Engineers Inc., 2019.
@inproceedings{d928d76017e74b64899d03c99d27caaa,
title = "A Static Hand Gesture Recognition Model based on the Improved Centroid Watershed Algorithm and a Dual-Channel CNN",
abstract = "In order to achieve static hand gesture recognization within complex skin-like background regions in an effective and intelligent manner, this study proposed an integrated hand gesture recognition model based on the improved centroid watershed algorithm (ICWA) and a dual-channel convolutional neural network (DCCNN) structure. The effectiveness of this approach stemmed from more accurate segmentation of hand gestures from an original image by using the ICWA. The segmented image and the corresponding Local Binary Patterns (LBP) features extracted from the original image then serve as inputs for two channels of the devised DCCNN respectively for classification. The contributions of this study included an innovative method for reducing the image gradient difference while segmenting in the YCrCb color space, and the fusion of both Principal Component Analysis (PCA) for dimension reduction and a convexity detection process for identifying the secant line between the palm and arm. The devised DCCNN enables significant improvement on the static hand gesture classification accuracy by employing independent dual-convolution neural network framework for dealing with richer features at different scales. Tests and evaluations on benchmarking databases demonstrated that the devised models and techniques outperform classic methods with distinctive advantages when operating under challenging skin-like background conditions.",
keywords = "Centroid watershed algorithm, Dual-channel convolution neural network, Hand gesture recognition, Hand gesture segmentation",
author = "Xude Dong and Yuanping Xu and Zhijie Xu and Jian Huang and Jun Lu and Chaolong Zhang and Li Lu",
year = "2019",
month = "7",
day = "1",
doi = "10.23919/IConAC.2018.8749063",
language = "English",
isbn = "9781538648919",
editor = "Xiandong Ma",
booktitle = "2018 24th IEEE International Conference on Automation and Computing (ICAC 2018)",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Dong, X, Xu, Y, Xu, Z, Huang, J, Lu, J, Zhang, C & Lu, L 2019, A Static Hand Gesture Recognition Model based on the Improved Centroid Watershed Algorithm and a Dual-Channel CNN. in X Ma (ed.), 2018 24th IEEE International Conference on Automation and Computing (ICAC 2018): Improving Productivity through Automation and Computing., 8749063, Institute of Electrical and Electronics Engineers Inc., 24th IEEE International Conference on Automation and Computing, Newcastle upon Tyne, United Kingdom, 6/09/18. https://doi.org/10.23919/IConAC.2018.8749063

A Static Hand Gesture Recognition Model based on the Improved Centroid Watershed Algorithm and a Dual-Channel CNN. / Dong, Xude; Xu, Yuanping; Xu, Zhijie; Huang, Jian; Lu, Jun; Zhang, Chaolong; Lu, Li.

2018 24th IEEE International Conference on Automation and Computing (ICAC 2018): Improving Productivity through Automation and Computing. ed. / Xiandong Ma. Institute of Electrical and Electronics Engineers Inc., 2019. 8749063.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A Static Hand Gesture Recognition Model based on the Improved Centroid Watershed Algorithm and a Dual-Channel CNN

AU - Dong, Xude

AU - Xu, Yuanping

AU - Xu, Zhijie

AU - Huang, Jian

AU - Lu, Jun

AU - Zhang, Chaolong

AU - Lu, Li

PY - 2019/7/1

Y1 - 2019/7/1

N2 - In order to achieve static hand gesture recognization within complex skin-like background regions in an effective and intelligent manner, this study proposed an integrated hand gesture recognition model based on the improved centroid watershed algorithm (ICWA) and a dual-channel convolutional neural network (DCCNN) structure. The effectiveness of this approach stemmed from more accurate segmentation of hand gestures from an original image by using the ICWA. The segmented image and the corresponding Local Binary Patterns (LBP) features extracted from the original image then serve as inputs for two channels of the devised DCCNN respectively for classification. The contributions of this study included an innovative method for reducing the image gradient difference while segmenting in the YCrCb color space, and the fusion of both Principal Component Analysis (PCA) for dimension reduction and a convexity detection process for identifying the secant line between the palm and arm. The devised DCCNN enables significant improvement on the static hand gesture classification accuracy by employing independent dual-convolution neural network framework for dealing with richer features at different scales. Tests and evaluations on benchmarking databases demonstrated that the devised models and techniques outperform classic methods with distinctive advantages when operating under challenging skin-like background conditions.

AB - In order to achieve static hand gesture recognization within complex skin-like background regions in an effective and intelligent manner, this study proposed an integrated hand gesture recognition model based on the improved centroid watershed algorithm (ICWA) and a dual-channel convolutional neural network (DCCNN) structure. The effectiveness of this approach stemmed from more accurate segmentation of hand gestures from an original image by using the ICWA. The segmented image and the corresponding Local Binary Patterns (LBP) features extracted from the original image then serve as inputs for two channels of the devised DCCNN respectively for classification. The contributions of this study included an innovative method for reducing the image gradient difference while segmenting in the YCrCb color space, and the fusion of both Principal Component Analysis (PCA) for dimension reduction and a convexity detection process for identifying the secant line between the palm and arm. The devised DCCNN enables significant improvement on the static hand gesture classification accuracy by employing independent dual-convolution neural network framework for dealing with richer features at different scales. Tests and evaluations on benchmarking databases demonstrated that the devised models and techniques outperform classic methods with distinctive advantages when operating under challenging skin-like background conditions.

KW - Centroid watershed algorithm

KW - Dual-channel convolution neural network

KW - Hand gesture recognition

KW - Hand gesture segmentation

UR - http://www.scopus.com/inward/record.url?scp=85069216991&partnerID=8YFLogxK

U2 - 10.23919/IConAC.2018.8749063

DO - 10.23919/IConAC.2018.8749063

M3 - Conference contribution

SN - 9781538648919

BT - 2018 24th IEEE International Conference on Automation and Computing (ICAC 2018)

A2 - Ma, Xiandong

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Dong X, Xu Y, Xu Z, Huang J, Lu J, Zhang C et al. A Static Hand Gesture Recognition Model based on the Improved Centroid Watershed Algorithm and a Dual-Channel CNN. In Ma X, editor, 2018 24th IEEE International Conference on Automation and Computing (ICAC 2018): Improving Productivity through Automation and Computing. Institute of Electrical and Electronics Engineers Inc. 2019. 8749063 https://doi.org/10.23919/IConAC.2018.8749063