Multiscale Convolutional Neural Networks for Hand Detection

Unconstrained hand detection in still images plays an important role in many hand-related vision problems, for example, hand tracking, gesture analysis, human action recognition and human-machine interaction, and sign language recognition. Although hand detection has been extensively studied for dec...

Full description

Saved in:
Bibliographic Details
Main Authors: Shiyang Yan, Yizhang Xia, Jeremy S. Smith, Wenjin Lu, Bailing Zhang
Format: Article
Language:English
Published: Wiley 2017-01-01
Series:Applied Computational Intelligence and Soft Computing
Online Access:http://dx.doi.org/10.1155/2017/9830641
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849309028531830784
author Shiyang Yan
Yizhang Xia
Jeremy S. Smith
Wenjin Lu
Bailing Zhang
author_facet Shiyang Yan
Yizhang Xia
Jeremy S. Smith
Wenjin Lu
Bailing Zhang
author_sort Shiyang Yan
collection DOAJ
description Unconstrained hand detection in still images plays an important role in many hand-related vision problems, for example, hand tracking, gesture analysis, human action recognition and human-machine interaction, and sign language recognition. Although hand detection has been extensively studied for decades, it is still a challenging task with many problems to be tackled. The contributing factors for this complexity include heavy occlusion, low resolution, varying illumination conditions, different hand gestures, and the complex interactions between hands and objects or other hands. In this paper, we propose a multiscale deep learning model for unconstrained hand detection in still images. Deep learning models, and deep convolutional neural networks (CNNs) in particular, have achieved state-of-the-art performances in many vision benchmarks. Developed from the region-based CNN (R-CNN) model, we propose a hand detection scheme based on candidate regions generated by a generic region proposal algorithm, followed by multiscale information fusion from the popular VGG16 model. Two benchmark datasets were applied to validate the proposed method, namely, the Oxford Hand Detection Dataset and the VIVA Hand Detection Challenge. We achieved state-of-the-art results on the Oxford Hand Detection Dataset and had satisfactory performance in the VIVA Hand Detection Challenge.
format Article
id doaj-art-05e40578b8fa40ddab6bbc2dc8a4e7a9
institution Kabale University
issn 1687-9724
1687-9732
language English
publishDate 2017-01-01
publisher Wiley
record_format Article
series Applied Computational Intelligence and Soft Computing
spelling doaj-art-05e40578b8fa40ddab6bbc2dc8a4e7a92025-08-20T03:54:16ZengWileyApplied Computational Intelligence and Soft Computing1687-97241687-97322017-01-01201710.1155/2017/98306419830641Multiscale Convolutional Neural Networks for Hand DetectionShiyang Yan0Yizhang Xia1Jeremy S. Smith2Wenjin Lu3Bailing Zhang4Department of Computer Science and Software Engineering, Xi’an Jiaotong-Liverpool University, Suzhou 215123, ChinaDepartment of Computer Science and Software Engineering, Xi’an Jiaotong-Liverpool University, Suzhou 215123, ChinaDepartment of Electrical Engineering and Electronics, University of Liverpool, Liverpool, UKDepartment of Computer Science and Software Engineering, Xi’an Jiaotong-Liverpool University, Suzhou 215123, ChinaDepartment of Computer Science and Software Engineering, Xi’an Jiaotong-Liverpool University, Suzhou 215123, ChinaUnconstrained hand detection in still images plays an important role in many hand-related vision problems, for example, hand tracking, gesture analysis, human action recognition and human-machine interaction, and sign language recognition. Although hand detection has been extensively studied for decades, it is still a challenging task with many problems to be tackled. The contributing factors for this complexity include heavy occlusion, low resolution, varying illumination conditions, different hand gestures, and the complex interactions between hands and objects or other hands. In this paper, we propose a multiscale deep learning model for unconstrained hand detection in still images. Deep learning models, and deep convolutional neural networks (CNNs) in particular, have achieved state-of-the-art performances in many vision benchmarks. Developed from the region-based CNN (R-CNN) model, we propose a hand detection scheme based on candidate regions generated by a generic region proposal algorithm, followed by multiscale information fusion from the popular VGG16 model. Two benchmark datasets were applied to validate the proposed method, namely, the Oxford Hand Detection Dataset and the VIVA Hand Detection Challenge. We achieved state-of-the-art results on the Oxford Hand Detection Dataset and had satisfactory performance in the VIVA Hand Detection Challenge.http://dx.doi.org/10.1155/2017/9830641
spellingShingle Shiyang Yan
Yizhang Xia
Jeremy S. Smith
Wenjin Lu
Bailing Zhang
Multiscale Convolutional Neural Networks for Hand Detection
Applied Computational Intelligence and Soft Computing
title Multiscale Convolutional Neural Networks for Hand Detection
title_full Multiscale Convolutional Neural Networks for Hand Detection
title_fullStr Multiscale Convolutional Neural Networks for Hand Detection
title_full_unstemmed Multiscale Convolutional Neural Networks for Hand Detection
title_short Multiscale Convolutional Neural Networks for Hand Detection
title_sort multiscale convolutional neural networks for hand detection
url http://dx.doi.org/10.1155/2017/9830641
work_keys_str_mv AT shiyangyan multiscaleconvolutionalneuralnetworksforhanddetection
AT yizhangxia multiscaleconvolutionalneuralnetworksforhanddetection
AT jeremyssmith multiscaleconvolutionalneuralnetworksforhanddetection
AT wenjinlu multiscaleconvolutionalneuralnetworksforhanddetection
AT bailingzhang multiscaleconvolutionalneuralnetworksforhanddetection