Idioma:

HGR-Net: a fusion network for hand gesture segmentation and recognition

Dadashzadeh, Amirhossein ; Targhi, Alireza Tavakoli ; Tahmasbi, Maryam ; Mirmehdi, Majid

IET computer vision, 2019-12, Vol.13 (8), p.700-707 [Periódico revisado por pares]

The Institution of Engineering and Technology

Texto completo disponível

Citações Citado por

Enviar para

Título:
HGR-Net: a fusion network for hand gesture segmentation and recognition
Autor: Dadashzadeh, Amirhossein ; Targhi, Alireza Tavakoli ; Tahmasbi, Maryam ; Mirmehdi, Majid
Assuntos: cluttered backgrounds ; complex backgrounds ; convolutional neural nets ; depth information ; feature extraction ; fully convolutional residual network ; fusion network ; gesture recognition ; hand gesture segmentation ; hand regions ; hand segmentation ; HGR-Net ; image classification ; image segmentation ; learning (artificial intelligence) ; object detection ; real-world applications ; recognition stage ; red-green-blue and segmented images ; redundant information ; Research Article ; robust recognition ; scene background ; segmentation stage architecture ; segmentation sub-network ; segmented images ; spatial pyramid pooling ; static hand gestures ; two-stage convolutional neural network architecture ; unconstrained environmental factors
É parte de: IET computer vision, 2019-12, Vol.13 (8), p.700-707
Descrição: We propose a two-stage convolutional neural network (CNN) architecture for robust recognition of hand gestures, called HGR-Net, where the first stage performs accurate semantic segmentation to determine hand regions, and the second stage identifies the gesture. The segmentation stage architecture is based on the combination of fully convolutional residual network and atrous spatial pyramid pooling. Although the segmentation sub-network is trained without depth information, it is particularly robust against challenges such as illumination variations and complex backgrounds. The recognition stage deploys a two-stream CNN, which fuses the information from the red–green–blue and segmented images by combining their deep representations in a fully connected layer before classification. Extensive experiments on public datasets show that our architecture achieves almost as good as state-of-the-art performance in segmentation and recognition of static hand gestures, at a fraction of training time, run time, and model size. Our method can operate at an average of 23 ms per frame.
Editor: The Institution of Engineering and Technology
Idioma: Inglês

Voltar para lista de resultados

Anterior Resultado 4 Avançar Ir para próxima página

Realização: Logos de Redes Sociais:

HGR-Net: a fusion network for hand gesture segmentation and recognition

Dadashzadeh, Amirhossein ; Targhi, Alireza Tavakoli ; Tahmasbi, Maryam ; Mirmehdi, Majid

The Institution of Engineering and Technology

Buscando em bases de dados remotas. Favor aguardar.