Journal
IET COMPUTER VISION
Volume 13, Issue 8, Pages 700-707Publisher
WILEY
DOI: 10.1049/iet-cvi.2018.5796
Keywords
feature extraction; gesture recognition; image classification; image segmentation; learning (artificial intelligence); object detection; convolutional neural nets; fusion network; hand gesture segmentation; robust recognition; real-world applications; cluttered backgrounds; unconstrained environmental factors; hand segmentation; redundant information; scene background; recognition stage; two-stage convolutional neural network architecture; hand regions; segmentation stage architecture; fully convolutional residual network; segmentation sub-network; depth information; complex backgrounds; segmented images; static hand gestures; HGR-Net; spatial pyramid pooling; red-green-blue and segmented images; HGR-Net
Ask authors/readers for more resources
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 23ms per frame.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available