Gesture recognition, as an important means of human-computer interaction, can achieve more natural and flexible human-computer interaction, so it has been widely concerned by researchers in the field of computer vision. At present, most gesture recognition algorithms are based on monocular visual images and recognize the apparent features of hands. Most gesture image segmentation methods are carried out in color space according to skin color information. These methods are highly susceptible to interference from the external environment, such as lighting, background, etc. Convolutional neural network has the advantages of strong anti-interference and outstanding self-organization and self-learning ability. Therefore, based on the principle of convolutional neural network, a novel deep convolutional neural network dedicated to gesture recognition was designed in this paper. This network combines skin color information with finger position information for gesture recognition. Experimental results showed that the algorithm based on fingertip position information has better performance than the algorithm based solely on skin color information. Moreover, the network has simple structure and few parameters. Compared with VGG16 and other classical networks, the recognition accuracy is basically the same under the premise of fewer parameters and structural layers, and the recognition effect is better than other classical networks.
With the promotion of smart city and other technologies, the application of embedded vision detection equipment is becoming more and more popular, among which gesture recognition is an important application of embedded vision detection equipment. At present, gesture recognition technology on embedded visual detection equipment is mostly implemented by calling API in domestic and foreign researches and products. But this method needs the support of stable communication network and has certain delay problem. To solve the above problems, this paper proposes a lightweight neural network model that can be deployed on embedded devices, which can realize local gesture recognition on embedded terminals without network remote transmission. The network builds a training framework on PyTorch and uses a homemade dataset for training, then lightens the network and finally deploys on raspberry PI for gesture recognition. Experimental results show that this network can run at a higher rate in raspberry PI 4B (4GB), and the model size is greatly reduced. The final recognition effect is good, and it has high practical value.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.