UDC 004.93:004.89
STATIC HAND GESTURES RECOGNITION SYSTEM WITH USING DEPTH CAMERA
D. Zh. Satybaldina, Ph.D. (Phys. and Math.), professor of Computer Engineering Department, L.N.Gumilyov ENU, Nur-Sultan, Kazakhstan;
orcid.org/0000-0003-0291-4685, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
G. V. Ovechkin, Dr. Sc. (Tech.), full professor, Head of the Department, RSREU, Ryazan, Russia;
orcid.org/0000-0001-6887-2217, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
G. A. Kalymova, Ph.D. student, L.N.Gumilyov Eurasian National University, Nur-Sultan, Kazakhstan;
orcid.org/0000-0003-0610-740X, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
The aim of the work is to develop a system for static hand gestures recognition based on a convolutional neural network using transfer learning framework. The gesture recognition system consists of a gesture capture device (sensor), preprocessing and image segmentation algorithms, a feature extraction and gestures classification block. This work is performed in Python 3.6 tools. As a sensor, Intel® RealSense™ depth camera D435 is used. Several Python libraries, which provide solid implementations of image processing and segmentation, are used. The subsystem for features extracting and gestures classification is based on the modified VGG-16, being realized with the help of TensorFlow & Keras deep learning frameworks. Experimental results show that the proposed model, trained on the database of 2000 images, provides high recognition accuracy on testing stage.
Key words: intelligent information systems and technologies, deep learning, depth camera, gesture recognition, convolutional neural network, Keras, OpenCV, Python, TensorFlow, VGG-16.