We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Static Hand Gesture Recognition Based on Gaussian Mixture Model and Partial Differential Equation.
- Authors
Qinghe Zheng; Xinyu Tian; Shilei Liu; Mingqiang Yang; Hongjun Wang; Jiajie Yang
- Abstract
In the hand gesture recognition process, manually designed features are difficult to achieve good results under the condition of changeable gestures and complex backgrounds. In this paper, we propose a hand gesture recognition method based on Gaussian skin color model and deep convolutional neural network (DCNN). For gesture images in different backgrounds, we first use the Gaussian skin color model to segment the gesture area, then we use the DCNN to establish gesture classification model. Finally, we use the back propagation algorithm based on partial differential equation to train the neural network on the pure gesture data samples to converge to the global optimum, and obtain the classification results. The model combines the process of feature extraction and classification, simulates the biological visual transmission and cognition, and effectively avoids the subjectivity and limitations of artificial features. And model reduces the size and the complexity of network by using weights sharing and pooling technology. Experimental results show that the method is efficient for gesture representation and classification. The average classification accuracies under two datasets (indoor and outdoor environments) are both more than 99%. Compared with the traditional methods, the proposed method has higher classification accuracy and speed.
- Subjects
HUMAN facial recognition software; ARTIFICIAL neural networks; SUPPORT vector machines; PARTIAL differential equations; COMPUTER vision
- Publication
IAENG International Journal of Computer Science, 2018, Vol 45, Issue 4, p17
- ISSN
1819-656X
- Publication type
Article