Hand Gesture Recognition using k-means clustering and Convolutional neural networks

Electronics and Communication Engineering

Hand gesture recognition can be defined as an ability of a computer to recognize meaningful expressions of form and motion by a human involving only the hands. These hand gesture recognitions have plenty of replications which can be applied for improving control, accessibility, communication and learning. There is a complexity issue with this hand gesture recognition feature extraction, for example the variation of the light and background. In this paper, the convolution neural network is applied for the recognition of gestures, and the characteristics of convolution neural network are used to overcome the issue of feature extraction process and reduce the number of parameters needs to be trained. The purpose of unsupervised learning, error back propagation algorithm can be finally achieved which is loaded into the convolution neural network algorithm, modify the threshold and weights of neural network to reduce the error of the model. The advantage of our method is that there is no need for feature extraction. Without explicitly segmenting foreground the proposed CNN learns to recognize the hand pose even in presence of complex, varying background or illumination.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.