Dynamic Hand Gesture Recognition using PCA, Pruning and ANN

Gesture recognition has the potential to be a natural and powerful tool supporting efficient and intuitive interaction between the human and the computer. The primary goal of hand gesture recognition research is to create a system which can identify specific hand gestures and use them to convey information for device control. This paper proposes a visionbased dynamic hand gesture recognition system using PCA, pruning and ANN. The system will find hand location in each frame. The hand segmentation is done using color marker for PCA. Skin color detection method is used for pruning and ANN. After connecting all these hand locations, the template is generated at the end of Segmentation. Template is used to extract the feature for training and testing purpose. The implementation uses the eigenspace which is determined by processing the eigenvalues and eigenvectors of the image set. The experimental results show ANN method gives more recognition rate than PCA and pruning.