Application of support vector machine algorithm based gesture recognition technology in human-computer interaction

Abstract

Gesture recognition technology is an important part of human-computer interaction. This study focused on the application of support vector machine (SVM) in gesture recognition. The gesture image was segmented by YCgCr color space based skin color segmentation method. Then four Hu invariant moments and the ratio of area to circumference of gesture were taken as eigenvalues to extract gesture features. Finally, SVM was used for recognition. It was found that the proposed method had good performance in gesture recognition and could segment the collected images accurately. The recognition rate of Hu invariant moments based SVM algorithm reached 99.2% in the recognition of the six gestures designed in this study, which was 9.2% higher than that of HMM algorithm. The proposed method is reliable and feasible and can achieve simple man-machine interaction.