An Improved Algorithm of Hand-Gesture Recognition Based on Haar-Like Features and Adaboost
You Dong Ding, Hai Bo Pang · Advanced materials research · 2012
In this paper, we proposed an improved algorithm of hand-gesture recognition based on Haar-like features and Adaboost. Initial, we calculated the Haar-like features of hand-gesture images by integral image. Then, we used the principal components analysis method to reduce the dimension of Haar-like features. At last, an Adaboost classifier performed the hand-gesture recognition task with the hand-gesture features. A dataset with large hand gestures (12 types, 600 hand-gesture images) was built, including some large pose-angle (about 40 deg.) hand-gesture images. Our experiment results demonstrated that our method could effectively recognize different hand gesture, and the best appropriate N was 12. In addition, the average processing time of the proposed method was about 0.05 second for every image.