Real-time hand gesture recognition base on Viola -Jones method, algorithm CAMShift, wavelet transform and principal component analysis

The task of hand gesture recognition on digital images and in video sequence in real-time is considered. A novel algorithm based on wavelet transform and principal component analysis is proposed for hand gesture recognition on digital images. The experiment results show that the proposed algorithm has the high rate of hand gesture recognition. A novel complex algorithm using Viola - Jones method, algorithm CAMShift, wavelet transform and principal component analysis is proposed for hand gesture recognition in video sequence. It is shown that use of the proposed algorithm has processing speed about 30 frames per second and allows recognizing hand gesture video sequence in real time. In this paper, a part of Cambridge Gesture database is used for testing the performance of hand gesture recognition algorithm on digital images. This database consists of 5 parts. The contrast condition of each part is not the same. All the hand gestures are divided into 12 classes using for recognition. For each part one hand gesture database, containing 200 images of each class (summary 12x200 = 2400 images), is created for testing this algorithm. The combining testing database of all 5 parts contains 1000 images of each class (summary 12x1000 = 12 000 images). For each part one training database also is created. This training database contains 20 images of each class (summary 12x20 = 240 images). The combining testing database of all 5 parts contains 100 images of each class (summary 12x100 = 1200 images). Testing results of the proposed algorithm show that the number of rightly recognized hand gestures is 94.63 %.

Keywords

Authors

References