Abstract
Hand gesture recognition based on computer vision is considered as an efficient approach to establish communication between human and computer. This research provides a novel system to recognize dynamic hand gestures as different functions of mouse. For this purpose, a white glove is utilized in which fingertips have five different colors. Then, based on the functions of the mouse, 11 dynamic hand gestures are defined. In order to track the hand in each frame, the optical flow and GMM algorithms are used. Then, by using the mean and variance of the colors in each RGB plane, trajectories of the fingertips are detected. To make the acquired information richer, the Representative Trajectory of these five trajectories is computed. Features are extracted from the curves through a process inspired by the concept of shape context. In this process, each trajectory is normalized and then the histogram of extracted vector from normalized curve is calculated in a log-polar space. Thus, by this descriptor, a feature vector with length of 672 is created. Using the defined 11 dynamic gestures, a dataset including 220 observations is constructed and by using the aforementioned features, the relevant training matrix is formed. By employing PCA and Sequential Feature Selection techniques, dimension of the feature vector is reduced. For the experiment, different classifiers are applied and the experimental results confirm the privileged performance of the proposed system for the intelligent visual mouse.
Similar content being viewed by others
References
Lee, J.Y., Rhee, G.W., Seo, D.W.: Hand gesture-based tangible interactions for manipulating virtual objects in a mixed reality environment. Int. J. Adv. Manuf. Technol. 51, 1069–1082 (2010)
Hu, C., Liang, L., Ma, S., Lu, H.: Virtual Mouse—Inputting Device by Hand Gesture Tracking and Recognition. National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing (2000)
Rautaray, S.S., Agrawal, A.: Interaction with virtual game through hand gesture recognition. In: International conference on multimedia, signal processing and communication technologies, 2011
Starner, T., Auxier, J., Ashbrook, D., Gandy, M.: The gesture pendant: a self-illuminating, wearable, infrared computer vision system for home automation control and medical monitoring. In: Proc. of IEEE int. symposium on 2000
Agris, U.V., Zieren, J., Canzler, U., Bauer, B., Kraiss, K.-F.: Recent developments in visual sign language recognition. Univ. Access Inf. Soc. 6, 323–362 (2008)
Kim, J.-H., Thang, N. D., Kim, E.-S.: 3-D hand motion tracking and gesture recognition using a data glove. In: IEEE international symposium on industrial electronics. Seoul (2009)
Murthy, G.R.S., Jadon, R.S.: A review of vision based hand gestures recognition. Int. J. Inf. Technol. Knowl. Manag. 2(2), 405–410 (2009)
Zhao, Z.-Y., Gao, W.-L., Zhu, M.-M., Yu, L.: A vision based method to distinguish and recognize static and dynamic gesture. In: International workshop on information and electronics engineering (IWIEE) (2012)
Ramamoorthy, A., Vaswani, N., Chaudhury, S., Banerjee, S.: Recognition of dynamic hand gestures. Pattern Recogn. 36, 2069–2081 (2003)
Maccormick, J., Blake, A.: A probabilistic contour discriminant for object localisation, pp. 390–395 (1998)
Alon, J., Athitsos, V., Yuan, Q., Sclaroff, S.: Simultaneous localization and recognition of dynamic hand gestures. In: Proc. IEEE workshop on motion and video computing (2005)
Müller, M.: Dynamic time warping. Information retrieval for music and motion, pp. 69–82. Springer, Berlin (2007)
Bao, J., Song, A., Guo, Y., Tang, H.: Dynamic hand gesture recognition based on SURF tracking. In: Electric information and control engineering (ICEICE), Wuhan (2011)
Bay, H., Ess, A., Tuytelaars, T., Gool, L.V.: SURF: speeded up robust features. Comput. Vision Image. Underst. (CVIU) 110(3), 346–359 (2008)
Laptev, I., Indeberg, T.L.: Space-time interest points. In: The ninth ieee international conference on computer vision (ICCV) (2003)
Shen, X., Hua, G., Williams, L., Wu, Y.: Dynamic hand gesture recognition: an exemplar-based approach from motion divergence fields. Image Vis. Comput. 30, 227–235 (2011)
Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide baseline stereo from maximally stable extremal regions. In: Proc. of British machine vision conference (2002)
Nistér, D., Stewénius, H.: Scalable recognition with a vocabulary tree. In: Computer vision and pattern recognition (2006)
Lienhart, R., Maydt, J.: An extended set of haar-like features for rapid object detection. In: IEEE ICIP (2002)
Rojas, R.: AdaBoost and the super bowl of classi a tutorial introduction to adaptive boosting. Computer Science Departmen, Freie Universitat, Berlin (2009)
Stern, H., Shmueli, M., Berman, S.: Most discriminating segment—longest common subsequence (MDSLCS) algorithm for dynamic hand gesture classification. Pattern Recognit. Lett. 34(15), 1980–1989 (2013)
Li, H., Greenspan, M.: Model-based segmentation and recognition of dynamic gestures in continuous video streams. Pattern Recogn. 44, 1614–1628 (2011)
Bhuyan, M., Ghosh, D., Bora, P.: Feature extraction from 2D gesture trajectoy in dynamic hand gesture recognition. Cybernetics and intelligent systems. Chulalongkorn Univ, Bangkok (2006)
Bhuyan, M.K., Ghosh, D., Bora, P.K.: Estimation of 2D motion trajectories from video object planes and its application in hand gesture recognition. Pattern recognition and machine intelligence. Indian Statistical Institute, Kolkata (2005)
Barron, J.L., Fleet, D., Beauchemin, S.: Performance of optical flow techniques. IEEE 1, 236–242 (1992)
Fleet, D.J., Weiss, Y.: Optical flow estimation, handbook of mathematical models in computer vision. Springer, New York (2006)
Belongie, S., Malik, J.: Matching with shape contexts. In: IEEE workshop on content based access of image and video libraries (2000)
de Boor, C.: A practical guide to splines. Springer-Verlag, New York (1978)
Kohavi, R.: A study of cross validation and bootstrap for accuracy estimation and model selection. In: Proceedings of the fourteenth international joint conference on artificial intelligence, San Mateo (1995)
de La Gorce, M., Paragios, N.: A variational approach to monocular hand-pose estimation. Comput. Vis. Image Underst. 114, 363–372 (2010)
Elmezain, M., Al-Hamadi, A., Michaelis, B.: A robust method for hand gesture segmentation and recognition using forward spotting scheme in conditional random fields. In: international conference on pattern recognition, Istanbul (2010)
Wenjun, T., Chengdong, W., Shuying, Z., Li, J.: Dynamic hand gesture recognition using motion trajectories and key frames. In: 2nd international conference on advanced computer control (ICACC), Shenyang (2010)
Kao, C.-Y., Fahn, C.-S.: A human-machine interaction technique: hand gesture recognition based on hidden markov models with trajectory of hand motion. Procedia Eng 15, 3739–3743 (2011)
Al-Hamadi, A., Elmezain, M., Michaelis, B.: Hand gesture recognition based on combined features extraction. Int. J. Inf. Math. Sci. 6(1), 1–6 (2010)
Lamberti, L., Camastra, F.: Handy: A real-time three color glove-based gesture recognizer with learning vector quantization. Expert Syst. Appl. 39(12), 10489–10494 (2012)
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by B. Prabhakaran.
Rights and permissions
About this article
Cite this article
Maleki, B., Ebrahimnezhad, H. Intelligent visual mouse system based on hand pose trajectory recognition in video sequences. Multimedia Systems 21, 581–601 (2015). https://doi.org/10.1007/s00530-014-0420-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00530-014-0420-y