Finger Recognition and Tracking Algorithm Based on Single Optical Camera

Abstract:

A new synthesis method of fingertip detection based on single camera is proposed, which effectively reduces the amount of computation while not relying on hardware performance too much. It provides portability as well because single camera is easy to get in contemporary devices, such as mobile phone. The main idea is to use the curvature of fingertip as a feature to distinguish the tip-part of finger in tracing the motion of hand. The Camshift algorithm is used to track the whole hand to diminish the detective region. The skin-color extraction method is used as an auxiliary part to enhance the ability of discriminating hand from background, which also helps to weaken the interferences produced by brightness of hand surface. Finally a serial frames is used to examine the performance of the new method. With the tracking part and the fingertip recognition part being tested respectively, the result indicates the performance clearly.

• Periodical: Applied Mechanics and Materials (Volume 615)
• Pages: 181-188
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.615.181
• Online since: August 2014
• Authors: Rui Nan, Ming Li Yang*
• Keywords: Camshift Tracking Algorithm, Fingertip Detection, Skin Color Extraction

References

[1] Yang D D, Jin L W, Yin J X. An effective robust fingertip detection method for finger writing character recognition system[C]/Machine Learning and Cybernetics, 2005. Proceedings of 2005 International Conference on. IEEE, 2005, 8: 4991-4996.

DOI: 10.1109/icmlc.2005.1527822

[2] Pavlovic V I, Sharma R, Huang T S. Visual interpretation of hand gestures for human-computer interaction: A review[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 1997, 19(7): 677-695.

DOI: 10.1109/34.598226

[3] Hsieh C C, Tsai M R, Su M C. A fingertip extraction method and its application to handwritten alphanumeric characters recognition [C]/Signal Image Technology and Internet Based Systems, 2008. SITIS'08. IEEE International Conference on. IEEE, 2008: 293-300.

DOI: 10.1109/sitis.2008.17

[4] Simion G, Gui V, Otesteanu M. Finger detection based on hand contour and colour information [C]/Applied Computational Intelligence and Informatics (SACI), 2011 6th IEEE International Symposium on. IEEE, 2011: 97-100.

DOI: 10.1109/saci.2011.5872979

[5] Rosales R, Athitsos V, Sigal L, et al. 3D hand pose reconstruction using specialized mappings [C]/Computer Vision, 2001. ICCV 2001. Proceedings. Eighth IEEE International Conference on. IEEE, 2001, 1: 378-385.

DOI: 10.1109/iccv.2001.937543

[6] Pavlovic V I, Sharma R, Huang T S. Visual interpretation of hand gestures for human-computer interaction: A review[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 1997, 19(7): 677-695.

DOI: 10.1109/34.598226

[7] Lee C C, Shih C Y, Jeng B S. Fingertip-Writing Alphanumeric Character Recognition for Vision-Based Human Computer Interaction[C]/Broadband, Wireless Computing, Communication and Applications (BWCCA), 2010 International Conference on. IEEE, 2010: 533-537.

DOI: 10.1109/bwcca.2010.127

[8] Kim J M, Lee W K. Hand shape Recognition using fingertips[C]/Fuzzy Systems and Knowledge Discovery, 2008. FSKD'08. Fifth International Conference on. IEEE, 2008, 4: 44-48.

DOI: 10.1109/fskd.2008.383

[9] Ying H, Song J, Ren X, et al. Fingertip detection and tracking using 2D and 3D information[C]/Intelligent Control and Automation, 2008. WCICA 2008. 7th World Congress on. IEEE, 2008: 1149-1152.

DOI: 10.1109/wcica.2008.4593085

[10] Gutchess D, Trajkovics M, Cohen-Solal E, et al. A background model initialization algorithm for video surveillance[C]/Computer Vision, 2001. ICCV 2001. Proceedings. Eighth IEEE International Conference on. IEEE, 2001, 1: 733-740.

DOI: 10.1109/iccv.2001.937598