Abstract
This paper discusses a Japanese hand sign recognition system with a simple classifier network. In the system, input hand images are preprocessed through horizontal/vertical projection followed by discrete Fourier transforms (DFTs) that calculate the magnitude spectrum. The magnitude spectrum is used as the feature vector. Use of the magnitude spectrum makes the system very robust against the position changes of the hand image. The final classification is carried out by the classifier network, which uses simple neurons. Each neuron evaluates the possibility of the input vector belonging to assigned cluster. From the evaluation results, the hand sign is identified. The feasibility of the system is verified by simulations. The simulation results show that the average recognition rate of the system is 93% even though the hand positions are changed randomly.
Keywords
- Feature Vector
- Input Vector
- Recognition Rate
- Discrete Fourier Transform
- Radial Basis Function Neural Network
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Pavlovic, V.I., Sharma, R., Huang, T.S.: Visual Interpretation of Hand Gestures for Human-Computer Interaction: A Review. IEEE Trans. Pattern Analysis and Machine Intelligence 19, 677–695 (1997)
Triesch, J., von der Malsburg, C.: A System for Person-Independent Hand Posture Recognition against Complex Backgrounds. IEEE Trans. Pattern Analysis and Machine Intelligence 23(12), 1449–1453 (2001)
Hoshino, K., Tanimoto, T.: Realtime Hand Posture Estimation with Self-Organizing Map for Stable Robot Control. IEICE Trans. on Information and Systems E89-D(6), 1813–1819 (2006)
Bobick, A.F., Wilson, A.D.: A state-based approach to the representtion and recognition of gesture. IEEE Trans. Pattern Analysis and Machine Intelligence 19(12), 1325–1337 (1997)
Yang, H.-H., Ahuja, N., Tabb, M.: Extraction of 2D motion trajectories and its application to hand gesture recogntion. IEEE Trans. Pattern Analysis and Machine Intelligence 24(8), 1061–1074 (2002)
Chu, F., Wang, L.: Applying RBF Neural Network to Cancer Classification Based on Gene Expressions. In: Proc. IJCNN 2006, pp. 3888–3892 (2006)
Chen, S., Harris, C.J., Hong, X.: Construction of RBF Classifiers with Tunable Units Using Orthgonal Forward Selection Based on Leave-One-Out Misclassification Rate. In: Proc. IJCNN 2006, pp. 6390–6394 (2006)
Bors, A.G., Gabbouj, G.: Minimal topology for a radial basis function neural network for pattern classification. Digital Signal Processing: a review journal 2(2), 302–309 (1994)
Matsubara, S., Hikawa, H.: Hardware Friendly Vector Quantization Algorithm. In: Proc. IEEE ISCAS 2005, pp. 3623–3626 (2005)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Fujimura, H., Sakai, Y., Hikawa, H. (2008). Japanese Hand Sign Recognition System. In: Ishikawa, M., Doya, K., Miyamoto, H., Yamakawa, T. (eds) Neural Information Processing. ICONIP 2007. Lecture Notes in Computer Science, vol 4984. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69158-7_101
Download citation
DOI: https://doi.org/10.1007/978-3-540-69158-7_101
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-69154-9
Online ISBN: 978-3-540-69158-7
eBook Packages: Computer ScienceComputer Science (R0)