Abstract
Recognition technologies using digital cameras have gained considerable interest in recent years. However, even with the improvements of digital cameras, the quality of captured images often can be insufficient for the recognition in many practical cases. In order to recognize low-quality images, similarly degraded images should be used for training classifiers. This chapter presents a training method for the subspace method. It is named “Generative learning method,” since the training images are generated artificially from an original image. Conventional approaches used camera-captured images as training data, which required exhaustive collection of captured samples. The generative learning method, instead, allows to obtain these training images based on a small set of actual images. Since the training images need to be generated on the basis of actual degradation characteristics, the estimation step of the degradation characteristics is introduced. This framework is applied to traffic sign recognition that is one of the important tasks for driver support systems.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Murase, H.: Generative learning for image recognition. Trans. IPS Japan 46(SIG15, CVIM-12), 35–42 (2005) (in Japanese)
Ishii, K.: Generation of distorted characters and its applications. Systems and Computers in Japan 14(6), 19–27 (1983)
Horiuchi, T., Toraichi, K., Yamamoto, L., Yamada, H.: On method of training dictionaries for handwritten character recognition using relaxation matching. In: Proc. 2nd Int. Conf. on Document Analysis and Recognition, Tsukuba, Japan, pp. 638–641 (October 1993)
Doermann, D., Liang, J., Li, H.: Progress in camera-based document image analysis. In: Proc. 5th Int. Conf. on Document Analysis and Recognition, Edinburgh, Scotland, UK, pp. 606–616 (August 2003)
Andrew, H., Hunt, B.: Digital image restoration. Prentice-Hall, Englewood Cliffs (1977)
Oja, E.: Subspace methods of pattern recognition. Research Studies, Hertfordshire, UK (1983)
Bishop, R.: A survey of intelligent vehicle applications worldwide. In: Proc. IEEE 2000 Intelligent Vehicles Symp., Dearborn, MI, USA, pp. 25–30 (October 2000)
Geronimo, D., Lopez, A.M., Sappa, A.D., Graf, T.: Survey of pedestrian detection for advanced driver assistance systems. IEEE Trans. PAMI 32(7), 1239–1258 (2010)
Kamijo, S., Okumura, K., Kitamura, A.: Digital road map database for vehicle navigation and road information systems. In: Proc. Int. Conf. on Vehicle Navigation and Information Systems, Toronto, ON, Canada, pp. 319–323 (September 1989)
Escalera, A., Salichs, M.: Road traffic sign detection and classification. IEEE Trans. Industrial Electronics 44(12), 848–859 (1997)
Gavrila, D.: Multi-feature hierarchical template matching using distance transforms. In: Proc. 14th IAPR Int. Conf. on Pattern Recognition, Brisbane, QLD, Australia, vol. 1, pp. 439–444 (August 1998)
Miura, J., Kanda, T., Shirai, Y.: An active vision system for real-time traffic sign recognition. In: Proc. IEEE 2000 Intelligent Transportation Systems, Dearborn, MO, USA, pp. 52–57 (June 2000)
Mo, G., Aoki, Y.: A recognition method for traffic sign in color image. IEICE Trans. J87-D-II(12), 2124–2135 (2004) (in Japanese)
Uchimura, K., Kimura, H., Wakiyama, S.: Extraction and recognition of circular road signs using road scene color images. IEICE Trans. J81-A(4), 546–553 (1998) (in Japanese)
Matsuura, D., Yamauchi, H., Takahashi, H.: Extracting circular road signs using specific color distinction and region limitation. IEICE Trans. J85-D-II(6), 1075–1083 (2002) (in Japanese)
Lafuente-Arroyo, S., Gil-Jimenez, P., Maldonado-Bascon, R., Lopez-Ferreras, F.: Traffic sign shape classification evaluation I: SVM using distance to borders. In: Proc. IEEE 2005 Intelligent Vehicles Symp., Las Vegas, NV, USA, pp. 557–562 (June 2005)
Gil-Jimenez, P., Lafuente-Arroyo, S., Gomez-Moreno, H., Lopez-Ferreras, F., Maldonado-Bascon, S.: Traffic sign shape classification evaluation II: FFT applied to the signature of blobs. In: Proc. IEEE 2005 Intelligent Vehicles Symp., Las Vegas, NV, USA, pp. 607–612 (June 2005)
Bahlmann, C., Zhu, Y., Ramesh, V., Pellkofer, M., Koehler, T.: A system for traffic sign recognition, tracking, and recognition using color, shape, and motion information. In: Proc. IEEE 2005 Intelligent Vehicles Symp., Las Vegas, NV, USA, pp. 255–260 (June 2005)
Johansson, B.: Road sign recognition from a moving vehicle. Master’s thesis, Center for Image Analysis, Swedish University of Agricultural Science (2002)
Ishida, H., Takahashi, T., Ide, I., Mekada, Y., Murase, H.: Generation of training data by degradation models for traffic sign symbol recognition. IEICE Trans. E90-D(8), 1134–1141 (2007)
Yanadume, S., Mekada, Y., Ide, I., Murase, H.: Recognition of very low-resolution characters from motion images captured by a portable digital camera. In: Aizawa, K., Nakamura, Y., Satoh, S. (eds.) PCM 2004. LNCS, vol. 3331, pp. 247–254. Springer, Heidelberg (2004)
Daris, L.: Handbook of genetic algorithms. Van Nostrand Reinhold, New York (1991)
von Neumann, J.: Various techniques used in connection with random digits. National Bureau of Standards Series (12), 36–38 (1951)
Golub, G., Loan, C.: Matrix computations, 2nd edn. Cambridge Univ. Press, Cambridge (1992)
MIST project, http://mist.murase.m.is.nagoya-u.ac.jp/trac-en/
Smith, A.: Color Gamut transform pairs. Computer Graphics 12(3), 12–19 (1978)
Hirayama, K., Omachi, S., Aso, H.: String extraction from scene images using color and luminance information. IEICE Trans. J-89-D(4), 893–896 (2006) (in Japanese)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Ishida, H., Ide, I., Murase, H. (2014). Subspace Construction from Artificially Generated Images for Traffic Sign Recognition. In: Chen, YW., C. Jain, L. (eds) Subspace Methods for Pattern Recognition in Intelligent Environment. Studies in Computational Intelligence, vol 552. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-54851-2_4
Download citation
DOI: https://doi.org/10.1007/978-3-642-54851-2_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-54850-5
Online ISBN: 978-3-642-54851-2
eBook Packages: EngineeringEngineering (R0)