Abstract
Log-Polar transformation is an approximate model of human vision. If using it to recognize human faces, a reference point for the transformation is necessary, and the position of the reference point influences the recognition accuracy directly. However, it is difficult to extract an appropriate reference point from an image automatically. This paper proposes a face recognition method that detects the face center point as a reference point for Log-Polar transformation automatically. It is easier than before to recognize the faces by using Log-Polar transformation with the propose method.
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
Hitoshi, H., Mamoru, Y., Kazuhiko, Y.: Face Recognition Using an Adaptive Discriminant Space. In: IEICE. PRMU 2001, vol. 121, pp. 59–62 (2001)
Maki, M., Kiyomi, N.: Real-time Iris Recognition System Using a Rotation Spreading Neural Network. In: IEICE. NC 2002, vol. 207, pp. 25–30 (2003)
Kazuhiro, H., Takio, K., Taketoshi, M.: Scale Invariant Recognition Method Using Spectral Features Extracted From Log-Polar Image. In: IEICE. PRMU 1999, vol. 110, pp. 69–76 (1999)
Takayuki, N., Yue, B., Naofumi, F.: A 3D Log-Polar transform for Pattern Recognition. Systems and Computers in Japan 38(13), 49–57 (2007)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bao, Y., Qi, B., Gu, F. (2011). High-Speed Facial Recognition Using Log-Polar Transformation. In: Tan, H. (eds) Informatics in Control, Automation and Robotics. Lecture Notes in Electrical Engineering, vol 132. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-25899-2_19
Download citation
DOI: https://doi.org/10.1007/978-3-642-25899-2_19
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-25898-5
Online ISBN: 978-3-642-25899-2
eBook Packages: EngineeringEngineering (R0)