This Article 
 Bibliographic References 
 Add to: 
Object Recognition Robust Under Translations, Deformations, and Changes in Background
July 1997 (vol. 19 no. 7)
pp. 769-775

Abstract—Recognition systems based on model matching using low level features often fail due to a variation in background. As a solution, I present a system for the recognition of human faces independent of hairstyle. Correspondence maps between an image and a model are established by coarse-fine matching in a Gabor pyramid. These are used for hierarchical recognition.

[1] J.G. Daugman, “Complete Discrete 2D Gabor Transforms by Neural Networks for Image Analysis and Compression,” IEEE Trans. Acoustics, Speech, and Signal Processing, vol. 36, no. 7, 1988.
[2] M. Lades, J.C. Vorbruggen, J. Buhmann, J. Lange, C. von der Malsburg, R.P. Wurtz, and W. Konen, “Distortion Invariant Object Recognition in the Dynamic Link Architecture,” IEEE Trans. Computers, vol. 42, no. 3, pp. 300-311, Mar. 1993.
[3] T.S. Lee, “Image Representation Using 2D Gabor Wavelets,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 18, no. 10, pp. 959-971, Oct. 1996.
[4] R.P. Würtz, Multilayer Dynamic Link Networks for Establishing Image Point Correspondences and Visual Object Recognition, vol. 41, Reihe Physik. Thun, Frankfurt am Main, Germany: Verlag Harri Deutsch, 1995.
[5] D.J. Fleet, Measurement of Image Velocity.Dordrecht, Netherlands: Kluwer Academic Publishers, 1992.
[6] R. Phillips, "Why Are Faces Hard to Recognize in Photographic Negatives?," Perception and Psychophysics, vol. 12, pp. 425-426, 1972.
[7] S.J. McKenna, S. Gong, R.P. Würtz, J. Tanner, and D. Banin, "Tracking Facial Feature Points With Gabor Wavelets and Shape Models," Proc. First Int'l Conf. Audio- and Video-Based Biometric Person Authentication, J. Bigün, G. Chollet, and G. Borgefors, eds. Crans-Montana, Switzerland, Mar. 1997, LNCS, vol. 1,206, pp. 35-42. Springer Verlag, 1997.
[8] M. Bichsel, ed., Int'l Workshop on Automatic Face- and Gesture-Recognition, MultiMedia Lab, Department of Computer Science, University of Zürich, June 1995. Winterthurerstrsse 190, CH-8057 Zurich, Switzerland,

Index Terms:
Object recognition, face recognition, coarse-to-fine strategy, parallel processing, Gabor function, wavelet transform, image pyramid, correspondence problem, background independence.
Rolf P. Würtz, "Object Recognition Robust Under Translations, Deformations, and Changes in Background," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 769-775, July 1997, doi:10.1109/34.598234
Usage of this product signifies your acceptance of the Terms of Use.