This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Affine Invariant Pattern Recognition Using Multiscale Autoconvolution
June 2005 (vol. 27 no. 6)
pp. 908-918
This paper presents a new affine invariant image transform called Multiscale Autoconvolution (MSA). The proposed transform is based on a probabilistic interpretation of the image function. The method is directly applicable to isolated objects and does not require extraction of boundaries or interest points, and the computational load is significantly reduced using the Fast Fourier Transform. The transform values can be used as descriptors for affine invariant pattern classification and, in this article, we illustrate their performance in various object classification tasks. As shown by a comparison with other affine invariant techniques, the new method appears to be suitable for problems where image distortions can be approximated with affine transformations.

[1] N. Götze, S. Drüe, and G. Hartmann, “Invariant Object Recognition with Discriminant Features Based on Local Fast-Fourier Mellin Transform,” Proc. Int'l Conf. Pattern Recognition, pp. 950-951, 2000.
[2] S.R. Deans, The Radon Transform and Some of Its Applications. Krieger, 1983.
[3] H. Xiong, T. Zhang, and Y.S. Moon, “A Translation- and Scale-Invariant Adaptive Wavelet Transform,” IEEE Trans. Image Processing, vol. 9, pp. 2100-2108, Dec. 2000.
[4] H. Burkhardt and S. Siggelkow, “Invariant Features for Discriminating between Equivalence Classes,” Nonlinear Model-Based Image/Video Processing and Analysis, I. Pitas and C. Kotropoulis, eds., pp. 269-307, 2001.
[5] R.C. Gonzales and R.E. Woods, Digital Image Processing. Reading, Mass.: Addison-Wesley, 1993.
[6] M.T. Quang and W.W. Boles, “Wavelet-Based Affine Invariant Representation: A Tool for Recognizing Planar Objects in 3D Space,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no 8, pp. 846-857, Aug. 1997.
[7] K. Arbter, W.E. Snyder, H. Burkhardt, and G. Hirzinger, “Application of Affine-Invariant Fourier Descriptors to Recognition of 3-D Objects,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, no. 7, pp. 640-647, July 1990.
[8] Y. Lamdan, J.T. Schwartz, and H.J. Wolfson, “Affine Invariant Model-Based Object Recognition,” IEEE Trans. Robotics and Automation, vol. 6, no. 5, pp. 578-589, 1990.
[9] D. Forsyth and J. Ponce, Computer Vision. Prentice Hall, 2003.
[10] V.H.S. Ha and J.M.F. Moura, “Affine Invariant Wavelet Transform,” Proc. Int'l Conf. Acoustics, Speech, and Signal Processing, pp. 1937-1940, 2001.
[11] M.I. Khalil and M.M. Bayoumi, “A Dyadic Wavelet Affine Invariant Function for 2D Shape Recognition,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 10, pp. 1152-1164, Oct. 2001.
[12] K. Mikolajczyk and C. Schmid, “An Affine Invariant Interest Point Detector,” Proc. European Conf. Computer Vision, pp. 128-142, 2002.
[13] M.-K. Hu, “Visual Pattern Recognition by Moment Invariants,” IEEE Trans. Information Theory, vol. 8, pp. 179-187, Feb. 1962.
[14] T.H. Reiss, “The Revised Fundamental Theorem of Moment Invariants,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, no. 8, pp. 830-834, Aug. 1991.
[15] J. Flusser and T. Suk, “Pattern Recognition by Affine Moment Invariants,” Pattern Recognition, vol. 26, no. 1, pp. 167-174, Jan. 1993.
[16] J. Ben-Arie and Z. Wang, “Pictorial Recognition of Objects Employing Affine Invariance in the Frequency Domain,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 6, pp. 604-618, June 1998.
[17] J. Ben-Arie and Z. Wang, “Gabor Kernels for Affine-Invariant Object Recognition,” Gabor Analysis and Algorithms, H. Feichtinger and T. Strohmer, eds., 1997.
[18] Z. Yang and F. Cohen, “Cross-Weighted Moments and Affine Invariants for Image Registration and Matching,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 21, no. 8, pp. 804-814, Aug. 1999.
[19] M. Petrou and A. Kadyrov, “Affine Invariant Features from the Trace Transform,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 1, pp. 30-44, Jan. 2004.
[20] J. Heikkilä, “Multiscale Autoconvolution for Affine Invariant Pattern Recognition,” Proc. Int'l Conf. Pattern Recognition, pp. 119-122, 2002.
[21] E. Rahtu and J. Heikkilä, “Object Classification with Multi-Scale Autoconvolution,” Proc. Int'l Conf. Pattern Recognition, 2004.
[22] E. Rahtu, M. Salo, and J. Heikkilä, “Convexity Recognition Using Multi-Scale Autoconvolution,” Proc. Int'l Conf. Pattern Recognition, 2004.
[23] I. Rigoutsos, “Well-Behaved, Tunable 3D-Affine Invariants,” Proc. Computer Vision and Pattern Recognition, pp. 455-460, 1998.
[24] O. Ronneberg, H. Burkhardt, and E. Schultz, “General-Purpose Object Recognition in 3D Volume Data Sets Using Gray-Scale Invariants— Classification of Airborne Pollen-Grains Recorded with Confocal Laser Scanning Microscope,” Proc. Int'l Conf. Pattern Recognition, pp. 290-295, 2002.
[25] S.S.M. Schael, “Invariant Grey-Scale Features for 3D Sensor-Data,” Proc. Int'l Conf. Pattern Recognition, pp. 531-535, 2002.
[26] M. Frigo and S.G. Johnson, “FFTW: An Adaptive Software Architecture for the FFT,” Proc. Int'l Conf. Acoustics Speech and Signal Processing, vol. 3, pp. 1381-1384, 1998.
[27] Columbia University, “Coil-100 Image Database,” http:/www.cs.columbia.edu, 2003.

Index Terms:
Affine invariance, affine invariant features, pattern classification, target identification, object recognition, image transforms.
Citation:
Esa Rahtu, Mikko Salo, Janne Heikkilä, "Affine Invariant Pattern Recognition Using Multiscale Autoconvolution," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, no. 6, pp. 908-918, June 2005, doi:10.1109/TPAMI.2005.111
Usage of this product signifies your acceptance of the Terms of Use.