Affine invariant pattern recognition using multiscale autoconvolution

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]  Zhengwei Yang,et al.  Cross-Weighted Moments and Affine Invariants for Image Registration and Matching , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  José M. F. Moura,et al.  Affine invariant wavelet transform , 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

[3]  Wesley E. Snyder,et al.  Application of Affine-Invariant Fourier Descriptors to Recognition of 3-D Objects , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Esa Rahtu,et al.  Convexity recognition using multi-scale autoconvolution , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[5]  Hans Burkhardt,et al.  General-purpose object recognition in 3D volume data sets using gray-scale invariants - classification of airborne pollen-grains recorded with a confocal laser scanning microscope , 2002, Object recognition supported by user interaction for service robots.

[6]  Janne Heikkilä.  Multi-Scale Autoconvolution for Affine Invariant Pattern Recognition , 2002, ICPR.

[7]  Cordelia Schmid,et al.  An Affine Invariant Interest Point Detector , 2002, ECCV.

[8]  Mahmoud I. Khalil,et al.  A Dyadic Wavelet Affine Invariant Function for 2D Shape Recognition , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Esa Rahtu,et al.  Object classification with multi-scale autoconvolution , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[10]  Jezekiel Ben-Arie,et al.  Pictorial Recognition of Objects Employing Affine Invariance in the Frequency Domain , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Wageeh Boles,et al.  Wavelet-based affine invariant representation: a tool for recognizing planar objects in 3D space , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Azriel Rosenfeld,et al.  Computer Vision , 1988, Adv. Comput..

[13]  Jezekiel Ben-Arie,et al.  Gabor kernels for affine—invariant object recognition , 1998 .

[14]  Jan Flusser,et al.  Pattern recognition by affine moment invariants , 1993, Pattern Recognit..

[15]  Tianxu Zhang,et al.  A translation- and scale-invariant adaptive wavelet transform , 2000, IEEE Trans. Image Process..

[16]  Marc Schael,et al.  Invariant grey-scale features for 3D sensor-data , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[17]  Thomas H. Reiss,et al.  The revised Fundamental Theorem of Moment Invariants , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Steven G. Johnson,et al.  FFTW: an adaptive software architecture for the FFT , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[19]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[20]  Paul Wintz,et al.  Digital image processing (2nd ed.) , 1987 .

[21]  Isidore Rigoutsos,et al.  Well-behaved, tunable 3D-affine invariants , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[22]  Alexander Kadyrov,et al.  Affine invariant features from the trace transform , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Georg Hartmann,et al.  Invariant object recognition with discriminant features based on local fast-Fourier Mellin transform , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[24]  Yehezkel Lamdan,et al.  Affine invariant model-based object recognition , 1990, IEEE Trans. Robotics Autom..