An application of wavelet-based affine-invariant representation

Recently, a novel technique used to construct an affine-invariant representation based on the dyadic wavelet transform was proposed and tested on synthesised 2D contours (Tieng and Boles, 1994). In this paper, the performance of this representation with real objects under perspective transformation is considered. In comparison with a similarity invariant (curvature) representation, experimental results show that the proposed affine-invariant representation is the most appropriate one to represent and recognise objects under perspective transform.

[1]  Yoshiaki Shirai,et al.  Object Recognition Using Three-Dimensional Information , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  David P. Dobkin,et al.  Contour tracing by piecewise linear approximations , 1990, TOGS.

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

[4]  R. Hibbeler.  Engineering Mechanics: Dynamics , 1986 .

[5]  Pong C. Yuen,et al.  Recognition of occluded objects , 1992, Pattern Recognit..

[6]  David Cyganski,et al.  Object Identification And Orientation Estimation From Contours Based On An Affine Invariant Curvature , 1988, Other Conferences.

[7]  Svetha Venkatesh,et al.  Extracting natural scales using fourier descriptors , 1993, Pattern Recognit..

[8]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Qi Jin,et al.  A new method of extracting invariants under affine transform , 1992, [1992] Proceedings. 11th IAPR International Conference on Pattern Recognition.

[10]  Wageeh W. Boles,et al.  Complex Daubechies wavelet based affine invariant representation for object recognition , 1994, Proceedings of 1st International Conference on Image Processing.

[11]  Mandyam D. Srinath,et al.  Partial Shape Classification Using Contour Matching in Distance Transformation , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Jin H. Kim,et al.  Recognition of 3-D objects by forward checking constrained search , 1992, Robotics Auton. Syst..

[13]  Mark J. Shensa,et al.  The discrete wavelet transform: wedding the a trous and Mallat algorithms , 1992, IEEE Trans. Signal Process..

[14]  Farzin Mokhtarian,et al.  A Theory of Multiscale, Curvature-Based Shape Representation for Planar Curves , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  David G. Lowe,et al.  Three-Dimensional Object Recognition from Single Two-Dimensional Images , 1987, Artif. Intell..

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

[17]  Wageeh Boles,et al.  Object recognition using an affine invariant wavelet representation , 1994, Proceedings of ANZIIS '94 - Australian New Zealnd Intelligent Information Systems Conference.

[18]  Andrew P. Witkin,et al.  Scale-Space Filtering , 1983, IJCAI.

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

[20]  Paul L. Rosin.  Representing curves at their natural scales , 1992, Pattern Recognit..