Accurate Computation of Orthogonal Fourier-Mellin Moments

Orthogonal Fourier-Mellin moments (OFMMs) suffer from geometric error and the numerical integration error. The geometric error arises when the square image is mapped into a unit disk and the mapping does not become perfect. The numerical integration error arises when the double integration is approximated by the zeroth order summation. In this paper, we propose methods which reduce these errors. The geometric error is reduced by considering the arc-grids lying on the boundary of the unit disk and the square grids lying completely inside the disk. The numerical integration error is reduced by Gaussian numerical integration, for which a simple computational framework is provided. The relative contributions of geometric error and numerical integration error to the total error are also analyzed. It is observed that the geometric error is significant only for the small images whereas the magnitude of numerical integration is significantly high for all image sizes, which increases with the order of moments. A simple computational framework which is similar to the conventional zeroth order approximation is also proposed which not only reduces numerical integration error but also reduces geometric error without considering arc-grids. The improved accuracy of OFMMs are shown to provide better image reconstruction, numerical stability and rotation and scale invariance. Exhaustive experimental results on a variety of real images have shown the efficacy of the proposed methods.

[1]  Chandan Singh,et al.  Fast and numerically stable methods for the computation of Zernike moments , 2010, Pattern Recognit..

[2]  Khalid M. Hosny Fast and accurate method for radial moment's computation , 2010, Pattern Recognit. Lett..

[3]  Mandyam D. Srinath,et al.  Orthogonal Moment Features for Use With Parametric and Non-Parametric Classifiers , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Miroslaw Pawlak,et al.  On the Accuracy of Zernike Moments for Image Analysis , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Glen P. Abousleman,et al.  Orthogonal Rotation-Invariant Moments for Digital Image Processing , 2008, IEEE Transactions on Image Processing.

[6]  Miroslaw Pawlak,et al.  Accurate Computation of Zernike Moments in Polar Coordinates , 2007, IEEE Transactions on Image Processing.

[7]  Chandan Singh,et al.  On the fast computation of orthogonal Fourier–Mellin moments with improved numerical stability , 2010, Journal of Real-Time Image Processing.

[8]  Huazhong Shu,et al.  Construction of a complete set of orthogonal Fourier-Mellin moment invariants for pattern recognition applications , 2010, Image Vis. Comput..

[9]  Khalid M. Hosny,et al.  Fast computation of orthogonal Fourier–Mellin moments in polar coordinates , 2009, Journal of Real-Time Image Processing.

[10]  Chandan Singh,et al.  Algorithms for fast computation of Zernike moments and their numerical stability , 2011, Image Vis. Comput..

[11]  Yee Ming Chen,et al.  Face recognition using combined multiple feature extraction based on Fourier-Mellin approach for single example image per person , 2010, Pattern Recognit. Lett..

[12]  T. B. J. Andrew,et al.  Integrated Wavelet and Fourier-Mellin invariant feature in fingerprint verification system , 2003, WBMA '03.

[13]  Y. Sheng,et al.  Orthogonal Fourier–Mellin moments for invariant pattern recognition , 1994 .

[14]  Chee-Way Chong,et al.  The scale invariants of pseudo-Zernike moments , 2003, Pattern Analysis & Applications.

[15]  Mandyam D. Srinath,et al.  Invariant character recognition with Zernike and orthogonal Fourier-Mellin moments , 2002, Pattern Recognit..

[16]  Raveendran Paramesran,et al.  On the computational aspects of Zernike moments , 2007, Image Vis. Comput..

[17]  Dandan Liu,et al.  Subpixel edge location based on orthogonal Fourier-Mellin moments , 2008, Image Vis. Comput..

[18]  Basil G. Mertzios,et al.  Performance of the Orthogonal Moments in Reconstructing Biomedical Images , 2009, 2009 16th International Conference on Systems, Signals and Image Processing.

[19]  Karim Faez,et al.  Study on the performance of moments as invariant descriptors for practical face recognition systems , 2010 .

[20]  Bin Xiao,et al.  Scaling and rotation invariant analysis approach to object recognition based on Radon and Fourier-Mellin transforms , 2007, Pattern Recognit..