Y. Sheng and H.H. Arsenault. Experiments on pattern recognition using invariant Fourier-Mellin descriptors. J. of the Optical Society of America A, 3(6):771--776, June 1986.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....of the estimated parameters. 1 INTRODUCTION The Fourier Mellin transform has been extensively studied for pattern description and recognition in the last decades. A number of works to date were motivated by the search for some sets of features invariant under rotation and scale transformations [11]. Due to the crucial numerical problem faced in estimating the standard FMT, the analytical Fourier Mellin transform (AFMT) was proposed in [5] and three e#cient approximations were then presented [3] In this work, the AFMT is used to derive two algorithms for, first, the estimation of the ....

Y. Sheng and H. Arsenault. Experiments on pattern recognition using invariant Fourier-Mellin descriptors. J. of the OSA A, 3(6):771--776, 1986.

.... (see works on Legendre, Zernike, and related moments [12, 13, 14] and disk harmonic coe#cients [15] Late on the 70 s, the optical research community introduced the Fourier Mellin Transform (FMT) for pattern recognition [16, 17] and it was later used in digital signal and image processing [18, 19, 20]. Several sets of rotation and scale invariant features based on the FMT modulus have been designed, but completeness was not reached since the descriptors do not hold phase information. Furthermore, it was also pointed out that numerical estimation of the Mellin integral brings up crucial ....

....of the shape of the object. For pattern recognition purposes, the classification of an unknown object as one of a set of reference patterns is achieved with a comparison method such as: the computation of an error between the features [32] neural networks [33, 34] or statistical classifiers [19, 35, 20]. These methods are turned out to be e#cient when the models to compare have simple and distinct shapes (typographic symbols or 1 FIG. 9. Idem to Fig. 7 with the C Afmt algorithm. letters) Nevertheless, image databases become more and more voluminous and heterogeneous. Due to the lack of ....

Y. Sheng and H.H. Arsenault. Experiments on pattern recognition using invariant FourierMellin descriptors. J. of the Optical Society of America A, 3(6):771--776, June 1986.

....they have long been of interest to the pattern recognition community. A comprehensive discussion of the pattern recognition literature is outside the scope of this paper. Hu [12] described the use of moment invariants for visual pattern recognition of planar geometric figures. It has been shown [13] that these classic moment invariants are equivalent to the radial moments of circular harmonic functions (CHF s) that arise from a Mellin transform of the log polar representation of an image when the complex Mellin radial frequency , is a real integer . The Fourier Mellin transform is closely ....

Y. Sheng and H. H. Arsenault, "Experiments on pattern recognition using invariant Fourier--Mellin descriptors," J. Opt. Soc. Amer. A, vol. 3, no. 6, pp. 771--776, 1986.

....interest to the pattern recognition community. A comprehensive discussion of the pattern recognition literature is outside the scope of this chapter. Hu [49] described the use of momentinvariants for visual pattern recognition of planar geometric figures. It has been shown [120] that these classic momentinvariants are equivalentto the radial moments of circular harmonic functions (CHF s) that arise from a Mellin transform of the log polar representation of an image when the complex Mellin radial frequency s,isarealinteger s 1. The Fourier Mellin transform is closely ....

Y. Sheng and H. H. Arsenault, "Experiments on Pattern Recognition using InvariantFourier-Mellin Descriptors," J. Opt. Soc. Am. A, pp. 771-776, 1986.

....and pentagon. Several example shape images are shown in Figure C.1. Each shape image consists of a matrix of size 64 x 64, and each element in the matrix represents a binary valued pixel in the image. The feature types are Circular Harmonic Expansion (CHEF) 60] Fourier Mellin Descriptor (FMDF) [61], Ring Wedge Energy (RWEF) 62] Log Polar Transform (LPTF) 63] and Radius Feature (RDF) 64] In Table C.1, we summarize the different shape feature sets. Table C.1 Shape Features. Shape Features # of Inputs # of Classes # of Patterns per Class CHEF 16 4 200 FMDF 16 4 200 RWEF 16 4 200 LPTF ....

Y. Sheng and H.H. Arsenault, "Experiment on pattern recognition using invariant Fourier-Mellin descriptor," Optics society of America, Vol. 3, pp. 771-776, 1986. 118

....the object shape and the phase spectrum contains information about the object translation; therefore, the shape information in the magnitude spectrum is naturally translation invariant. The Fourier Mellin transform is a powerful tool for image recognition techniques that use this spectral property [12, 9]. This method represents rotation and scaling as single translations on the parameter space, and allows the use of the Phase Correlation Technique [10] to determine translation, scaling and rotation. Thus, there are four free parameters. To represent scaling and rotation as translations, the ....

Y.Sheng and H.H. Arsenault. Experiments on pattern recognition using invariant Fourier-Mellin descriptors. J. of Opt. Soc. Am. A., 3(6):771--776, 1986.

No context found.

Y. Sheng and H.H. Arsenault. Experiments on pattern recognition using invariant Fourier-Mellin descriptors. J. of the Optical Society of America A, 3(6):771--776, June 1986.

No context found.

Sheng and Arsenault (1986). Experiments on pattern recognition using invariant Fourier-Mellin descriptors. J. Opt. Soc. Am. A, 3(6):771--776.

No context found.

Y. Sheng and H. H. Arsenault, "Experiments on pattern recognition using invariant fourier-mellin descriptors," J. Opt. Soc. Am. A, vol. 3, pp. 771--776, 1986.

No context found.

Y. Sheng and H. H. Arsenault, "Experiments on pattern recognition using invariant Fourier-Mellin descriptors," J. Opt. Soc. Am. A , pp. 771--776, 1986.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC