Pattern recognition using invariants defined from higher order spectra: 2-D image inputs

QSpace/Manakin Repository

Pattern recognition using invariants defined from higher order spectra: 2-D image inputs

Show simple item record Chandran, V Carswell, B Boashash, B Elgar, S 2011-07-26T04:41:49Z 2011-07-26T04:41:49Z 1997-05
dc.identifier.citation IEEE Transactions on Image Processing, Volume : 6 , Issue:5, page(s): 703 en_US
dc.identifier.issn 1057-7149
dc.description This paper applies higher order spectra to image pattern recognition with an algorithm that is invariant to translation, rotation and scaling. (The most recent upgrade of the original software package that calculates Time-Frequency Distributions and Instantaneous Frequency estimators can be downloaded from the web site: This was the first software developed in the field, and it was first released publicly in 1987 at the 1st ISSPA conference held in Brisbane, Australia., and then continuously updated). en_US
dc.description.abstract A new algorithm for extracting features from images for object recognition is described. The algorithm uses higher order spectra to provide desirable invariance properties, to provide noise immunity, and to incorporate nonlinearity into the feature extraction procedure thereby allowing the use of simple classifiers. An image can be reduced to a set of 1D functions via the Radon transform, or alternatively, the Fourier transform of each 1D projection can be obtained from a radial slice of the 2D Fourier transform of the image according to the Fourier slice theorem. A triple product of Fourier coefficients, referred to as the deterministic bispectrum, is computed for each 1D function and is integrated along radial lines in bifrequency space. Phases of the integrated bispectra are shown to be translation- and scale-invariant. Rotation invariance is achieved by a regrouping of these invariants at a constant radius followed by a second stage of invariant extraction. Rotation invariance is thus converted to translation invariance in the second step. Results using synthetic and actual images show that isolated, compact clusters are formed in feature space. These clusters are linearly separable, indicating that the nonlinearity required in the mapping from the input space to the classification space is incorporated well into the feature extraction stage. The use of higher order spectra results in good noise immunity, as verified with synthetic and real images. Classification of images using the higher order spectra-based algorithm compares favorably to classification using the method of moment invariants. en_US
dc.description.sponsorship IEEE Signal Processing Society en_US
dc.language.iso en en_US
dc.publisher IEEE en_US
dc.subject 1D projection en_US
dc.subject 2-D image inputs en_US
dc.subject 2D Fourier transform en_US
dc.subject Fourier slice theorem en_US
dc.subject Fourier transform en_US
dc.subject Radon transform en_US
dc.subject algorithm en_US
dc.subject bi-frequency space en_US
dc.subject classification en_US
dc.subject deterministic bispectrum en_US
dc.subject feature extraction procedure en_US
dc.subject higher order spectra en_US
dc.subject invariance properties en_US
dc.subject invariants en_US
dc.subject noise immunity en_US
dc.subject nonlinearity en_US
dc.subject object recognition en_US
dc.subject pattern recognition en_US
dc.subject rotation invariance en_US
dc.subject translation invariance en_US
dc.subject triple product en_US
dc.subject image non-linear mapping en_US
dc.title Pattern recognition using invariants defined from higher order spectra: 2-D image inputs en_US
dc.type Article en_US

Files in this item

Files Size Format View
Boashash-Chandr ... attern-recognition-HOS.pdf 208.5Kb PDF View/Open

This item appears in the following Collection(s)

Show simple item record

Search QSpace

Advanced Search


My Account