Paper Info
Title
Classification of rotated and scaled textures using HMHV spectrum estimation and the Fourier-Mellin transform
Abstract
In the framework of image modeling for texture analysis, we propose the combination of the new parametric 2-D spectrum estimation method called HMHV (harmonic mean horizontal vertical) and the Fourier-Mellin transform. This latter technique allows the calculation of a set of texture descriptors from a 2-D spectrum estimate which is invariant under rotation and scaling. A comparison of the HMHV and the “standard” parametric HM (harmonic mean) methods on synthetic and natural stochastic textures shows that the HMHV method presents almost no spurious peaks and is quite isotropic. By performing the classification of a set of 60 images divided in 12 texture classes, descriptors computed with the HMHV method provide better results than those computed with the HM method
Year
DOI
Venue
1998
10.1109/ICIP.1998.723414
Image Processing, 1998. ICIP 98. Proceedings. 1998 International Conference
Keywords
Field
DocType
Fourier transforms,image classification,image texture,multidimensional signal processing,parameter estimation,spectral analysis,Fourier-Mellin transform,HMHV spectrum estimation,classification,harmonic mean horizontal vertical,image modeling,natural stochastic textures,parametric 2-D spectrum estimation method,rotated texture,scaled textures,synthetic stochastic textures,texture analysis
Computer vision,Multidimensional signal processing,Pattern recognition,Image texture,Harmonic mean,Fourier transform,Parametric statistics,Artificial intelligence,Invariant (mathematics),Estimation theory,Contextual image classification,Mathematics
Conference
Volume
ISBN
Citations 
1
0-8186-8821-1
9
PageRank 
References 
Authors
3.49
7
4
Name
Order
Citations
PageRank
Olivier Alata111819.81
Claude Cariou293.49
Clarisse Ramananjarasoa393.49
Mohamed Najim414932.29