A Multiresolution Independent Component Analysis for textile images

Colţuc, Daniela; Fournel, Thierry; Becker, Jean-Marie; Jourlin, Michel

doi:10.1088/1742-6596/77/1/012003

Cited by 5 publications

(7 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We can extend these matrices by such way as is extended phase rotating matrix (21) in the Fourier operator (20). For this let change the first term of the sum in (22) by elements which are analogues to the matrix…”

Section: B Creation Of a Function Basis For High Order Ehdmentioning

confidence: 99%

“…This approach was widely developed in many papers [21][22][23][24][25][26][27][28]. The EVD is computationally complicated; therefore Independent Component Analysis (ICA) [21,22], Empirical Mode Decomposition (EMD) [23][24][25] and Singular Values Decomposition (SVD) [26][27][28] are substituted for it. These decompositions reduce the size and dimension of texture parameters according to Principal Component Analysis (PCA).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Approximation of bidirectional reflectance distribution function for highly efficient shading

Romanyuk¹,

Павлов²,

Romanyuk³

et al. 2017

Information Technology in Medical Diagnostics

View full text Add to dashboard Cite

Abstract. Recognition of textured objects is a typical problem in computer vision and pattern recognition. Usually are meeting two variations of this problem. The first is the recognition of a signed texture. The second is objects of interest recognition in image with textured background. We offer an approach for solving of the both problems with using of the inverse resonant filtration. A textured object or background dynamic space can be approximated by a set of principal eigenvectors in the form of resonantharmonic functions called as eigen harmonics (EH). The Inverse ResonantFilter (IRF) which is resonant in respect to EH series eliminates textured background and forms indicator signal of certain species. The IRF is founded on the approximation and extrapolation of the texture template signal by series of EH. Two methods of 2-dimensional (2D) EH parameter estimation are considered. The methods give estimates robust tobreaks and noise peakspresentedin textured image signal. The first method is based on the linear symmetry model and can be presented as a double linear prediction model. Additionally the condition of the unitary symmetry is used to provide stationarity and periodicity of the model. The second method is based on 2D correlation matrix splitting with projection into the subspace of principal harmonic components. Implementation of the IRF is considered in spatial and spectral domains. Discrete Fourier transform with eigen kernel (DFTEK) was used for design and realization of the high order IRF. The DFTEK has fractionally fast transform algorithm. Aligning image fragment phases improved inverse resonant filtration in the spectral domain. It was shown that the optimal approach to image filtration consists of an initial fast filtration in the spectral domain, followed by postfiltration of the image zones containing anomalous background variations using IRF in the spatial domain. It was shown that the IRF is invariant to shift transform. It can be invariant to affine and scale transform if instead initial texture and image are using their invariant pattern in the form of image surface geometry characteristics.

show abstract

Section: B Creation Of a Function Basis For High Order Ehdmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Approximation of bidirectional reflectance distribution function for highly efficient shading

Romanyuk¹,

Павлов²,

Romanyuk³

et al. 2017

Information Technology in Medical Diagnostics

View full text Add to dashboard Cite

show abstract

“…An enhanced wavelet analysis may be obtained by applying an ICA on the wavelet subbands [3]. Since the Wavelet Transform (WT) has a decorrelating effect, the whitening stage in the beginning of many ICA algorithms is no more necessary, the simple normalization of the wavelet subband by its standard deviation giving a near whitening effect.…”

Section: A Wavelet Analysis Enhanced By Icamentioning

confidence: 99%

“…Depending on the initial conditions -in the case of FastICA, the initialization of A -the ICs may be different. For two ICs, the experiments have shown two possible solutions (2) [3]. They were obtained by loading one of the columns of A by the wavelet filter, another constraint for obtaining ICs close to wavelet subbands.…”

Section: A Wavelet Analysis Enhanced By Icamentioning

confidence: 99%

See 1 more Smart Citation

A texture descriptor for textile image retrieval

Carbunaru

Colţuc

Jourlin

et al. 2009

2009 International Symposium on Signals, Circuits and Systems

View full text Add to dashboard Cite

This paper proposes a new descriptor for textures, obtained by an Independent Components Analysis (ICA) applied to image wavelet subbands. In certain conditions, ICA refines the wavelet multiband analysis. The descriptor, consisting in the independent components (ICs) distribution parameters, serves as basis for the textile image signature in a recognition application. By using the Kullback-Liebler divergence to compare the signatures, the textile images from a 30 jacquards databasis, were recognized with average rates ranging from 89 to 94%, depending on the analysis number of levels.

show abstract