A comparison of texture feature extraction using adaptive gabor filtering, pyramidal and tree structured wavelet transforms

Pichler, O; Teuner, A.; Hosticka, B.J.

doi:10.1016/0031-3203(95)00127-1

Cited by 128 publications

(57 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Systems having robustness to linear monotonic variations of the gray-scale were proposed by Partio et al (2004) and Sukanya (2000). Rotation invariance texture classification was addressed in many several ways: Chetverikov (1982) used texture anisotropy, Davis et al (1979) used generalized co-occurrence matrices, Pichler et al (1996) and Idrissa and Acheroy (2002) used banks of Gabor filters, whereas Charalampidis and Kasparis (2002) and Manthalkar et al (2003b) used wavelet-based filters. Systems which incorporate invariance to both linear monotonic variations of the grayscale and rotation are much more rare in literature.…”

Section: Introductionmentioning

confidence: 99%

Texture classification using invariant ranklet features

Masotti

Campanini

2008

Pattern Recognition Letters

View full text Add to dashboard Cite

A novel invariant texture classification method is proposed. Invariance to linear/nonlinear monotonic gray-scale transformations is achieved by submitting the image under study to the ranklet transform, an image processing technique relying on the analysis of the relative rank of pixels rather than on their gray-scale value. Some texture features are then extracted from the ranklet images resulting from the application at different resolutions and orientations of the ranklet transform to the image. Invariance to 90 • -rotations is achieved by averaging, for each resolution, correspondent vertical, horizontal, and diagonal texture features. Finally, a texture class membership is assigned to the texture feature vector by using a support vector machine (SVM) classifier. Compared to three recent methods found in literature and having being evaluated on the same Brodatz and Vistex datasets, the proposed method performs better. Also, invariance to linear/non-linear monotonic gray-scale transformations and 90 • -rotations are evidenced by training the SVM classifier on texture feature vectors formed from the original images, then testing it on texture feature vectors formed from contrast-enhanced, gamma-corrected, histogram-equalized and 90 • -rotated images.

show abstract

Section: Introductionmentioning

confidence: 99%

Texture classification using invariant ranklet features

Masotti

Campanini

2008

Pattern Recognition Letters

View full text Add to dashboard Cite

show abstract

“…In this method a segmentation algorithm is applied to a feature vector ®eld computed with the operator, and the segmentation performance and suitability of the used features are evaluated by using the number of misclassi®ed pixels (Weszka et al 1976;Conners and Harlow 1980;Pichler et al 1996). In this way, the practical value of the operator can be evaluated and compared with other texture operators.…”

Section: Classi®cation Results Comparison With Other Texture Operatorsmentioning

confidence: 99%

Computational model of dot-pattern selective cells

Kruizinga

Petkov

2000

Biological Cybernetics

View full text Add to dashboard Cite

“…Automated sea ice classification schemes-which implicitly include SIC or an open-water class-based on single-band SAR texture have been proposed [18][19][20][21][22][23][24]. These methods use multiple techniques such as the gray-level co-occurrence texture features [25], Markov random fields [26], and Gabor filters [18,27] to classify the SAR imagery. It has been shown that open-water detection and SIC estimates that are based solely on SAR co-polarized (HH) channel backscattering magnitude can be improved by including cross-polarized (HV) channel information.…”

Section: Sea Ice Concentrationmentioning

confidence: 99%

Bohai Sea Ice Parameter Estimation Based on Thermodynamic Ice Model and Earth Observation Data

et al. 2017

View full text Add to dashboard Cite

Abstract:We estimate two essential sea ice parameters-namely, sea ice concentration (SIC) and sea ice thickness (SIT)-for the Bohai Sea using a combination of a thermodynamic sea ice model and Earth observation (EO) data from synthetic aperture radar (SAR) and microwave radiometer. We compare the SIC and SIT estimation results with in-situ measurements conducted in the study area and estimates based on independent EO data from near-infrared/optical instruments. These comparisons suggest that the SAR-based discrimination between sea ice and open-water works well, and areas of thinner and thicker ice can be distinguished. A larger comprehensive training dataset is needed to set up an operational algorithm for the estimation of SIC and SIT.

show abstract

A comparison of texture feature extraction using adaptive gabor filtering, pyramidal and tree structured wavelet transforms

Cited by 128 publications

References 12 publications

Texture classification using invariant ranklet features

Texture classification using invariant ranklet features

Computational model of dot-pattern selective cells

Bohai Sea Ice Parameter Estimation Based on Thermodynamic Ice Model and Earth Observation Data

Contact Info

Product

Resources

About