Texture classification using ridgelet transform

Arivazhagan, S.; Ganesan, L.; Kumar, T. Ganesh

doi:10.1016/j.patrec.2006.04.013

Cited by 66 publications

(43 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On image regions extracted from four VisTex and Brodatz image datasets, classification results perform very well and demonstrate to be superior to those reached on the same image datasets by three recent texture classification methods found in literature (Arivazhagan et al, 2006;Muneeswaran et al, 2005;Li et al, 2003 …”

Section: Resultsmentioning

confidence: 76%

“…Ranklets+SVM represents the proposed ranklet-based approach. Ridgelets+Dist (Arivazhagan et al, 2006), Wavelets+Dist (Muneeswaran et al, 2005), and Wavelets+SVM (Li et al, 2003) Li et al (2003) used wavelet transform and SVM (i.e., Wavelets+SVM) on a number of image regions extracted from the same 30 Brodatz images used in Test-4.As evident from the seventh and eighth rows of Tab. 1, they reached 96.34% of accuracy versus the 100.00% achieved by Ranklets+SVM.…”

Section: Resultsmentioning

confidence: 99%

“…First, to propose a system as general-purpose as possible, rather than overly suited for a specific texture classification problem. Second, to be able to compare the proposed system directly with three recent automatic texture classification systems found in literature and having being evaluated on the same images, namely, (1) a texture classification approach based on ridgelets and minimum distance classification (Arivazhagan et al, 2006), (2) a rotation-invariant approach based on wavelets and minimum distance classification (Muneeswaran et al, 2005), and (3) an approach based on wavelets and SVM (Li et al, 2003).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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: Resultsmentioning

confidence: 76%

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Texture classification using invariant ranklet features

Masotti

Campanini

2008

Pattern Recognition Letters

View full text Add to dashboard Cite

show abstract

“…These include approaches based on Ranklets and SVM [15], Wavelets and SVM [13], the Ridgelet transform and the L 1 distance [3] and invariant wavelet features in combination with NN [19]. Comparison with some of these works can only be indicative, as the size of the sub-images used for classification varies from 32 × 32 to 256 × 256 (128 × 128 is used here); however our results are quite comparable with the state-of-the-art and actually outperform some of the other algorithms on some of the datasets.…”

Section: Resultsmentioning

confidence: 99%

“…We show that using Variance Ranklets together with Intensity Ranklets leads to significantly lower error rates than those obtained with standard Ranklets alone. We compare our recognition rates with recently published results obtained using four different algorithms [3,13,15,19].…”

Section: Introductionmentioning

confidence: 94%

Variance Ranklets: orientation–selective rank features for contrast modulations

Azzopardi¹,

Smeraldi²

2009

Procedings of the British Machine Vision Conference 2009

View full text Add to dashboard Cite

We introduce a novel type of orientation-selective rank features that are sensitive to contrast modulations (second-order stimuli). Variance Ranklets are designed in close analogy with the standard Ranklets, but use the Siegel-Tukey statistics for dispersion instead of the Wilcoxon statistics. Their response shows the same orientation selectivity pattern of Haar wavelets on second-order signals that are not detectable by linear filters. To the best of our knowledge, this is the first family of rank filters designed to detect orientation in variance modulations.We validate our descriptors with an application to texture classification over a subset of the VisTex and Brodatz databases. The combination of standard (intensity) Ranklets with Variance Ranklets greatly improves on the performance of Ranklets alone. Comparison with other published results shows that state-of-the-art recognition rates can be achieved with a simple Nearest Neighbour classifier.

show abstract