Continuous rotation invariant features for gradient-based texture classification

Hanbay, Kazım; Alpaslan, Nuh; Talu, Muhammed Fatih; Hanbay, Davut; Karcı, Ali; Kocamaz, Adnan Fatih

doi:10.1016/j.cviu.2014.10.004

Cited by 27 publications

(14 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Recently, Xu et al [33] presented a new descriptor based on multi-fractal analysis in wavelet pyramids of texture images (WMFS). In [34], Hanbay et al proposed four state-of-the-art rotation invariant gradient features based on HOG and CoHOG, i.e., GDF-HOG, Eig(Hess)-HOG, Eig(Hess)-CoHOG, and GM-CoHOG.…”

Section: Compared With Recent Non-lbp Methodsmentioning

confidence: 99%

“…The performance of the proposed LQC at (R=3, P=24) is compared with that of these non-LBP methods. The experimental results of MFS and WMFS on UIUC database are from [33], and the results of four gradient-based methods on UIUC database are from [34]. The experimental results on three texture databases are listed in Table 6.…”

Section: Compared With Recent Non-lbp Methodsmentioning

confidence: 99%

“…Eichmann et al [4] presented texture descriptors based on line structures extracted by Hough transform. In [34], Hanbay et al presented four effective rotation invariant features based on histograms of oriented gradients (HOG) and co-occurrence HOG (CoHOG). In model-based methods, texture is usually presented as a probability model or as a linear combination of a set of basis functions.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Local Quantization Code histogram for texture classification

Zhao

Wang

et al. 2016

Neurocomputing

View full text Add to dashboard Cite

Abstract-In this paper, an efficient local operator, namely the Local Quantization Code (LQC), is proposed for texture classification. The conventional local binary pattern can be regarded as a special local quantization method with two levels, 0 and 1. Some variants of the LBP demonstrate that increasing the local quantization level can enhance the local discriminative capability. Hence, we present a simple and unified framework to validate the performance of different local quantization levels. In the proposed LQC, pixels located in different quantization levels are separately counted and the average local gray value difference is adopted to set a series of quantization thresholds. Extensive experiments are carried out on several challenging texture databases. The experimental results demonstrate the LQC with appropriate local quantization level can effectively characterize the local gray-level distribution.

show abstract

Section: Compared With Recent Non-lbp Methodsmentioning

confidence: 99%

Section: Compared With Recent Non-lbp Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Local Quantization Code histogram for texture classification

Zhao

Wang

et al. 2016

Neurocomputing

View full text Add to dashboard Cite

show abstract

“…To extract invariant features from masses, Non-Subsampled Contourlet transform (NSCT) [24] is utilized due to its powerful capability in image representation compared to wavelets and contourlet transform. Furthermore, in order to distinguish normal and abnormal tissues, eig(Hess) HOG [25] features are extracted based on computation of eigenvalues of the Hessian matrix in a histogram of oriented gradients in addition to several geometric features from the masses in mammographic images. HOG is known as a keypoint descriptor in literature which expresses the local statistics of the gradient orientations around a keypoint [46].…”

Section: Introductionmentioning

confidence: 99%

A Decision Support System (DSS) for Breast Cancer Detection Based on Invariant Feature Extraction, Classification, and Retrieval of Masses of Mammographic Images

Rahman¹,

Alpaslan²

2019

Medical Imaging and Image-Guided Interventions

Self Cite

View full text Add to dashboard Cite

This paper presents an integrated system for the breast cancer detection from mammograms based on automated mass detection, classification, and retrieval with a goal to support decision-making by retrieving and displaying the relevant past cases as well as predicting the images as benign or malignant. It is hypothesized that the proposed diagnostic aid would refresh the radiologist's mental memory to guide them to a precise diagnosis with concrete visualizations instead of only suggesting a second diagnosis like many other CAD systems. Towards achieving this goal, a Graph-Based Visual Saliency (GBVS) method is used for automatic mass detection, invariant features are extracted based on using Non-Subsampled Contourlet transform (NSCT) and eigenvalues of the Hessian matrix in a histogram of oriented gradients (HOG), and finally classification and retrieval are performed based on using Support Vector Machines (SVM) and Extreme Learning Machines (ELM), and a linear combination-based similarity fusion approach. The image retrieval and classification performances are evaluated and compared in the benchmark Digital Database for Screening Mammography (DDSM) of 2604 cases by using both the precision-recall and classification accuracies. Experimental results demonstrate the effectiveness of the proposed system and show the viability of a real-time clinical application.

show abstract

“…The Eigen analysis of the Hessian matrix is important for texture analysis. In [24], gradient magnitude and orientations were calculated using the Eigenvalues…”

Section: Cohog and Eig(hess)-cohog Featuresmentioning

confidence: 99%