Curvelet-Based Synthetic Aperture Radar Image Classification

Uslu, Erkan; Albayrak, Songul

doi:10.1109/lgrs.2013.2286089

Cited by 25 publications

(11 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Curvelet-based, histogram of curvelets (HoC) feature extraction method is introduced in our previous work together with the first implementation of curvelet subband GGD parameter estimation features for SAR image classification [14]. In our previous work, using only one element of the coherency matrix, histograms for each normalized curvelet subbands are cascaded to form a feature vector per pixel.…”

Section: Curvelet Transform Subband Statistical Momentsmentioning

confidence: 99%

Synthetic Aperture Radar Image Clustering with Curvelet Subband Gauss Distribution Parameters

Uslu

Albayrak

2014

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Curvelet transform is a multidirectional multiscale transform that enables sparse representations for signals. Curvelet-based feature extraction for Synthetic Aperture Radar (SAR) naturally enables utilizing spatial locality; the use of curvelet-based feature extraction is a novel method for SAR clustering. The implemented method is based on curvelet subband Gaussian distribution parameter estimation and cascading these estimated values. The implemented method is compared against original data, polarimetric decomposition features and speckle noise reduced data with use of k-means, fuzzy c-means, spatial fuzzy c-means and self-organizing maps clustering methods. Experimental results show that the curvelet subband Gaussian distribution parameter estimation method with use of self-organizing maps has the best results among other feature extraction-clustering performances, with up to 94.94% overall clustering accuracies. The results also suggest that the implemented method is robust against speckle noise.

show abstract

Section: Curvelet Transform Subband Statistical Momentsmentioning

confidence: 99%

Synthetic Aperture Radar Image Clustering with Curvelet Subband Gauss Distribution Parameters

Uslu

Albayrak

2014

Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

“…Curvelet analysis is the multi scale directional transform in the higher dimensions that incorporates the multi scale geometric information such as curvely shaped features during the modeling process [11]. It is capable of feature extractions such as spatial locality, scale and orientation details in more directions, which is critical to the analysis of piece-wise smooth image with rich edge information.…”

Section: Introductionmentioning

confidence: 99%

“…Theoretically it can achieve the optimal sparse representation of the C 2 sigularities. It uses angled polar wedges or angled trapezoid window to achieve optimal sparse representation of curvelike features [11]. Compared to multivariate wavelet analysis, Curvelet analysis has demonstrated more accurate projection and modeling of edge discontinuities mainly in the engineering fields including video processing, biomedical and seismic data analysis, fluid mechanics analysis and partial differential equation analysis, etc.…”

Section: Introductionmentioning

confidence: 99%

“…Compared to multivariate wavelet analysis, Curvelet analysis has demonstrated more accurate projection and modeling of edge discontinuities mainly in the engineering fields including video processing, biomedical and seismic data analysis, fluid mechanics analysis and partial differential equation analysis, etc. [11]. For example, [12] found the improved breast detection accuracy using the Curvelet analysis [12].…”

Section: Introductionmentioning

confidence: 99%

“…[13] proposes the 2D+T Curvelet analysis to characterize the dyanmic texture in the image sequences and found the satisfactory performance [13]. [11] proposed the curvelet based feature extraction method to achieve robust speckle noise reduction in synthetic aperture radar image analysis [11]. [14] found the improved noise removal performance when the nonlinear means denoising method is used to analyze the signal in the projected Curvelet domain [14].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Curvelet based Approach to Time Series Forecasting

Zou

Meiying

2015

Procedia Computer Science

View full text Add to dashboard Cite

In this paper we propose a new Curvelet based methodology for modeling the financial time series data, addressing and incorporating the diverse range of data characteristics. With the proposed methodology, we analyze and model the geometric multi scale and chaotic data characteristics. Empirical studies with some typical financial time series data show that more diverse heterogeneous data characteristics can be revealed and modeled in the projected time delayed domain. The proposed algorithm demonstrates the superior performance compared with the benchmark models.

show abstract

Curvelet-Based Classification of Brain MRI Images

Damseh

Ahmad

2017

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Curvelet-Based Synthetic Aperture Radar Image Classification

Cited by 25 publications

References 9 publications

Synthetic Aperture Radar Image Clustering with Curvelet Subband Gauss Distribution Parameters

Synthetic Aperture Radar Image Clustering with Curvelet Subband Gauss Distribution Parameters

A Curvelet based Approach to Time Series Forecasting

Curvelet-Based Classification of Brain MRI Images

Contact Info

Product

Resources

About