Effectiveness of Spectral Band Selection/Extraction Techniques for Spectral Data

Skurichina, Marina; Verzakov, Sergey; Pacĺık, Pavel; Duin, Robert P. W.

doi:10.1007/11815921_59

Cited by 5 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, transforms that decompose 2D contours which have different properties when compared to the Fourier transform can be investigated (e.g., the wavelet transform). To address the exhaustive combination of sets for descriptor selection, we plan to make use of methods for feature selection [23] or spectral band selection [28] that exist in the literature. Finally, we obtained improved results for the multi-class case by making use of a voting method, but even better results may be obtained with more elaborate coupling methods, e.g., by solving an optimization problem that takes into consideration the difference between the pairwise probability estimates [22].…”

Section: Discussionmentioning

confidence: 99%

Learning Fourier Descriptors for Computer-Aided Diagnosis of the Supraspinatus

et al. 2010

View full text Add to dashboard Cite

Rationale and Objectives. Supraspinatus muscle disorders are frequent and debilitating, resulting in pain and a limited range of shoulder motion.The gold standard for diagnosis involves an invasive surgical procedure. As part of a proposed clinical workflow for noninvasive computer-aided diagnosis (CAD) of the condition of the supraspinatus, we present a method to classify 3D shapes of the muscle into relevant pathology groups, based on magnetic resonance (MR) images. Results. We show that our method leads to significant improvement when compared to previous work. We are able to distinguish between normal shapes and shapes that possess a pathology with an accuracy of almost 100%. Materials andMoreover, we can differentiate between the different pathology groups with an average accuracy of 86%.Conclusion. We confirm that analyzing the 3D shape of the muscle has potential as a form of diagnosis reinforcement to assess the condition of the supraspinatus. Moreover, our proposed descriptor based on Fourier coefficients is able to distinguish the different pathology groups with accuracies higher than those obtained by previous work, indicating its potential application to support a system for CAD of the supraspinatus.

show abstract

Section: Discussionmentioning

confidence: 99%

Learning Fourier Descriptors for Computer-Aided Diagnosis of the Supraspinatus

et al. 2010

View full text Add to dashboard Cite

show abstract

“…While the coarse spectral resolution of imaging instruments such as Landsat-TM, ETMþ, ASTER, SPOT-HRV, IRS-LISS limits the ability to distinguish and map finer spectral differences of materials, very narrow spectral resolution coupled with large number of spectral bands significantly reduces the efficiency and accuracy of spectral analysis methods for material mapping. Consequently, numerous studies have reported the selection of optimal spectral bands as a compromise solution for an efficient processing of hyperspectral data for material mapping (Karlholm and Renhorn, 2002;Skurichina et al, 2006;Melendez-Pastor et al, 2008). Furthermore, the majority of the current generation hyperspectral imaging systems (eg, AVIRIS, HyMAP, DICE, CASI) acquires spectral data at a spectral resolution of 10-20 nm with variable sampling intervals, thus requiring the resampling of the finer resolution spectral libraries to match to that of the hyperspectral image under consideration.…”

Section: Optimal Spectral Resolution/sampling Intervalmentioning

confidence: 99%

A method for selecting optimal spectral resolution and comparison metric for material mapping by spectral library search

Nidamanuri

Zbell

2010

Progress in Physical Geography: Earth and Environment

View full text Add to dashboard Cite

Use of spectral library searching as an automated method of analysing hyperspectral remote sensing data for material mapping is gaining prominence, especially in the mineral mapping domain. The possibility and reliability of material identification by the spectral library search approach depends on the spectral representation, characterized by spectral resolution (or sampling interval) and comparison metric used. We present a method referred to as Relative Search Performance (RSP) for an evaluation of various spectral representations and comparison metrics for designing an optimal library search system for material mapping. The proposed method works on the basis of tracking the changes in the spectral matching ranks of entries in the hit lists of spectral library searches for various spectral representations and comparison metrics relative to a chosen standard. The method has been tested for the comparison of the search performance of various discrete spectral sampling intervals and popular comparison metrics using the USGS Spectral Library. Results indicate that this approach can be used for the selection of optimal spectral representation and/or for selecting a comparison metric appropriate for a particular material mapping application by the reflectance spectral library search.

show abstract

“…Since which spectral band selection technique is preferred seems to be defined by the problem [5], we study the performance of 7 different band selection strategies, applied for spectral classification of seismic events at Nevado del Ruiz volcano. We compare these results with those obtained without any dimensionality reduction, i.e.…”

Section: Introductionmentioning

confidence: 99%

Spectral Characterization of Volcanic Earthquakes at Nevado del Ruiz Volcano Using Spectral Band Selection/Extraction Techniques

Orozco-Alzate

Skurichina

Duin

2008

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. Spectral content of seismic signals contains essential information for discriminating different classes of volcanic earthquakes. Such an information is largely redundant; therefore, a reduce number of spectral regions may provide almost the same description of the original events. By reducing the number of bands considered, the amount of data to be processed is significantly decreased and the interpretability of the characterization results is enhanced as well. We consider several spectral band selection methods in a two-class classification problem of volcanic earthquakes recorded at Nevado del Ruiz Volcano. Selection approaches have been compared to each other in terms of classification accuracy as well as by looking at the resulting spectral divisions. Detailed discussions about the technical considerations of the selection approaches as well as regarding their possible physical interpretations have been conducted. Results show that the sequential selection approach is the most flexible and powerful for classifying and characterizing volcanic earthquakes.

show abstract

Effectiveness of Spectral Band Selection/Extraction Techniques for Spectral Data

Cited by 5 publications

References 12 publications

Learning Fourier Descriptors for Computer-Aided Diagnosis of the Supraspinatus

Learning Fourier Descriptors for Computer-Aided Diagnosis of the Supraspinatus

A method for selecting optimal spectral resolution and comparison metric for material mapping by spectral library search

Spectral Characterization of Volcanic Earthquakes at Nevado del Ruiz Volcano Using Spectral Band Selection/Extraction Techniques

Contact Info

Product

Resources

About