Feature extraction from wavelet coefficients for pattern recognition tasks

Pittner, Stefan; Kamarthi, Sagar

doi:10.1109/icnn.1997.614016

Cited by 48 publications

(63 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…6 Fourier transformation. Out of many available signal representations, such as Fourier transformation, discrete wavelets, and wavelet packets, 22 we choose Fourier transform to characterize the temporal enhancement curves of breast tissues. A pixelwise 1D discrete Fourier transform ͑DFT͒ is performed on the enhancement curve of each pixel p, C͑p , t͒ ͑t =1, ... ,T −1͒ ͓as defined in Eq.…”

Section: Iiib2 Temporal Enhancement Modelingmentioning

confidence: 99%

STEP: Spatiotemporal enhancement pattern for MR‐based breast tumor diagnosis

et al. 2009

View full text Add to dashboard Cite

The authors propose a spatiotemporal enhancement pattern ͑STEP͒ for comprehensive characterization of breast tumors in contrast-enhanced MR images. By viewing serial contrast-enhanced MR images as a single spatiotemporal image, they formulate the STEP as a combination of ͑1͒ dynamic enhancement and architectural features of a tumor, and ͑2͒ the spatial variations of pixelwise temporal enhancements. Although the latter has been widely used by radiologists for diagnostic purposes, it has rarely been employed for computer-aided diagnosis. This article presents two major contributions. First, the STEP features are introduced to capture temporal enhancement and its spatial variations. This is essentially carried out through the Fourier transformation and pharmacokinetic modeling of various temporal enhancement features, followed by the calculation of moment invariants and Gabor texture features. Second, for effectively extracting the STEP features from tumors, we develop a graph-cut based segmentation algorithm that aims at refining coarse manual segmentations of tumors. The STEP features are assessed through their diagnostic performance for differentiating between benign and malignant tumors using a linear classifier ͑along with a simple ranking-based feature selection͒ in a leave-one-out cross-validation setting. The experimental results for the proposed features exhibit superior performance, when compared to the existing approaches, with the area under the ROC curve approaching 0.97.

show abstract

Section: Iiib2 Temporal Enhancement Modelingmentioning

confidence: 99%

STEP: Spatiotemporal enhancement pattern for MR‐based breast tumor diagnosis

et al. 2009

View full text Add to dashboard Cite

show abstract

“…The following techniques are commonly used for mapping data on a new space where their properties can facilitate pattern recognition: PCA, ICA, Hermite expansions (HEs), and WT, among others. In this study, PCA and WT [29] were used as transformation principles of the data in order to carry out the feature extraction stage.…”

Section: ) Level 1 (Projection)mentioning

confidence: 99%

Dimensionality Reduction Oriented Toward the Feature Visualization for Ischemia Detection

Delgado-Trejos

Perera-Lluna

Vallverdú-Ferrer

et al. 2009

IEEE Trans. Inform. Technol. Biomed.

View full text Add to dashboard Cite

Abstract-An effective data representation methodology on high-dimension feature spaces is presented, which allows a better interpretation of subjacent physiological phenomena (namely, cardiac behavior related to cardiovascular diseases), and is based on search criteria over a feature set resulting in an increase in the detection capability of ischemic pathologies, but also connecting these features with the physiologic representation of the ECG. The proposed dimension reduction scheme consists of three levels: projection, interpretation, and visualization. First, a hybrid algorithm is described that projects the multidimensional data to a lower dimension space, gathering the features that contribute similarly in the meaning of the covariance reconstruction in order to find information of clinical relevance over the initial training space. Next, an algorithm of variable selection is provided that further reduces the dimension, taking into account only the variables that offer greater class separability, and finally, the selected feature set is projected to a 2-D space in order to verify the performance of the suggested dimension reduction algorithm in terms of the discrimination capability for ischemia detection. The ECG recordings used in this study are from the European ST-T database and from the Universidad Nacional de Colombia database. In both cases, over 99% feature reduction was obtained, and classification precision was over 99% using a five-nearest-neighbor classifier (5-NN).

show abstract

“…One of the most widely used techniques for identifying non-repetitive and/or periodic patterns or distortions has been the wavelet transform [4][5].This technique adapts a wavelet pattern to the characteristics of the signal distortion to be identified.This has been used for identification of epileptic spikes in electroencephalography (EEG) signal [6][7][8][9], to identify emboli in the blood flow signal [10][11][12][13], to identify arrhythmias in the ECG signal [14][15][16], for identifying flaws in industrial materials (metals, concrete, etc. )in the ultrasound signal [17][18][19], and many other scenarios.…”

Section: Iirelated Workmentioning

confidence: 99%

Stochastic Method for Non-Homogeneous Cycles Identification in Quasi-Periodic Signals

Guzmán¹,

Carbajal²

2015

IJAREEIE

View full text Add to dashboard Cite

ABSTRACT:Quasi-periodic signals can be contaminated with random distortions ("artifacts") not manifested periodically and homogenously,without affecting all signal cycles.These distortions cannot be characterized statistically or modelled with a known probability function. In this paper, a stochastic analysis method to detect the presence of such distortions is proposed. The aim of the method is identifying the affected cycles, which exhibit a different morphology compared to the unaffected cycles.The identification of the affected cycles (or non-homogeneous cycles) allows to estimate parameters and extract the useful information needed for a correct characterization of the signal.The method compares nearly periodic signal cycles through the mean square error and the estimated variance of the inherent noise affecting the signal. Expressions are derived to estimate this error and compared with experimental results.

show abstract

Feature extraction from wavelet coefficients for pattern recognition tasks

Cited by 48 publications

References 23 publications

STEP: Spatiotemporal enhancement pattern for MR‐based breast tumor diagnosis

STEP: Spatiotemporal enhancement pattern for MR‐based breast tumor diagnosis

Dimensionality Reduction Oriented Toward the Feature Visualization for Ischemia Detection

Stochastic Method for Non-Homogeneous Cycles Identification in Quasi-Periodic Signals

Contact Info

Product

Resources

About