The Correntropy Mace Filter for Image Recognition

Jeong, Kyu-Hwa; Prı́ncipe, José C.

doi:10.1109/mlsp.2006.275513

Cited by 17 publications

(11 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We do not discuss this work 5 further, since our objective is to examine kernel versions of DIFs. Prior kernel DIFs [2][3][4] have been used only for face recognition applications on near frontal face images. In this limited application, all test faces were registered and centered [2][3][4] , and thus no shifts of the test input faces were needed and only a single VIP at one fixed point was necessary.…”

Section: Prior Work and Our Work On Kernel Difsmentioning

confidence: 99%

See 1 more Smart Citation

Analysis of kernel distortion-invariant filters

Casasent

Patnaik

2007

SPIE Proceedings

View full text Add to dashboard Cite

Kernel techniques have been used in support vector machines (SVMs), feature spaces, etc. In kernel methods, the wellknown kernel trick is used to implicitly map the input data to a higher-dimensional feature space. If all terms can be written as a kernel function, one can then use data in higher-dimensional space without actually computing the higherdimensional features or knowing the mapping function Φ. In this paper, we address kernel distortion-invariant filters (DIFs). Standard DIFs are synthesized in a linear feature space (in the image or Fourier domain). They are fast since they use FFT-based correlations. If the data is mapped to a higher-dimensional feature space before filter synthesis and before performing correlations, kernel filters result and performance can be improved. Kernel versions of several DIFs (OTF, SDF, and Mace) have been presented in prior work. However, several key issues were ignored in all prior work. These include : the unrealistic assumption of centered data in tests, the significantly larger storage and on-line computation time required, and the proper type of energy minimization in filter synthesis to reduce false peaks is necessary when the filters are applied to target scenes and has yet to be done. In addition, prior kernel DIF work used test set data to select the value of the kernel parameter. In this paper, we analyze these issues, present supporting test results on two face databases, and present several improvements to prior kernel DIF work.

show abstract

Section: Prior Work and Our Work On Kernel Difsmentioning

confidence: 99%

“…All prior kernel DIF work [2][3][4] has not employed the shift-invariant property of DIFs. These prior kernel DIFs have been evaluated at only one point in a correlation output.…”

Section: Introductionmentioning

confidence: 99%

Analysis of kernel distortion-invariant filters

Casasent

Patnaik

2007

SPIE Proceedings

View full text Add to dashboard Cite

show abstract

“…[12] proposed a power spectral measure for Fourier based surrogate nonlinearity test through correntropy as a discriminant measure. Extending the Minimum Average Correlation Energy (MACE) filter to nonlinear filter via correntropy improves MACE performance, when applied to face recognition [13]. Moreover, similar extension of Granger causality by correntropy can detect causality of a nonlinear dynamical system where the linear Granger causality failed [14].…”

Section: Introductionmentioning

confidence: 99%

Kernel adaptive filtering with maximum correntropy criterion

Zhao

Chen

Prı́ncipe

2011

The 2011 International Joint Conference on Neural Networks

177

View full text Add to dashboard Cite

Abstract-Kernel adaptive filters have drawn increasing attention due to their advantages such as universal nonlinear approximation with universal kernels, linearity and convexity in Reproducing Kernel Hilbert Space (RKHS). Among them, the kernel least mean square (KLMS) algorithm deserves particular attention because of its simplicity and sequential learning approach. Similar to most conventional adaptive filtering algorithms, the KLMS adopts the mean square error (MSE) as the adaptation cost. However, the mere second-order statistics is often not suitable for nonlinear and non-Gaussian situations. Therefore, various non-MSE criteria, which involve higherorder statistics, have received an increasing interest. Recently, the correntropy, as an alternative of MSE, has been successfully used in nonlinear and non-Gaussian signal processing and machine learning domains. This fact motivates us in this paper to develop a new kernel adaptive algorithm, called the kernel maximum correntropy (KMC), which combines the advantages of the KLMS and maximum correntropy criterion (MCC). We also study its convergence and self-regularization properties by using the energy conservation relation. The superior performance of the new algorithm has been demonstrated by simulation experiments in the noisy frequency doubling problem.

show abstract

“…Therefore, it improves the accuracy in determining the pitch period. Correntropy has also been successfully applied to various signal processing and machine learning problems such as blind equalization [1], minimum average correlation energy filter [23], principal component analysis [24], and others. The proposed PDA method is applied after the acoustical signal is processed by an equivalent rectangular bandwidth filter bank in the time domain.…”

Section: Introduction P Itch or The Fundamental Frequencymentioning

confidence: 99%

A Pitch Detector Based on a Generalized Correlation Function

Prı́ncipe

2008

IEEE Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Abstract-This paper proposes a novel pitch determination algorithm (PDA) based on the newly introduced concept of a generalized correlation function called correntropy. Correntropy is a positive definite kernel function which implicitly transforms the original signal into a high-dimensional reproducing kernel Hilbert space (RKHS) in a nonlinear way, and calculates very efficiently the generalized correlation in that RKHS. By incorporating the kernel function, correntropy is able to utilize higher order statistics to enhance the resolution of pitch estimation. The proposed PDA computes the summary of correntropy functions from the outputs of an equivalent rectangular bandwidth (ERB) filter bank. We present simulations on pitch determination for a single vowel, double vowels, and a benchmark database test. Simulations show that correntropy exhibits much better resolution than conventional autocorrelation in pitch determination and outperforms other PDAs in the benchmark database test.Index Terms-Correntropy, pitch determination, reproducing kernel Hilbert space (RKHS).

show abstract

The Correntropy Mace Filter for Image Recognition

Cited by 17 publications

References 41 publications

Analysis of kernel distortion-invariant filters

Analysis of kernel distortion-invariant filters

Kernel adaptive filtering with maximum correntropy criterion

A Pitch Detector Based on a Generalized Correlation Function

Contact Info

Product

Resources

About