Adaptive filter support selection for signal denoising based on the improved ICI rule

Sucic, Victor; Lerga, Jonatan; Vrankić, Miroslav

doi:10.1016/j.dsp.2012.06.014

Cited by 18 publications

(26 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The LPA-RICI method's performance depends on the proper  and c R value selection, as shown in [3]. However, the LPA-RICI method's performance was shown to be significantly less sensitive to  and c R value selection than the LPA-ICI method is sensitive to proper  value selection [13]. Furthermore, c R was shown to belong to the finite interval 01 c R  (unlike the  value belonging to interval 0,    ), making it much easer than to find the proper  value for the ICI based method.…”

Section: The Modified Lpa-ici Methodsmentioning

confidence: 99%

“…Furthermore, c R was shown to belong to the finite interval 01 c R  (unlike the  value belonging to interval 0,    ), making it much easer than to find the proper  value for the ICI based method. Proper  and c R values selection for the LPA-RICI method was dealt with in [13], proposing the formula for ( , ) c R  pair. The next section presents the performance study of the LPA-RICI method with parameters selected using the formula given in [13].…”

Section: The Modified Lpa-ici Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Parameters Analysis for the Time-Varying Automatically Adjusted LPA Based Estimators

Lerga¹,

Franušić²,

Sucic³

2014

JOACE

Self Cite

View full text Add to dashboard Cite

The paper provides the performance analysis of the optimal parameters selection for the weighted local polynomial approximation (LPA) estimators combined by a data-driven adaptive method used for the automatically adjusted nonparametric LPA estimator size detection. The provided examples show that the LPA estimators upgraded by the modified adaptive intersection of the confidence intervals (ICI) based method (called the RICI method) outperform those based on the original ICI rule, while the ICI rule based LPA estimators were known to outperform non-adaptive ones with fixed size window length. The method's performance is analyzed in noise environment for two signals, showing the modified ICI based LPA estimators to be superior to those based on the original ICI method in terms of denoising estimation error reduction. The method can be applied in various technical fields, including image and video filtering, beamforming for phased array radar with antenna switching, acoustic echo cancellation, instantaneous frequency estimation, etc. 

show abstract

Section: The Modified Lpa-ici Methodsmentioning

confidence: 99%

Section: The Modified Lpa-ici Methodsmentioning

confidence: 99%

Parameters Analysis for the Time-Varying Automatically Adjusted LPA Based Estimators

Lerga¹,

Franušić²,

Sucic³

2014

JOACE

Self Cite

View full text Add to dashboard Cite

show abstract

“…The threshold R c can be chosen using the formula proposed in [5] ≤ values, the RICI rule was shown to significantly outperform the original ICI rule [7] when used in signal denoising.…”

Section: The Relative Ici (Rici) Methodsmentioning

confidence: 99%

“…In order to extract the useful information from the noisy data, i.e., to reduce noise as much as possible, a powerful and robust denoising method is required. The main goal of such methods is to reduce noise levels so that the estimation error (for example, mean squared error (MSE)) is as small as possible, while desirable signal features, such as jumps or instantaneous slope changes, are well preserved [5]. As shown in [6], successful denoising techniques utilize locally adaptive, edge-sensitive algorithms which provide trade-off between the noise removal and the instantaneous slope changes and edges preserving.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Methods for Video Denoising Based on the ICI, FICI, and RICI Algorithms

et al. 2018

View full text Add to dashboard Cite

Abstract:In various applications, reducing noise from video sequence is of crucial importance. In this paper, we have presented performance analysis of the novel video denoising method based on the relative intersection of confidence intervals (RICI) rule, and compared it to the methods based on the intersection of confidence intervals (ICI) rule and the fast ICI (FICI) rule. Detailed comparisons, based on two test video signals, are provided for a range of noise levels and different noise types. The RICI video denoising method has shown to outperform the original ICI based method, both in the algorithms execution time, reducing it by up to 11 %, and in the level of noise suppression, improving it by up to 10 dB. It also outperforms the FICI based video denoising method by up to 12.7 dB for the two test videos.

show abstract

“…On the other hand, too large z c values reduce variance and increase estimation bias resulting in oversized filter supports [8,10]. The proper z c value selection procedure is given in [11].…”

Section: The Ici Methodsmentioning

confidence: 99%

An ICI Based Algorithm for Fast Denoising of Video Signals

2014

Self Cite

View full text Add to dashboard Cite

In this paper, we have proposed a fast method for video denoising using the modified intersection of confidence intervals (ICI) rule, called fast ICI (FICI) method. The goal of the new FICI based video denoising method is to maintain an acceptable quality level of the denoised video estimate, and at the same time to significantly reduce denoising execution time when compared to the original ICI based method. The methods are tested on real-life video signals and their performances are analyzed and compared.It is shown that the FICI method outperforms the ICI method in terms of the execution time reduction by up to 96% (or up to 25 times). However, practical application demands dictate the choice of the video denoising method. If one wants fast denoising method with decent denoising results, the FICI based video denoising method is a better choice. The original ICI method, however, should be used in applications where significant noise suppression is an imperative regardless the computational complexity. Key words: adaptive and temporal filtering, edge preserving, intersection of confidence intervals (ICI) rule, video denoisingAlgoritam za brzo uklanjanje šuma iz video signala temeljen na ICI postupku. U ovom smo radu predložili brzi postupak za uklanjanje šuma iz video signala koristeći modificirano pravilo presjecišta intervala pouzdanosti (eng. intersection of confidence intervals -ICI), nazvano brzim ICI (eng. fast ICI -FICI) postupkom. Cilj novog FICI postupka za uklanjanje šuma iz video signala jest da se, uz zadržavanje prihvatljive razine kvalitete odšuml-jenog video signala, značajno smanji vrijeme izvršavanja algoritma u usporedbi s izvornim ICI postupkom. Postupci su testirani na realnim video signalima, a njihove su performanse analizirane i usporeîene.Pokazano je da FICI postupak ima do 96% kraće vrijeme izvršavanja (odnosno kraće i do 25 puta) u usporedi s izvornim ICI postupkom. Meîutim, zahtjevi praktične primjene odreîuju izbor postupka za uklanjanje šuma iz video signala. Ukoliko je potrebno brzo izvršavanje s pristojnim performansama uklanjanja šuma, FICI postupak je bolji izbor. Meîutim, u aplikacijama kojima je imperativ značajno suzbijanje šuma bez obzira na računsku složenost, trebao bi se koristiti izvorni ICI postupak.Ključne riječi: adaptivno i vremensko filtriranje, očuvanje rubova, metoda presjecišta intervala pouzdanosti, uklanjanje šuma iz video signala

show abstract

Adaptive filter support selection for signal denoising based on the improved ICI rule

Cited by 18 publications

References 17 publications

Parameters Analysis for the Time-Varying Automatically Adjusted LPA Based Estimators

Parameters Analysis for the Time-Varying Automatically Adjusted LPA Based Estimators

Adaptive Methods for Video Denoising Based on the ICI, FICI, and RICI Algorithms

An ICI Based Algorithm for Fast Denoising of Video Signals

Contact Info

Product

Resources

About