2021
DOI: 10.1145/3450626.3459773
|View full text |Cite
|
Sign up to set email alerts
|

Fast median filters using separable sorting networks

Abstract: Median filters are a widely-used tool in graphics, imaging, machine learning, visual effects, and even audio processing. Currently, very-small-support median filters are performed using sorting networks, and large-support median filters are handled by O (1) histogram-based methods. However, the constant factor on these O (1) algorithms is large, and they scale poorly to data types above 8-bit integers. On the other hand, good sorting networks have not been descri… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
3
0

Year Published

2022
2022
2023
2023

Publication Types

Select...
7

Relationship

0
7

Authors

Journals

citations
Cited by 8 publications
(4 citation statements)
references
References 21 publications
0
3
0
Order By: Relevance
“…Therefore, in order to make the extracted spectral information more accurately reflect the change of the sample curve, it is necessary to preprocess the original spectrum to eliminate or reduce the influence of light intensity, environmental factors and noise interference on the spectral information as much as possible. In this experiment, the Savitzky-Golay(SG) , multivariate scatter correction(MSC) (Liang et al, 2018) and median filter(MF) (Adams, 2021) methods were used to preprocess the original data.…”
Section: Spectral Preprocessing Methodsmentioning
confidence: 99%
“…Therefore, in order to make the extracted spectral information more accurately reflect the change of the sample curve, it is necessary to preprocess the original spectrum to eliminate or reduce the influence of light intensity, environmental factors and noise interference on the spectral information as much as possible. In this experiment, the Savitzky-Golay(SG) , multivariate scatter correction(MSC) (Liang et al, 2018) and median filter(MF) (Adams, 2021) methods were used to preprocess the original data.…”
Section: Spectral Preprocessing Methodsmentioning
confidence: 99%
“…Morphological operations are related to the median filter in that they use statistical information within the windows. There are two main approaches to median filtering: the sorting network method [Ada21] and the histogram‐based method [Gre17]. Moroto et al [MU22] presented another approach using a wavelet matrix, and discussed its extension to polygonal windows.…”
Section: Related Workmentioning
confidence: 99%
“…Xu et al present an effective approach [45] for structure-texture image decomposition, leveraging the discriminative patch recurrence to develop a nonlocal transform that can better distinguish and sparsify texture components. Motivated by the rapid development of machine learning theory, many global filtering methods [3,[46][47][48][49][50][51][52][53][54][55][56][57] have been designed under the deep learning architecture. For instance, a CNN-based joint filter [46] was proposed by selectively taking advantage of the structure information consistent with both guided and input images.…”
Section: Introductionmentioning
confidence: 99%