2013 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) 2013
DOI: 10.1109/fuzz-ieee.2013.6622458
|View full text |Cite
|
Sign up to set email alerts
|

Image reduction operators based on non-monotonic averaging functions

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
20
0

Year Published

2014
2014
2017
2017

Publication Types

Select...
5
3

Relationship

5
3

Authors

Journals

citations
Cited by 15 publications
(20 citation statements)
references
References 18 publications
0
20
0
Order By: Relevance
“…On the other hand, the averaging must be robust to the noise in the image, so that even large increases/ decreases in the intensity of the individual pixels (due to corruption) do not lead to the undesired changes in the intensity of the output. In fact discarding such outliers may lead to changes in the intensity in the opposite direction [7,8,31], as to minimize the dissimilarity between the non-corrupt inputs and the output. Hence weak monotonicity is one of the basic requirements in that application.…”
Section: Weak Monotonicitymentioning
confidence: 97%
See 1 more Smart Citation
“…On the other hand, the averaging must be robust to the noise in the image, so that even large increases/ decreases in the intensity of the individual pixels (due to corruption) do not lead to the undesired changes in the intensity of the output. In fact discarding such outliers may lead to changes in the intensity in the opposite direction [7,8,31], as to minimize the dissimilarity between the non-corrupt inputs and the output. Hence weak monotonicity is one of the basic requirements in that application.…”
Section: Weak Monotonicitymentioning
confidence: 97%
“…Recently proposed density based means [1] and their generalizations [10] also turn out to be proper weakly monotone. Another application comes from the processing of noisy images, where mode-like weakly monotone averages were used [7,8,31].…”
Section: Weak Monotonicitymentioning
confidence: 99%
“…On the other hand, the averaging must be robust to the noise in the image, so that even large increases/decreases in the intensity of the individual pixels (due to corruption) do not lead to the undesired changes in the intensity of the output. In fact discarding such outliers may lead to changes in the intensity in the opposite direction [9,10,30], as to minimize the dissimilarity between the non-corrupt inputs and the output. Hence weak monotonicity is one of the basic requirements in that application.…”
Section: Monotonicity In Applicationsmentioning
confidence: 97%
“…Another application comes from the processing of noisy images, where mode-like weakly monotone averages were used [9,10,30]. Image reduction refers to reducing the resolution of an image so that it can fit a particular display, or to speed up its analysis [6,22].…”
Section: Monotonicity In Applicationsmentioning
confidence: 99%
“…This technique was further adapted to the identification of clusters of pixels that represent fine-scale details in images and applied in the problem of image reduction [2]. In that study, a variety of intensity-based, mode-seeking algorithms were evaluated, and these mode-like averages were justified as a basis for identifying tonal clusters.…”
Section: Introductionmentioning
confidence: 99%