2020 International Conference on Inventive Computation Technologies (ICICT) 2020
DOI: 10.1109/icict48043.2020.9112434
|View full text |Cite
|
Sign up to set email alerts
|

Analysis of Deep Learning Architecture for Non-Uniformly Illuminated Images

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
4
1
1

Relationship

0
6

Authors

Journals

citations
Cited by 7 publications
(1 citation statement)
references
References 9 publications
0
1
0
Order By: Relevance
“…This method has strong dependence on the constructed energy functional model, and the image is prone to step effect after corrected, and the algorithm solution convergence speed is slow. The nonuniformity correction methods based on statistical matching include histogram matching [16], moment matching [17,18] and their improvement methods [19][20][21][22][23], among others, the essence of moment matching is to normalize the image [24][25][26], taking the average of all column means and column standard deviations of the whole image as reference values and bring them into the moment matching formula to complete the non-uniformity correction of recovering the true column means from the column means containing noise. These methods perform non-uniformity correction according to the difference of the numerical statistics of the imaging data, and the column mean of the corrected image is too smooth, which can achieve better correction effect for remote sensing images with relatively uniform scenes.…”
Section: Introductionmentioning
confidence: 99%
“…This method has strong dependence on the constructed energy functional model, and the image is prone to step effect after corrected, and the algorithm solution convergence speed is slow. The nonuniformity correction methods based on statistical matching include histogram matching [16], moment matching [17,18] and their improvement methods [19][20][21][22][23], among others, the essence of moment matching is to normalize the image [24][25][26], taking the average of all column means and column standard deviations of the whole image as reference values and bring them into the moment matching formula to complete the non-uniformity correction of recovering the true column means from the column means containing noise. These methods perform non-uniformity correction according to the difference of the numerical statistics of the imaging data, and the column mean of the corrected image is too smooth, which can achieve better correction effect for remote sensing images with relatively uniform scenes.…”
Section: Introductionmentioning
confidence: 99%