2019
DOI: 10.3390/s19132975
|View full text |Cite
|
Sign up to set email alerts
|

Applying Speckle Noise Suppression to Refractive Indices Change Detection in Porous Silicon Microarrays

Abstract: The gray value method can be used to detect gray value changes of each unit almost parallel to the surface image of PSi (porous silicon) microarrays and indirectly measure the refractive index changes of each unit. However, the speckles of different noise intensities produced by lasers on a porous silicon surface have different effects on the gray value of the measured image. This results in inaccurate results of refractive index changes obtained from the change in gray value. Therefore, it is very important t… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2020
2020
2022
2022

Publication Types

Select...
4

Relationship

0
4

Authors

Journals

citations
Cited by 4 publications
(1 citation statement)
references
References 37 publications
0
1
0
Order By: Relevance
“…According to Figure 1 , the breast ultrasound image speckle de-noising process mainly consists of three parts: preprocessing, training and de-noising. First of all, the acquired breast ultrasound images are aligned, the standardized and clear ultrasound images are found, and the contrast increase processing is completed ( Piao et al, 2018 ; Ren et al, 2019 ). After processing, data expansion processing is performed to obtain training samples, and the 3D convolutional cloud network is obtained after training on the training samples.…”
Section: Methodsmentioning
confidence: 99%
“…According to Figure 1 , the breast ultrasound image speckle de-noising process mainly consists of three parts: preprocessing, training and de-noising. First of all, the acquired breast ultrasound images are aligned, the standardized and clear ultrasound images are found, and the contrast increase processing is completed ( Piao et al, 2018 ; Ren et al, 2019 ). After processing, data expansion processing is performed to obtain training samples, and the 3D convolutional cloud network is obtained after training on the training samples.…”
Section: Methodsmentioning
confidence: 99%