Abstract
In this Letter, we propose a fast speckle noise reduction method with only a single reconstructed image based on convolutional neural networks. The proposed network has multi-sized kernels that can capture the speckle noise component effectively from digital holographic images. For robust noise reduction performance, the network is trained with a large noisy image dataset that has object-dependent noise and a wide range of noise levels. The experimental results show the fast, robust, and outstanding speckle noise reduction performance of the proposed approach.
| Original language | English |
|---|---|
| Pages (from-to) | 4240-4243 |
| Number of pages | 4 |
| Journal | Optics Letters |
| Volume | 43 |
| Issue number | 17 |
| DOIs | |
| Publication status | Published - 2018 Sep 1 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Atomic and Molecular Physics, and Optics
Cite this
}
Speckle noise reduction for digital holographic images using multi-scale convolutional neural networks. / Jeon, Wonseok; Jeong, Wooyoung; Son, Kyungchan; Yang, Hyunseok.
In: Optics Letters, Vol. 43, No. 17, 01.09.2018, p. 4240-4243.Research output: Contribution to journal › Article
TY - JOUR
T1 - Speckle noise reduction for digital holographic images using multi-scale convolutional neural networks
AU - Jeon, Wonseok
AU - Jeong, Wooyoung
AU - Son, Kyungchan
AU - Yang, Hyunseok
PY - 2018/9/1
Y1 - 2018/9/1
N2 - In this Letter, we propose a fast speckle noise reduction method with only a single reconstructed image based on convolutional neural networks. The proposed network has multi-sized kernels that can capture the speckle noise component effectively from digital holographic images. For robust noise reduction performance, the network is trained with a large noisy image dataset that has object-dependent noise and a wide range of noise levels. The experimental results show the fast, robust, and outstanding speckle noise reduction performance of the proposed approach.
AB - In this Letter, we propose a fast speckle noise reduction method with only a single reconstructed image based on convolutional neural networks. The proposed network has multi-sized kernels that can capture the speckle noise component effectively from digital holographic images. For robust noise reduction performance, the network is trained with a large noisy image dataset that has object-dependent noise and a wide range of noise levels. The experimental results show the fast, robust, and outstanding speckle noise reduction performance of the proposed approach.
UR - http://www.scopus.com/inward/record.url?scp=85052578601&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85052578601&partnerID=8YFLogxK
U2 - 10.1364/OL.43.004240
DO - 10.1364/OL.43.004240
M3 - Article
AN - SCOPUS:85052578601
VL - 43
SP - 4240
EP - 4243
JO - Optics Letters
JF - Optics Letters
SN - 0146-9592
IS - 17
ER -