US 12,235,607 B2
Machine learning-based digital holography device and method for operating same
Sang Joon Lee, Pohang-si (KR); and Tae Sik Go, Pohang-si (KR)
Assigned to POSTECH RESEARCH AND BUSINESS DEVELOPMENT FOUNDATION, Pohang-si (KR)
Appl. No. 18/015,139
Filed by POSTECH RESEARCH AND BUSINESS DEVELOPMENT FOUNDATION, Pohang-Si (KR)
PCT Filed Aug. 31, 2020, PCT No. PCT/KR2020/011619
§ 371(c)(1), (2) Date Jan. 9, 2023,
PCT Pub. No. WO2022/014772, PCT Pub. Date Jan. 20, 2022.
Claims priority of application No. 10-2020-0088205 (KR), filed on Jul. 16, 2020.
Prior Publication US 2023/0251603 A1, Aug. 10, 2023
Int. Cl. G03H 1/00 (2006.01); G02B 21/00 (2006.01); G02B 21/12 (2006.01); G03H 1/04 (2006.01); G06N 3/045 (2023.01); G06N 3/08 (2023.01); G06T 7/50 (2017.01)
CPC G03H 1/0005 (2013.01) [G02B 21/12 (2013.01); G03H 1/0443 (2013.01); G06N 3/045 (2023.01); G06N 3/08 (2013.01); G06T 7/50 (2017.01); G02B 21/0008 (2013.01); G03H 2001/005 (2013.01); G03H 2210/33 (2013.01); G03H 2226/02 (2013.01); G06T 2207/10056 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 12 Claims
OG exemplary drawing
 
1. A digital holographic method including:
obtaining a bright-field (BF) image comprising two-dimensional (2D) information of a sample; and
generating a hologram image comprising three-dimensional (3D) information of the sample by inputting the BF image to a neural network, the neural network being trained by statistically learning a relationship between a training BF image according to a depth of a training sample and a corresponding training hologram image of the training sample.