Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Holographic reconstruction algorithm based on deep learning

A technology of deep learning and algorithm, applied in the field of digital holography and optics, can solve complex and massive calculation problems, and achieve the effect of simple optical path and fast calculation

Active Publication Date: 2019-03-12
NORTHWESTERN POLYTECHNICAL UNIV
View PDF4 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For digital holograms, computers are generally used to simulate the diffraction process of light waves to realize the numerical reconstruction of holograms, usually based on Fresnel diffraction algorithm or convolution algorithm, which requires a lot of calculation and is relatively complicated

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Holographic reconstruction algorithm based on deep learning
  • Holographic reconstruction algorithm based on deep learning
  • Holographic reconstruction algorithm based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] Embodiment 1: A kind of work flow that realizes the holographic reconstruction algorithm based on deep learning described in the present invention is as follows:

[0029] use as image 3 The off-axis holographic recording optical path includes: laser 1, collimating lens 2, non-polarizing beam splitting prism 3, mirror 4, cell sample 5, mirror 6, shutter 7, non-polarizing beam splitting prism 8, and CCD camera 9.

[0030] To execute the training phase: use image 3 In the optical path shown, first, the shutter 7 is opened, the reference light wave and the object light wave interfere on the target surface of the CCD camera 9, and the off-axis hologram H of the cell sample 5 is collected. n , and then close the shutter to collect the coaxial hologram D of the cell sample 5 n . Replace the cell sample, repeat the above process, and get the H of k samples n and D n , where n=1,2,3,4...k. The phase map P of the corresponding cell was obtained using a digital holographic...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a holographic reconstruction algorithm based on deep learning. Technical characteristics are as follows: an off-axis hologram of a training sample is acquired; the intensity image and the phase image of the sample are obtained by a digital holographic reconstruction algorithm; the coaxial hologram of the training sample and the corresponding intensity image and phase imageare used as a training set; the training set is input into a neural network model to train; training only needs to be carried out for one time; then, the coaxial hologram of an unknown sample can be acquired, and input into a trained network; and the intensity image and the phase image are recovered. The method has the advantages that: an optical path is simple; reference light is not needed; calculation is rapid; limitation of a boundary condition does not exist; and the intensity and phase information of an object can be recovered only through a coaxial hologram.

Description

technical field [0001] The invention relates to the field of optics, in particular to the field of digital holography. Background technique [0002] Due to the high frequency of light, the existing image acquisition equipment can only record the intensity information of the light field and cannot directly obtain the phase information, so the phase information of the light field needs to be recovered by means of the intensity information. The holographic interferometry technology records the phase information of the light field by introducing reference light waves to interfere with the object light waves to generate interference fringes of intensity distribution, which is a digital hologram. For digital holograms, computers are generally used to simulate the diffraction process of light waves to realize numerical reconstruction of holograms, usually based on Fresnel diffraction algorithm or convolution algorithm, which requires a lot of calculation and is relatively complicat...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G03H1/04G03H1/08
CPCG03H1/0443G03H1/0808G03H1/0866G03H2001/0883G03H2001/0825G03H2001/0816
Inventor 邸江磊王凯强李颖豆嘉真戴思清赵建林
Owner NORTHWESTERN POLYTECHNICAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com