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

A Deep Learning-Based Method for Eliminating Defocus Noise in Optical Scanning Holography

A technology of defocus noise and optical scanning, applied in the field of optical scanning holography, can solve the problems of rough edges, low timeliness, deformation, etc., and achieve the effect of simple implementation, easy operation, and simple method

Inactive Publication Date: 2019-09-24
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The document "Sectional image reconstruction in optical scanning holography using a random-phase pupil" proposes an algorithm for encrypting optical scanning holograms by using random phase plates, and proposes a method to eliminate defocus noise by using multi-frame averaging. The method can eliminate defocus noise very well, but due to the need for multi-frame averaging processing, the timeliness is low
[0005] The document "Defocus noise suppression with combined frame difference and connected component methods in optical scanning holography" proposes a method based on frame difference method and connected domain. This method has good timeliness, but the edge of the result obtained by this method is not smooth. And it is deformed compared with the original image

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
  • A Deep Learning-Based Method for Eliminating Defocus Noise in Optical Scanning Holography
  • A Deep Learning-Based Method for Eliminating Defocus Noise in Optical Scanning Holography
  • A Deep Learning-Based Method for Eliminating Defocus Noise in Optical Scanning Holography

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0054] Such as Figure 1 to Figure 6 As shown, the method for eliminating the defocus noise of optical scanning holography based on deep learning, the specific steps are as follows:

[0055] (S100) Obtaining an encrypted hologram by scanning the object with an optical holographic scanning device:

[0056] The basic structure of the optical holographic scanning device used is as follows: figure 1 As shown, it includes: the laser Laser, the first beam splitter BS1 corresponding to the laser Laser, the acousto-optic modulator AOFS, the first mirror M1, the first pupil p 1 (x, y) and the first optical path formed by the first convex lens L1 and corresponding to the first beam splitter BS1, the second mirror M2, the second pupil p 2 (x, y) and the second convex lens L2 constitute the second optical path corresponding to the first beam splitter BS1, the second beam splitter BS2 that combines the first optical path and the second optical path by interference, and the second beam sp...

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 method for eliminating defocus noise in optical scanning holography based on deep learning, which belongs to the fields of optical scanning holography and image denoising, and mainly solves the problem of defocus noise in optical scanning holography. The present invention uses a deep neural network learning method to eliminate the defocus noise of the reconstructed image after random encryption processing, and eliminates the defocus noise of the test image by training images with defocus noise and images without defocus noise. The invention effectively solves the problem of large defocus noise in optical scanning holography, and the noise removal method is applicable to various fields.

Description

technical field [0001] The present invention relates to the field of optical scanning holography and the field of image denoising, in particular, to a method for eliminating defocus noise of optical scanning holography based on deep learning and a device for realizing the method. Background technique [0002] Optical scanning holography, referred to as OSH, uses point-by-point scanning to store three-dimensional objects in the form of two-dimensional digital images. Compared with general digital holography, it scans point by point, so its resolution is not limited by digital devices. Limiting, meanwhile, its obtained holograms without interference-induced speckle noise. Since the technology was proposed, it has been applied in many fields, such as: scanning holographic microscope, 3D image recognition and 3D optical remote sensing and other fields. [0003] Eliminating defocus noise has always been a hot research issue in optical scanning holography, and it is of great sign...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G03H1/04G03H1/10
Inventor 欧海燕吴勇邵维王秉中
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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