A Neural Network-Based Optical Imaging Method for Scattering Media

A neural network and optical imaging technology, which is applied in the field of optical imaging of scattering media based on neural networks, can solve problems such as large amount of calculation of shaping and transmission matrix, complex operation of optical phase conjugation technology, etc., and achieve fast imaging speed, The effect of easy operation

Active Publication Date: 2021-08-24
IBE ELECTRONICS CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the calculation of wavefront shaping and transmission matrix is ​​large, and the operation of optical phase conjugation technology is complicated, and there are still no related mature technical products

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 Neural Network-Based Optical Imaging Method for Scattering Media
  • A Neural Network-Based Optical Imaging Method for Scattering Media
  • A Neural Network-Based Optical Imaging Method for Scattering Media

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] In order to make the purpose of the present invention, technical solutions and advantages clearer, the following combination figure 1 , figure 2 and image 3 Embodiments of the present invention are further described in detail.

[0023] The embodiment of the present invention discloses a neural network-based scattering medium optical imaging method, which is realized by a neural network-based scattering medium optical imaging system, including two processes of scattering medium optical model construction and imaging.

[0024] Such as figure 1 As shown, in the neural network-based scattering medium optical imaging system, a beam of laser light emitted by the laser 1 is converged by the first lens 2, and a diaphragm 3 is placed at the focal point of the light for low-pass filtering, and then passes through 1 / 2 The wave plate 4 and the polarizing plate 5 become polarized light in the horizontal polarization direction, and then the collimated and expanded beam of the se...

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 optical imaging of scattering medium based on neural network, which includes two processes of constructing optical neural network model of scattering medium and imaging. In the process of constructing the optical neural network model of the scattering medium, the modulated optical signal before the scattering medium is used as the output layer of the neural network model, and the optical speckle intensity information formed after passing through the scattering medium is used as the input layer of the model. The output layer data trains the neural network, and solves the parameters of each intermediate layer in the neural network model, so as to obtain a specific scattering medium optical neural network model. In the process of optical imaging of scattering media, the target pattern to be imaged is used as the input layer of the above neural network model, and the light wave pre-modulation signal is obtained through the calculation and output of the neural network, and then the pre-modulation signal is used to modulate the light wave surface of the incident light, thereby directly forming a target image.

Description

technical field [0001] The invention relates to the field of optical imaging of scattering media, in particular to a neural network-based optical imaging method for scattering media. Background technique [0002] Light scattering media can be seen everywhere in daily life, such as clouds, fog, biological tissues, walls, table surfaces, etc. It is difficult to directly transmit through this medium to realize optical imaging because the light is scattered randomly in a large amount. The study of optical imaging technology through scattering media will be of great significance to medical imaging of biological tissues, target imaging in haze, and target imaging in turbid water bodies. In order to control the scattered light and realize the optical imaging of scattering media, people have proposed various technical means such as wavefront shaping, transmission matrix, and optical phase conjugation. However, the calculation of wavefront shaping and transmission matrix is ​​large...

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): G02B27/00G06N3/04
CPCG02B27/0012G06N3/045
Inventor 何凌刚许尧军梁海史丽张凯李静静
Owner IBE ELECTRONICS CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products