Unlock instant, AI-driven research and patent intelligence for your innovation.

Device and method for lensless dual-type fusion target detection based on deep learning

A technology of target detection and deep learning, applied in neural learning methods, measurement devices, optical devices, etc., can solve the problems of poor quality of imaging results, and achieve the effect of reducing the workload of manual adjustment and speeding up the speed.

Active Publication Date: 2022-05-13
HANGZHOU DIANZI UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to solve the problem of poor imaging result quality in lensless microscopic imaging technology and the high requirement of imaging result expertise in practical application, a solution is proposed

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
  • Device and method for lensless dual-type fusion target detection based on deep learning
  • Device and method for lensless dual-type fusion target detection based on deep learning
  • Device and method for lensless dual-type fusion target detection based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific implementations described here are only used to explain the present invention, not to limit the present invention.

[0064] Two-step imaging method of digital holography: recording and reproduction. In the recording of holograms, the diffracted light waves of the object are recorded by reference light; during reproduction, the illumination light waves undergo the diffraction of the hologram to realize the reconstruction of the object light waves.

[0065] The implementation of the present invention will be further described below in conjunction with the accompanying drawings.

[0066] First, a simple schematic diagram of the experimental setup is shown in figure 2 As shown, the device includes a dual-type ...

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 lensless dual-type fusion target detection device and method based on deep learning. The device includes a dual-type fusion holographic lensless imaging module and a neural network module. The dual-type fusion holographic lensless imaging module includes a laser source, a microhole , filter, first reflector, second reflector, first coherent light source, second coherent light source, target sample and glass slide, first CCD sensor, second CCD sensor, computer and moving slide rail, neural network The module consists of a position parameter optimization neural network and a target detection area convolutional neural network. The dual-type fusion lensless imaging module simultaneously obtains the imaging information of the transmission module and the reflection module, and finally fuses and reconstructs higher-quality imaging results. The network continuously optimizes the position parameters, further optimizes the imaging results, and finally predicts the results by the convolutional neural network in the target detection area, and outputs easy-to-understand and explicit evaluation results.

Description

technical field [0001] The invention relates to the technical fields of computational imaging, deep learning, and lensless microscopic imaging, and in particular to a lensless dual-type fusion target detection device and method based on deep learning. Background technique [0002] Nowadays, the problems of disease diagnosis, food safety testing and environmental pollution investigation in backward areas are becoming more and more prominent. The traditional optical microscope system makes the optical microscope increasingly expensive, cumbersome and difficult to maintain. Due to remoteness and lack of talents in backward areas, equipment and technology cannot be well promoted and applied. [0003] Lensless imaging technology is a new type of effective imaging microscopy technology developed in recent years: it does not use lenses to focus, but directly transmits the sample to the photodetector to record the image, and uses effective algorithms to reconstruct the clear image. ...

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): G01N21/45G01B11/24G06N3/04G06N3/08
CPCG01N21/45G01B11/2441G06N3/08G01N2021/458G06N3/045
Inventor 赵巨峰吴小辉崔光茫毛海锋林君张钰臧月
Owner HANGZHOU DIANZI UNIV