Supercharge Your Innovation With Domain-Expert AI Agents!

An Autofocus Method for Formed Component Analyzer

A technology of automatic focusing and component analysis, applied in neural learning methods, color TV parts, TV system parts, etc., can solve problems such as inaccurate focus positions, and achieve the effect of simple calculation and easy implementation

Active Publication Date: 2022-04-12
长春迈克赛德医疗科技有限公司
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The invention provides an automatic focusing method of a formed component analyzer, which is used to solve the problem of inaccurate focusing position existing in the traditional evaluation function method

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
  • An Autofocus Method for Formed Component Analyzer
  • An Autofocus Method for Formed Component Analyzer
  • An Autofocus Method for Formed Component Analyzer

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] An automatic focusing method for a formed component analyzer, the automatic focusing method comprising the following steps:

[0039] An automatic focusing method for a formed component analyzer, the automatic focusing method comprising the following steps:

[0040] Step 1: the focus drive motor 5 of the autofocus device drives the planar flow cell 2, so that the focusing liquid flows through the planar flow cell 2;

[0041] Step 2: Based on the planar flow cell 2 through which the focused liquid flows in step 1, start from the initial position and move forward with the same step length, and take m images at each position, and move n positions in total;

[0042] Step 3: performing image segmentation on each of the m*n images in step 2 to obtain a standard particle image;

[0043] Step 4: Construct a deep neural network model based on the standard particle image in step 3;

[0044] Step 5: Train the deep neural network model of step 4 to obtain network parameters;

[0...

Embodiment 2

[0065] Step S1: move forward 500 steps from the starting point, with a step size of 1 micron, and take m=2 images at each position;

[0066] Step S2: Take a fixed threshold T, and use the threshold segmentation method to segment the image to obtain a standard particle image. The length and width of the standard particle image are both 40 pixels, and m i standard particle images, m i ≥0;

[0067] Step S3: Assign labels to the standard particle images, the label range is [-1.0,1.0], the label value of the standard particle at the focus position is 0, the label value of the standard particle on the left of the focus decreases in turn, and the label value of the standard particle on the right of the focus The label value of the standard particle increases sequentially, and its increasing or decreasing trend is linear, thus constructing the training set;

[0068] Step S4: The deep neural network consists of multiple convolutional layers, pooling layers, and fully connected layers...

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 an automatic focusing method of a formed component analyzer. Step 1: The focusing motor of the automatic focusing device drives the planar flow cell, so that the focusing liquid flows through the flow cell; Step 2: Based on the flow cell through which the focusing liquid flows in step 1, start from the initial position and move forward with the same step length Move, take m images at each position, and move n positions in total; Step 3: Carry out image segmentation on each of the m*n images in Step 2 to obtain a standard particle image; Step 4: Based on Step 3 The standard particle image of the standard particle image constructs the deep neural network model; Step 5: train the deep neural network model of step 4 to obtain network parameters; Step 6: do linear regression on the deep neural network model after the training of step 5, regression line The position where the axes intersect is the focus position. The invention is used to solve the problem of inaccurate focus position in the traditional evaluation function method.

Description

technical field [0001] The invention belongs to the field of automatic focusing; in particular, it relates to an automatic focusing method of a formed component analyzer. Background technique [0002] The traditional autofocus method based on image processing generally adopts the focus evaluation function method, by taking images at different positions, calculating the focus evaluation function values ​​of images at different positions, and taking the position at the maximum value of the focus evaluation function as the focus position. Since the focus evaluation function may have multiple peaks, it is easy to cause the obtained focus position to be inaccurate. Contents of the invention [0003] The invention provides an automatic focusing method of a formed component analyzer, which is used to solve the problem of inaccurate focusing position in the traditional evaluation function method. [0004] The present invention is realized through the following technical solutions...

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): H04N5/232G06N3/04G06N3/08
CPCG06N3/04G06N3/08H04N23/67H04N23/64
Inventor 王巧龙赵文军赵学魁陈海龙姜云龙
Owner 长春迈克赛德医疗科技有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com