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

A method for singleness identification and localization of microspheres based on microscopic images and deep learning

A microscopic image and deep learning technology, applied in the field of positioning and singleness recognition of microspheres, can solve problems such as non-identity

Active Publication Date: 2021-09-07
TIANJIN UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the above algorithm is also suitable for non-scalable cases, it is not the best choice for non-scalable cases

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 method for singleness identification and localization of microspheres based on microscopic images and deep learning
  • A method for singleness identification and localization of microspheres based on microscopic images and deep learning
  • A method for singleness identification and localization of microspheres based on microscopic images and deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The method for single identification and positioning of microspheres based on microscopic images and deep learning of the present invention will be described in detail below in conjunction with the embodiments and accompanying drawings.

[0030] The present invention uses a COMS camera to collect 8-bit grayscale microscopic images of microspheres, performs certain processing on the microscopic images, and finally achieves the purpose of identifying the shape of the microspheres and outputting the pixel coordinates at the center of the microspheres. The overall steps are attached figure 1 As shown, the detailed steps are as follows:

[0031] 1. Use optical tweezers and magnetic tweezers to perform several capture experiments on microspheres with diameters of 1 μm, 2 μm, and 5 μm, and use a CMOS camera to collect microscopic image data during the experiment, as shown in the attached figure 2 shown.

[0032] 2. For microspheres of different diameters, set boxes of diffe...

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 relates to a method for identifying and locating the singleness of microspheres based on microscopic images and deep learning, comprising the following steps: obtaining multiple microscopic images; extracting the microsphere regions in the microscopic images, and obtaining The image set X2 of X2 is used as the training set of the convolutional neural network; the convolutional neural network is built and trained, feature extraction is performed on the image, and the final output is used to represent the unique code of the classification result, where (1,0,0) Indicates no ball, (0,1,0) represents a single ball, (0,0,1) represents multiple balls, and the trained convolutional neural network is represented by C; positioning algorithm.

Description

technical field [0001] The invention relates to a method for single identification and positioning of microspheres based on microscopic images and deep learning. In particular, it relates to a method for unique identification and positioning of microspheres under narrow field of view and low depth of field imaging in optical tweezers and magnetic tweezers systems. Compared with the manual identification and positioning method in the optical tweezers and magnetic tweezers systems, the present invention can greatly improve the identification and positioning speed and accuracy of microspheres, and has great advantages in measurement and testing under the optical tweezers and magnetic tweezers systems. Significance. Background technique [0002] Optical tweezers and magnetic tweezers systems can capture and manipulate micro- and nano-scale particles, and measure the applied force. They have the characteristics of non-contact, non-damage, and high precision. They are widely used...

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): G06K9/62G06K9/46G06N3/04
CPCG06V10/40G06N3/045G06F18/241G06F18/214
Inventor 胡春光韩梦柯林祖增胡晓东李宏斌胡小唐
Owner TIANJIN UNIV