Female genital tract pathogen identification method based on morphology and YOLO algorithm

A technology based on morphology and recognition methods, applied in the field of automatic recognition of microscope images, can solve problems such as visual fatigue, misdiagnosis, missed diagnosis, and low efficiency, and achieve the effect of meeting high-efficiency requirements and improving detection accuracy and detection rate

Active Publication Date: 2019-11-15
山东仕达思生物产业有限公司 +1
View PDF6 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method for identifying pathogens in the female reproductive tract based on morphology and YOLO algorithm, which is used to solve th

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
  • Female genital tract pathogen identification method based on morphology and YOLO algorithm
  • Female genital tract pathogen identification method based on morphology and YOLO algorithm
  • Female genital tract pathogen identification method based on morphology and YOLO algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0024] Select some images to be tested (such as 50,000), and mark the recognition targets in the images to be tested. The marked images are as follows: image 3 , 4 shown in .

[0025] The marked images are formed into a training set and put into the network for training to obtain a model.

[0026] Preliminary screening of the YOLOv3 model based on the Darknet framework: put the image to be recognized into the test program, call the trained model for testing, obtain the preliminary screening result of the model, and mark it in the original image. This step is specifically: after model training, the image to be tested is imported into the model network. At this time, the type information predicted by each grid is multiplied by the confidence information predicted by the preselected box area, and each preselected box area is obtained. The class-specific confidence score (specific type confidence):

[0027] ;

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 female genital tract pathogen identification method based on morphology and a YOLO algorithm. For the problems of pathogenic bacteria species identification, cell viabilityinspection and the like under a domestic microscope, the invention provides an accurate, rapid and intelligent diagnosis mode by taking out a suspected target through a darknet-53 network model and aYOLO algorithm and then matching with a traditional morphological algorithm for screening. The detection speed of the YOLO algorithm is hundreds of times higher than that of a traditional algorithm, the efficient requirement of medical diagnosis can be met, then a morphological algorithm is added to carry out shape fitting on a target, dimensions such as color values, contours and sizes are judged, and therefore the detection accuracy and the detection rate are further improved.

Description

technical field [0001] The invention relates to the field of automatic identification of microscope images, in particular to a method for identifying pathogens in the female reproductive tract based on morphology and YOLO algorithm. Background technique [0002] Bacteria detection under the microecology is a branch of human medical science. Studies have found that there are more than 200 kinds of microorganisms in human body secretions, including many pathogenic bacteria, or an imbalance in the number of certain bacteria that causes disease. For medical testing, including bacterial population density, diversity, dominant bacteria, collective inflammatory response, pathogenic microorganisms, and identification of various pathogenic bacteria, higher efficiency and higher accuracy are required. [0003] For the problem of micro-ecological balance, because the current diagnostic method is to find pathogenic bacteria such as spores and hyphae to judge the micro-ecological imbalan...

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
IPC IPC(8): G06T7/00G06K9/62
CPCG06T7/0012G06T2207/20036G06T2207/20081G06F18/214
Inventor 谢晓鸿谢时灵张平李鑫铭
Owner 山东仕达思生物产业有限公司
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap