A detection and identification method, equipment and storage medium for spores in gynecological microecology
A recognition method and micro-ecological technology, applied in character and pattern recognition, acquisition/recognition of microscopic objects, calculation, etc., can solve the problems of large intra-class gap, small inter-class gap, and indistinguishability of epithelial cell nuclei, and achieve good practical application. Value and promotion value, the effect of accelerating convergence speed and reducing intra-class gap
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0091] Such as figure 2 As shown, an intelligent detection and identification method for spores in a gynecological microecology comprises the following steps:
[0092] Input the image to be detected into the effective target AI detection model, detect the corresponding target, and then eliminate the interference of the cell nucleus to the spore recognition through color segmentation, and determine whether the target is a spore.
[0093] The generation method of the effective target AI detection model is:
[0094] S1: Collect multi-scene microscopic images of gynecological vaginal microecological biological specimens based on Gram staining, and obtain original pictures, which contain at least one of spores and epithelial nuclei, and the resolution of the images is 1600×1200, In order to train an effective target detection model and ensure the completeness of the data, the image training set is sorted out in a more orderly manner, and classified according to the distribution o...
Embodiment 2
[0106] Such as figure 2 As shown, an intelligent detection and identification method for spores in a gynecological microecology comprises the following steps:
[0107] Input the image to be detected into the effective target AI detection model, detect the corresponding target, and then eliminate the interference of sperm to spore recognition through color segmentation, find the contour and calculate the minimum circumscribed quadrilateral of the contour and calculate the area of the minimum circumscribed quadrilateral again, so as to determine Whether the object is a spore.
[0108] The generation method of the effective target AI detection model is:
[0109] S1: Collect multi-scene microscopic images of gynecological vaginal microecological biological specimens based on Gram staining, and obtain original pictures, which contain at least one of spores and epithelial nuclei, and the resolution of the images is 1600×1200, In order to train an effective target detection model ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com