Spore germination rate calculation method and device and storage medium

A calculation method and technology of germination rate, applied in the field of image processing, can solve the problems of easy interference and low calculation accuracy of spore germination rate, and achieve the effect of avoiding interference and repeated focusing, improving classification accuracy and strong robustness.

Pending Publication Date: 2021-11-19
FOSHAN HAITIAN GAOMING FLAVORING & FOOD +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention provides a spore germination rate calculation method, device and storage medium to solve the problem that the existing spore germin

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
  • Spore germination rate calculation method and device and storage medium
  • Spore germination rate calculation method and device and storage medium
  • Spore germination rate calculation method and device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0056] As a specific implementation of the present invention, the construction method of the defuzzification model includes:

[0057] Obtaining the original spore image set, filtering out images without spores in the original spore image set to obtain a preprocessing image set; the preprocessing image set includes a first image set with clear focus and a second image set with blurred focus;

[0058] Segment the first image set and the second image set to obtain segmented image pairs, construct an autoencoder network according to the segmented image pairs, and construct a deblurring model by training the autoencoder network.

[0059] The original spore image set includes a clearly focused image set and a blurred focus image set. In the embodiment of the present invention, after preprocessing the original spore image set, a segmented image pair is obtained through image segmentation, and a deblurring is constructed based on the segmented image pair. Model, so that the deblurring...

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 spore germination rate calculation method and device and a storage medium. The method comprises the steps: obtaining a to-be-classified image, carrying out fuzzy calculation on the to-be-classified image, and judging whether the to-be-classified image needs to be deblurred or not; if yes, substituting the to-be-classified image into a preset deblurring model for fuzzy processing, and performing data segmentation to obtain a first segmented image set; if no, performing data segmentation on the to-be-classified image to obtain a first segmented image set; and substituting the first segmented image set into a preset classification model, obtaining a classification data set of the spore germination state, and calculating the spore germination rate according to the proportion of a germinated spore data set in the classification data set, wherein the classification data set of the spore germination state comprises the germinated spore data set, an ungerminated spore data set and other data sets. According to the embodiment of the invention, interference generated in a spore image processing process can be effectively eliminated, so that the spore germination state detection precision and the spore germination rate calculation precision are improved.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a calculation method, device and storage medium of spore germination rate. Background technique [0002] The image processing method based on deep learning is the most popular image processing method in recent years. It can effectively extract target features from a large amount of data independently, and solve many problems in the field of computer vision, such as image recognition, semantic segmentation, image classification, etc. Therefore, , and more and more researchers in other fields have begun to apply and solve various problems. The image processing neural network, from the earliest AlexNet, to the later VGG, ResNet, and then to the later Inception, DenseNet, etc., makes it very effective in classification and recognition in conventional natural image processing step by step. But among them, most of the methods need to establish a huge image set and car...

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): G06K9/00G06N3/04G06T5/30G06T7/12G06T7/155
CPCG06T7/155G06T7/12G06T5/30G06T2207/20021G06T2207/20081G06T2207/20084G06T2207/10056G06N3/045
Inventor 李泽鹏肖宇飞李贤信
Owner FOSHAN HAITIAN GAOMING FLAVORING & FOOD
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