Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Construction method of wheat variety identification model

An identification model and construction method technology, applied in the field of wheat variety identification model construction, can solve the problems of poor representativeness of the model, failure to realize the classification of different varieties of wheat, and small source and number of samples, so as to achieve stable identification, protect the interests of farmers, The effect of ensuring national food security

Inactive Publication Date: 2020-06-12
INST OF AGRO FOOD SCI & TECH CHINESE ACADEMY OF AGRI SCI
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In recent years, there have been few researches on the identification of wheat varieties based on hyperspectral imaging technology, and there are problems such as the lack of classification between different varieties of wheat, the small number of samples, poor representativeness of the model, and low recognition among multiple varieties.

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
  • Construction method of wheat variety identification model
  • Construction method of wheat variety identification model
  • Construction method of wheat variety identification model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] (1) Collect wheat grain samples: Collect wheat grains from 6 varieties of Shiluan 02-1, Jimai 22, Zhoumai 27, Gaoyou 2018, Zhengmai 366 and Aikang 58. In order to facilitate data processing, it is necessary to assign a value to each variety. Shiluan 02-1 is assigned a value of 1, Jimai 22 is assigned a value of 2, Zhoumai 27 is assigned a value of 3, Gaoyou 2018 is assigned a value of 4, Zhengmai 366 is assigned a value of 5, and short Anti-58 is assigned a value of 6. 100 well-proportioned and intact grains of the same variety were selected as test samples. After completion, each test sample was individually sealed in a marked ziplock bag to be tested;

[0048] (2) Spectral image acquisition: The hyperspectral imaging system was used to collect the image information of wheat grains in 6 test samples;

[0049] (3) Data extraction:

[0050] a. Spectral information data: extract the region of interest in the image information obtained in step (2): use the feature extrac...

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 construction method of a wheat variety identification model. The method comprises the following steps of 1, acquiring a test sample, and acquiring the image information of the test sample; 2, collecting the spectral information data, morphological characteristic data, texture characteristic data and color characteristic data; 3, distributing the data to obtain a trainingset and a prediction set; 4, screening an optimal modeling method; and 5, screening the optimal input layer data to obtain the wheat variety identification model. The method of the invention providesa more accurate method for wheat variety identification, realizes the rapid, lossless, effective and stable identification of wheat varieties, provides guarantee for wheat harvesting and storage management, processing and the like, protects the interests of farmers, and guarantees the national grain safety.

Description

technical field [0001] The invention relates to the technical field of detection and research of agricultural products. More specifically, the present invention relates to a method for constructing a wheat variety identification model. Background technique [0002] my country is a big country in the cultivation of wheat, and wheat is the main food crop in northern my country. The purity of the seeds is directly related to the yield and quality of wheat. If wheat seeds are mixed with adulteration, it will greatly harm the interests of the country and farmers. Different varieties of wheat have great differences in growth conditions, pest resistance, yield, and quality. The negligence caused by the variety is confusing or mixed, resulting in the authenticity and purity of the variety being affected, thereby affecting the subsequent wheat processing process, resulting in a greater loss of economic benefits. Therefore, the identification of wheat varieties is of great signifi...

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 Applications(China)
IPC IPC(8): G01N21/25G01N21/84
CPCG01N21/25G01N21/84G01N2021/8466
Inventor 郭波莉吴永清李明张波张影全
Owner INST OF AGRO FOOD SCI & TECH CHINESE ACADEMY OF AGRI SCI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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