Tea leaf grade identification method based on image recognition technology

A technology of image recognition and identification method, applied in measuring devices, material analysis by optical means, instruments, etc., can solve the problems of high price, slow identification of tea grades, strong subjectivity, etc., and achieve the effect of wide application

Inactive Publication Date: 2015-09-16
TEA RES INST CHINESE ACAD OF AGRI SCI
View PDF5 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is that the tea grade identification speed in the prior art is slow, subjectivity is strong, the price is expensive, etc., and a new tea grade identification method is provided, which has the characteristics of fast and accurate identification of tea grades

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
  • Tea leaf grade identification method based on image recognition technology
  • Tea leaf grade identification method based on image recognition technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0023] Accurately weigh 1.00 g of first-grade West Lake Longjing, add 100 mL of 100 o C boiling water, brew for 6 minutes, drain the tea soup, carefully spread the tea leaves on a transparent film with a known area with tweezers, and set aside; you can also add 20 mL of 90 o C boiling water, brew for 2 minutes, or add 150 mL 60 o C boiling water, brew for 8 minutes.

Embodiment 2

[0025] The transparent film that has tealeaves obtained in embodiment 1 is placed on the scanner, scans, and obtains the tealeaves image, saves image number 300 dpi this moment.

Embodiment 3

[0027] The tea image file obtained in Example 2 is preprocessed, the background other than the transparent film is removed, and the image is named and saved; then the image is grayscaled to obtain a binarized image, which is defined as being greater than a grayscale threshold of 170 White, identified as a blank area, less than the gray threshold 170 is defined as black, identified as a tea area; then the black pixels in the binarized image are counted to obtain the percentage; the surface area Sa of the tea is equal to the area of ​​the known transparent film × percentage × 2. Obtain the binarized image of tea and the surface area of ​​tea. See attached figure 1 .

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 provides a tea leaf grade identification method based on an image recognition technology. The tea leaf grade identification method comprises the following steps: brewing tea leaves with different grades, and leaching tea soup; flatly paving the expanded tea leaves on a fixed transparent film with known area; scanning to obtain a tea leaf image; programming the tea leaf image by using matlab software and converting the tea leaf image into a black and white binary image; and calculating the ratio of black and white pixels in the image to accurately obtain the surface area of the tea leaves. SPSS data statistic analysis software is used for carrying out single-factor variance analysis on the surface area of the tea leaves with the different grades, the significant difference p value is less than 0.05, and the tea leaves with the different grades are obviously different. A tea leaf grade predication model is established through a method for gradually and linearly judging. The novel method for identifying the tea leaf grades is provided for rapidly and accurately determining the surface area of the tea leaves with the different grades based on a scanning-image recognition technology.

Description

technical field [0001] The invention belongs to the technical field of agricultural product grade identification methods, in particular to a tea grade identification method based on image recognition technology. Background technique [0002] As one of the most popular beverages, tea has anti-oxidation, anti-cancer, anti-ultraviolet and other effects, and is welcomed by people. With the improvement of living standards, people have higher and higher requirements for the quality of tea. Tea grade is an important indicator of tea quality and sensory evaluation to judge the quality of tea. Traditionally, the evaluation of tea quality is mainly through the method of sensory evaluation, which requires professionals with rich knowledge of tea science and evaluation experience. Ordinary consumers have not received systematic review training and accumulated experience in tea tasting, so it is difficult to achieve reliable review results. For professional sensory evaluation experts,...

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): G01N21/84
Inventor 马桂岑鲁成银刘新刘平香张明露
Owner TEA RES INST CHINESE ACAD OF AGRI SCI
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