CN116309785A - Digitalized evaluation method for whole crushing degree of tea - Google Patents

Digitalized evaluation method for whole crushing degree of tea Download PDF

Info

Publication number
CN116309785A
CN116309785A CN202211094767.6A CN202211094767A CN116309785A CN 116309785 A CN116309785 A CN 116309785A CN 202211094767 A CN202211094767 A CN 202211094767A CN 116309785 A CN116309785 A CN 116309785A
Authority
CN
China
Prior art keywords
tea
whole
degree
crushing
sample
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202211094767.6A
Other languages
Chinese (zh)
Inventor
林杰
杨垚
施陈吉
卢思佳
王周立
钟玉
仝晨
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang A&F University ZAFU
Zhejiang Xinchang Chengtan Tea Factory
Original Assignee
Zhejiang A&F University ZAFU
Zhejiang Xinchang Chengtan Tea Factory
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Zhejiang A&F University ZAFU, Zhejiang Xinchang Chengtan Tea Factory filed Critical Zhejiang A&F University ZAFU
Priority to CN202211094767.6A priority Critical patent/CN116309785A/en
Publication of CN116309785A publication Critical patent/CN116309785A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/766—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using regression, e.g. by projecting features on hyperplanes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/7715—Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/68—Food, e.g. fruit or vegetables
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10004—Still image; Photographic image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30181—Earth observation
    • G06T2207/30188—Vegetation; Agriculture
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Geometry (AREA)
  • Tea And Coffee (AREA)

Abstract

The invention discloses a digital evaluation method of tea leaf whole crushing degree, which comprises the following steps: s1, constructing a whole-crushing degree discrimination model (LDA and logistic regression) of a measured tea sample; s2, collecting representative 50 pieces of dry tea samples at random at one time, and uniformly spreading the tea samples on a shadowless lamp to ensure that tea leaves are not overlapped with each other; s3, acquiring a tea sample image by using photographic equipment; s4, automatically identifying and directly measuring the length-width ratio of 50 tea leaves (quantified by pixels) by using a target identification algorithm
Figure DDA0003838404540000011
Area ratio AR, minimum included angle Ang min Relative area of
Figure DDA0003838404540000012
S5, grading the whole, still whole and broken tea leaves by using a whole breakage degree judging model; s6, obtaining the proportion of whole, still whole and broken tea leaves in the tea sample. The invention builds the whole crushing degree judging model, can quickly identify the whole crushing degree of each piece of tea in the picture, obtains the proportion of the whole tea, the whole tea and the crushed tea in the tea sample, and provides a reference basis for judging the quality of the tea.

Description

Digitalized evaluation method for whole crushing degree of tea
Technical Field
The invention relates to the technical field of tea index evaluation methods, in particular to a digital evaluation method for the whole crushing degree of tea.
Background
The whole crushing degree of tea refers to the uniformity and breaking degree of the appearance of the tea, is an important index of the appearance of the tea, and is different from the uniformity, the uniformity refers to the consistency of the appearance of the size of the tea, and the whole crushing degree refers to the integrity degree of the tea.
The existing evaluation method for the whole crushing degree of the tea leaves has the following defects:
1. the degree of overall crush depends on professionals and professional equipment and sites;
2. the evaluation of the comments is very subjective, can only be given macroscopically, and is not accurate enough.
3. The current evaluation is limited to a few comments such as whole, still whole, irregular, etc., and the grading is more general, the digital evaluation of the whole crushing degree is not realized, and the proportion of the whole tea, the still whole tea and the crushed tea in the tea sample cannot be given.
Therefore, a digital evaluation system of the whole tea crushing degree is established, the proportion of whole, still whole and crushed tea in the tea sample can be rapidly given, and a reference basis is provided for judging the quality of the tea.
Disclosure of Invention
The invention aims to provide a digital evaluation method for the whole tea crushing degree, which can quickly finish the digital evaluation work for the whole crushing degree of different leaf types of dry tea so as to solve the problems in the prior art.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a digital evaluation method for the whole crushing degree of tea comprises the following steps:
s1, constructing a whole-crushing degree discrimination model (LDA and logistic regression) of a measured tea sample;
s2, collecting representative 50 pieces of dry tea samples at random at one time, and uniformly spreading the tea samples on a shadowless lamp to ensure that tea leaves are not overlapped with each other;
s3, acquiring a tea sample image by using photographic equipment;
s4, automatically identifying and directly measuring the length-width ratio of 50 tea leaves (quantified by pixels) by using a target identification algorithm
Figure BDA0003838404520000021
Area ratio AR, minimum included angle Ang min Relative area->
Figure BDA0003838404520000022
S5, grading the whole, still whole and broken tea leaves by using a whole breakage degree judging model;
s6, obtaining the proportion of whole, still whole and broken tea leaves in the tea sample.
Preferably, the whole crushing degree discrimination model in the step S1 is constructed by adopting a similar aggregation segmentation algorithm according to the whole crushing degree grade of each piece of tea in the tea sample.
Preferably, accuracy testing is carried out on the whole breakage degree judging model, test data are divided into a training set and a test set (7:3), and judging accuracy of each obtained grading test set and total judging accuracy of the model are obtained.
Preferably, the total model discrimination accuracy of the test set model comprises:
the model total discrimination accuracy/(correct discrimination number/total number of tea leaves) of the test set model of the megalobrama (green tea) is 97.77 (307/314)%; the single-category discrimination accuracy/(correct discrimination number/total number of tea leaves) is respectively: the tea sample is whole: 97.48 (116/119)%, tea sample is still whole: 98.01 (148/151)%, tea sample was crushed: 97.72 (43/44)%;
the model total discrimination accuracy/(correct discrimination number/total number of tea leaves) of the test set model of assam (black tea) is 93.98 (390/415)%; the single-category discrimination accuracy/(correct discrimination number/total number of tea leaves) is respectively: the tea sample is whole: 94.00 (188/200)%, and the tea sample is still whole: 94.08 (143/152)%, tea sample is crushed: 93.65 (43/44)%.
Preferably, the "target recognition algorithm" in the step S4 includes using a code for displaying the pixel values in real time to obtain a section of the pixel values of the tea leaves; by using a connected domain method and a contour detection code, all target tea leaves are identified by adjusting the pixel values of perimeter, width and area, and the serial number S/N, the area S and the relative area of each tea leaf are read
Figure BDA0003838404520000031
Aspect ratio->
Figure BDA0003838404520000032
Minimum circumcircle area S MCC Ang at minimum angle min 。
Preferably, the aspect ratio
Figure BDA0003838404520000033
Aspect ratio of Minimum Bounding Rectangle (MBR); the area ratio AR:area/Minimum Circumscribed Circle (MCC) area;
said minimum included angle Ang min : the smallest internal angle of the external triangle;
the relative area
Figure BDA0003838404520000034
In a single picture, the sum of the areas of all tea leaves is 100%, and each tea leaf accounts for a percentage.
Preferably, the whole tea sample
Figure BDA0003838404520000035
Large value, small AR value, ang min Small value and (2)>
Figure BDA0003838404520000036
The value is large; broken tea samples are the opposite; the whole tea pattern is in the middle.
Preferably, the whole degree of crushing of each tea leaf is defined as "still whole" when the degree of crushing of the whole tea leaf reaches 40%, the degree of crushing being defined as "whole" when the degree of crushing is greater than 90%, and the degree of crushing being defined as "crushed" when the degree of crushing is less than 40%.
Preferably, the crushing degree of the tea sample is evaluated mainly by adopting a collective scoring method in a sensory evaluation method GB/T23776-2018, the whole evaluation process is completed by five tea evaluation operators, the crushing degree of tea leaves is evaluated firstly in the evaluation process, then the characteristics of the tea leaves evaluated by the main evaluation are modified and confirmed according to quality standards, the discussion is carried out on the tea leaves with larger viewpoint difference, and finally the whole crushing degree is determined jointly.
In summary, the beneficial effects of the invention are as follows due to the adoption of the technology:
1. the invention builds the whole crushing degree judging model, can rapidly identify the whole crushing degree of each piece of tea in the picture, and obtains the proportion of the whole, whole and crushed tea in the tea sample without depending on professional staff, professional equipment and places.
2. The discrimination model of the invention is based on the length-width ratio
Figure BDA0003838404520000041
Area ratio AR, minimum included angle Ang min Relative area->
Figure BDA0003838404520000042
The relative indexes are obtained, and the effects of the size, the placement angle and the like of the tea image are avoided;
3. the evaluation result is quantized microscopically, and is more accurate and visual.
Drawings
FIG. 1 is a flow chart of a digital evaluation method of the whole tea crushing degree;
FIG. 2 is a schematic diagram of the whole-crushing degree classification of tea leaves according to the invention;
FIG. 3 is a schematic diagram of sample analysis of the MBR measurement method of the present invention;
FIG. 4 is a schematic diagram of a sample analysis of the minimum circumscribed triangle measurement method of the present invention;
FIG. 5 is a schematic diagram illustrating a sample analysis of the MCC measurement method of the present invention;
FIG. 6 is a graph of a hierarchical model of a Buddha's Longjing tea (green tea) of the present invention;
FIG. 7 is a graph of a classification model of an assam black tea (black tea) of the present invention;
FIG. 8 is a sample of the Dafu longjing tea sample 1 of example 1 of the present invention;
FIG. 9 is a graph showing the evaluation results of the whole crushing degree of the Dafu longjing tea sample 1 in example 1 of the present invention;
FIG. 10 is a graph showing the sample of the Dafu longjing tea sample 2 in example 2 of the present invention;
FIG. 11 is a graph showing the evaluation results of the whole crushing degree of the Dafu longjing tea sample 2 in example 2 of the present invention;
FIG. 12 is a graph of an assam black tea sample 1 tea sample of example 3 of the present invention;
FIG. 13 is a graph showing the results of evaluation of whole crushing degree of assam black tea sample 1 tea sample in example 3 of the present invention;
FIG. 14 is a graph of an assam black tea sample 2 tea sample of example 4 of this invention;
FIG. 15 is a graph showing the results of evaluation of the whole crushing degree of the assam black tea-like 2 tea-like in example 4 of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, based on the embodiments of the invention, which are apparent to those of ordinary skill in the art without inventive faculty, are intended to be within the scope of the invention. Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, based on the embodiments of the invention, which are apparent to those of ordinary skill in the art without inventive faculty, are intended to be within the scope of the invention.
Example 1
The invention provides a digital evaluation method for the whole crushing degree of a megalobrama tea sample 1 shown in figures 1-15, which comprises the following steps:
s1, constructing a whole-crushing degree judging model (LDA and logistic regression) of the megalobrama;
s2, randomly taking a representative 53 pieces of dry tea samples 1 of the Dafu longjing tea, uniformly spreading the dry tea samples on white background cloth of a shadowless lamp, and enabling the tea leaves not to overlap with each other;
s3, shooting vertically from the top of the film studio by using photographic equipment, so that all tea leaves are in the photos and have no excessive blank;
s4, importing original pictures of the tea-like photos into a target recognition algorithm to automatically recognize and directly measure the aspect ratio of 53 tea leaves
Figure BDA0003838404520000061
Area ratio AR, minimum included angle Ang min Relative area->
Figure BDA0003838404520000062
Data;
s5, integrating the data into an Excel table, and grading the whole, still and broken tea leaves by using a whole breakage degree judging model;
s6, obtaining the proportion of whole, still whole and broken tea leaves in the tea sample.
Specifically, the whole crushing degree judging model in the step S1 is constructed by adopting a similar aggregation segmentation algorithm according to the whole crushing degree grade of each piece of tea in the tea sample.
Specifically, accuracy testing is carried out on the whole breakage degree judging model, test data are divided into a training set and a testing set (7:3), and the judging accuracy of each grading testing set and the total judging accuracy of the model are obtained.
Specifically, the total model discrimination accuracy of the test set model comprises the following steps according to different tea varieties: the model total discrimination accuracy/(correct discrimination number/total number of tea leaves) of the test set model of the megalobrama (green tea) is 97.77 (307/314)%; the single-category discrimination accuracy/(correct discrimination number/total number of tea leaves) is respectively: the tea sample is whole: 97.48 (116/119)%, tea sample is still whole: 98.01 (148/151)%, tea sample was crushed: 97.72 (43/44)%;
the model total discrimination accuracy/(correct discrimination number/total number of tea leaves) of the test set model of assam (black tea) is 93.98 (390/415)%; the single-category discrimination accuracy/(correct discrimination number/total number of tea leaves) is respectively: the tea sample is whole: 94.00 (188/200)%, and the tea sample is still whole: 94.08 (143/152)%, tea sample is crushed: 93.65 (43/44)%.
Specifically, the "target recognition algorithm" in the step S4 includes using a code for displaying the pixel values in real time to obtain a section of the pixel values of the tea leaves; by using a connected domain method and a contour detection code, all target tea leaves are identified by adjusting the pixel values of perimeter, width and area, and the serial number S/N, the area S and the relative area of each tea leaf are read
Figure BDA0003838404520000071
Aspect ratio->
Figure BDA0003838404520000072
Minimum circumcircle area S MCC Ang at minimum angle min 。
In particular, the aspect ratio
Figure BDA0003838404520000073
Aspect ratio of Minimum Bounding Rectangle (MBR);
the area ratio AR: area/Minimum Circumscribed Circle (MCC) area;
said minimum included angle Ang min : the smallest internal angle of the external triangle;
the relative area
Figure BDA0003838404520000074
In a single picture, the sum of the areas of all tea leaves is 100%, and each tea leaf accounts for a percentage.
In particular, the whole tea sample
Figure BDA0003838404520000081
Large value, small AR value, ang min Small value and (2)>
Figure BDA0003838404520000082
The value is large; broken tea samples are the opposite; the whole tea pattern is in the middle.
Specifically, the whole degree of crushing of each tea leaf is defined as "still whole" when the degree of crushing of the whole tea leaf reaches 40%, the degree of crushing is defined as "whole" when the degree of crushing is more than 90%, and the degree of crushing is defined as "crushing" when the degree of crushing is less than 40%.
Specifically, the crushing degree of the tea sample is evaluated mainly by adopting a collective scoring method in a sensory evaluation method GB/T23776-2018, the crushing degree of tea leaves is evaluated firstly in the evaluation process, then the characteristics of the tea leaves evaluated mainly are modified and confirmed according to quality standards, the discussion is carried out on the tea leaves with larger viewpoint differences, and finally the whole crushing degree is determined jointly.
It should be noted that the whole evaluation process is completed by five tea evaluation operators together, the personnel participating in the evaluation form an evaluation group, one of the personnel is recommended to evaluate the crushing degree of the tea leaves by the main evaluation in the evaluation process, other personnel modify and confirm the characteristics of the tea leaves evaluated by the main evaluation according to the quality standard, discuss the tea leaves with larger viewpoint difference, finally jointly determine the whole crushing degree, if disputed, vote decision, and add comments, and the comments refer to the terms in GB/T14487.
Example 2
Unlike example 1, the whole-crushing degree of the megalin-like tea sample 2 used in example 2 was different, and the method for digitally evaluating the whole-crushing degree thereof comprises the steps of:
s1, constructing a whole-crushing degree judging model (LDA and logistic regression) of the megalobrama;
s2, randomly taking a representative 51 pieces of dry tea samples 2 of the megalobrama dry tea, uniformly spreading the samples on white background cloth of the shadowless lamp, and enabling the tea leaves not to overlap with each other;
s3, shooting vertically from the top of the film studio by using photographic equipment, so that all tea leaves are in the photos and have no excessive blank;
s4, importing original pictures of the tea-like photos into a target recognition algorithm to automatically recognize and directly measure the aspect ratio of 51 tea leaves
Figure BDA0003838404520000091
Area ratio AR, minimum included angle Ang min Relative area->
Figure BDA0003838404520000092
Data;
s5, integrating the data into an Excel table, and grading the whole, still and broken tea leaves by using a whole breakage degree judging model;
s6, obtaining the proportion of whole, still whole and broken tea leaves in the tea sample.
Example 3
Unlike example 1, the tea sample used in example 3 was assam black tea sample 1, and the method for digitally evaluating the whole crushing degree thereof comprises the following steps:
s1, constructing a whole-crushing degree discrimination model (adopting LDA and logistic regression) of the assam black tea;
s2, randomly taking a representative 50-piece assam black tea dry tea sample 1, uniformly spreading the sample on white background cloth of a shadowless lamp, and enabling tea leaves not to overlap with each other;
s3, shooting vertically from the top of the film studio by using photographic equipment, so that all tea leaves are in the photos and have no excessive blank;
s4, importing original pictures of the tea-like photos into a target recognition algorithm to automatically recognize and directly measure the length-width ratio of 50 pieces of tea leaves
Figure BDA0003838404520000101
Area ratio AR, minimum included angle Ang m i n Relative area->
Figure BDA0003838404520000102
Data;
s5, integrating the data into an Excel table, and grading the whole, still and broken tea leaves by using a whole breakage degree judging model;
s6, obtaining the proportion of whole, still whole and broken tea leaves in the tea sample.
Example 4
Unlike example 1, the tea sample used in example 4 was assam black tea sample 2; unlike example 3, the whole-crushing degree of the assam black tea sample 2 used in example 4 was different, and the method for digitally evaluating the whole-crushing degree thereof comprises the following steps:
s1, constructing a whole-crushing degree discrimination model (adopting LDA and logistic regression) of the assam black tea;
s2, randomly taking a representative 50-piece assam black tea dry tea sample 2, uniformly spreading the sample on white background cloth of a shadowless lamp, and enabling tea leaves not to overlap with each other;
s3, shooting vertically from the top of the film studio by using photographic equipment, so that all tea leaves are in the photos and have no excessive blank;
s4, importing original pictures of the tea-like photos into a target recognition algorithm to automatically recognize and directly measure the length-width ratio of 50 pieces of tea leaves
Figure BDA0003838404520000103
Area ratio AR, minimum included angle Ang min Relative area->
Figure BDA0003838404520000104
Data;
s5, integrating the data into an Excel table, and grading the whole, still and broken tea leaves by using a whole breakage degree judging model;
s6, obtaining the proportion of whole, still whole and broken tea leaves in the tea sample.
The foregoing is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art, who is within the scope of the present invention, should make equivalent substitutions or modifications according to the technical scheme of the present invention and the inventive concept thereof, and should be covered by the scope of the present invention.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.

Claims (9)

1. A digital evaluation method for the whole crushing degree of tea is characterized by comprising the following steps:
s1, constructing a whole-crushing degree discrimination model (LDA and logistic regression) of a measured tea sample;
s2, collecting representative 50 pieces of dry tea samples at random at one time, and uniformly spreading the tea samples on a shadowless lamp to ensure that tea leaves are not overlapped with each other;
s3, acquiring a tea sample image by using photographic equipment;
s4, automatically identifying and directly measuring the length-width ratio of 50 tea leaves (quantified by pixels) by using a target identification algorithm
Figure FDA0003838404510000011
Area ratio AR, minimum included angle Ang min Relative area->
Figure FDA0003838404510000012
S5, grading the whole, still whole and broken tea leaves by using a whole breakage degree judging model;
s6, obtaining the proportion of whole, still whole and broken tea leaves in the tea sample.
2. The method for digitally evaluating the whole leaf crushing degree of tea according to claim 1, wherein the method comprises the following steps: the whole crushing degree judging model in the step S1 is constructed by adopting a similar aggregation segmentation algorithm according to the whole crushing degree grade of each piece of tea in the tea sample.
3. The method for digitally evaluating the whole leaf crushing degree of tea according to claim 1, wherein the method comprises the following steps: and (3) performing accuracy test on the whole breakage degree judging model, and dividing test data into a training set and a testing set (7:3), wherein the judging accuracy of each grading testing set and the total judging accuracy of the model are obtained.
4. A method for digitally evaluating the friability of tea leaves as claimed in claim 3, wherein: the total model discrimination accuracy of the test set model comprises the following steps according to different tea varieties: the model total discrimination accuracy/(correct discrimination number/total number of tea leaves) of the test set model of the megalobrama (green tea) is 97.77 (307/314)%; the single-category discrimination accuracy/(correct discrimination number/total number of tea leaves) is respectively: the tea sample is whole: 97.48 (116/119)%, tea sample is still whole: 98.01 (148/151)%, tea sample was crushed: 97.72 (43/44)%;
the model total discrimination accuracy/(correct discrimination number/total number of tea leaves) of the test set model of assam (black tea) is 93.98 (390/415)%; the single-category discrimination accuracy/(correct discrimination number/total number of tea leaves) is respectively: the tea sample is whole: 94.00 (188/200)%, and the tea sample is still whole: 94.08 (143/152)%, tea sample is crushed: 93.65 (43/44)%.
5. The method for digitally evaluating the whole leaf crushing degree of tea according to claim 1, wherein the method comprises the following steps: the target recognition algorithm in the step S4 comprises the steps of obtaining a section of the pixel point values of the tea leaves by using codes for displaying the pixel point values in real time; by using a connected domain method and a contour detection code, all target tea leaves are identified by adjusting the pixel values of perimeter, width and area, and the serial number S/N, the area S and the relative area of each tea leaf are read
Figure FDA0003838404510000021
Aspect ratio->
Figure FDA0003838404510000022
Minimum circumcircle area S MCC Ang at minimum angle min 。
6. The method for digitally evaluating the whole leaf crushing degree of tea according to claim 1, wherein the method comprises the following steps: the aspect ratio
Figure FDA0003838404510000023
Aspect ratio of Minimum Bounding Rectangle (MBR);
the area ratio AR: area/Minimum Circumscribed Circle (MCC) area;
said minimum included angle Ang min : the smallest internal angle of the external triangle;
the relative area
Figure FDA0003838404510000024
In a single picture, the sum of the areas of all tea leaves is 100%, and each tea leaf accounts for a percentage.
7. The method for digitally evaluating the whole leaf crushing degree of tea according to claim 1, wherein the method comprises the following steps: whole of the tea sample
Figure FDA0003838404510000031
Large value, small AR value, ang min Small value and (2)>
Figure FDA0003838404510000032
The value is large; broken tea samples are the opposite; the whole tea pattern is in the middle.
8. The method for digitally evaluating the whole leaf crushing degree of tea according to claim 1, wherein the method comprises the following steps: the whole degree of crushing grade of each tea leaf is defined as 'still whole' when the degree of crushing of the whole tea sample reaches 40%, the degree of crushing is defined as 'whole' when the degree of crushing is more than 90%, and the degree of crushing is defined as 'crushing' when the degree of crushing is less than 40%.
9. The method for digitally evaluating the whole leaf crushing degree of tea according to claim 1, wherein the method comprises the following steps: the tea sample crushing degree is evaluated mainly by adopting a collective scoring method in a sensory evaluation method GB/T23776-2018, the whole evaluation process is completed by five tea evaluation operators, the crushing degree of tea leaves is evaluated firstly in the evaluation process, then the characteristics of the tea leaves evaluated by a main evaluation are modified and confirmed according to quality standards, the discussion is carried out on the tea leaves with larger viewpoint difference, and finally the whole crushing degree is determined jointly.
CN202211094767.6A 2022-09-08 2022-09-08 Digitalized evaluation method for whole crushing degree of tea Pending CN116309785A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211094767.6A CN116309785A (en) 2022-09-08 2022-09-08 Digitalized evaluation method for whole crushing degree of tea

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211094767.6A CN116309785A (en) 2022-09-08 2022-09-08 Digitalized evaluation method for whole crushing degree of tea

Publications (1)

Publication Number Publication Date
CN116309785A true CN116309785A (en) 2023-06-23

Family

ID=86831050

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211094767.6A Pending CN116309785A (en) 2022-09-08 2022-09-08 Digitalized evaluation method for whole crushing degree of tea

Country Status (1)

Country Link
CN (1) CN116309785A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117593652A (en) * 2024-01-18 2024-02-23 之江实验室 Method and system for intelligently identifying soybean leaf shape
CN117593652B (en) * 2024-01-18 2024-05-14 之江实验室 Method and system for intelligently identifying soybean leaf shape

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117593652A (en) * 2024-01-18 2024-02-23 之江实验室 Method and system for intelligently identifying soybean leaf shape
CN117593652B (en) * 2024-01-18 2024-05-14 之江实验室 Method and system for intelligently identifying soybean leaf shape

Similar Documents

Publication Publication Date Title
US10942933B2 (en) Computerized technical authentication and grading system for collectible objects
WO2022042579A1 (en) Lcd screen defect detection method and apparatus
US10445330B2 (en) Computerized technical authentication and grading system for collectible objects
CN110210448B (en) Intelligent face skin aging degree identification and evaluation method
CN108074231A (en) A kind of magnetic sheet detection method of surface flaw based on convolutional neural networks
CN108304880A (en) A kind of building site sample witness sampling method based on image tagged
CN102404602A (en) Vidicon definition detection method based on definition test card
US20220374946A1 (en) Computerized technical authentication and grading system for collectible objects
CN106461373A (en) Real-time digitally enhanced imaging for the prediction, application, and inspection of coatings
CN111879735B (en) Rice appearance quality detection method based on image
Chen et al. Evaluating fabric pilling with light-projected image analysis
KR20180023847A (en) Method for Evaluating the Authenticity of a Painting as well as a Corresponding Use
Triantoro et al. Image based water gauge reading developed with ANN Kohonen
CN110321944A (en) A kind of construction method of the deep neural network model based on contact net image quality evaluation
CN116309785A (en) Digitalized evaluation method for whole crushing degree of tea
CN116309564B (en) Method and system for detecting appearance defects of battery cells based on artificial intelligent image recognition
CN116958960A (en) Egg dark spot detection method based on machine learning random forest algorithm
CN115546536A (en) Ivory product identification method and system
CN110174487A (en) A kind of phoenix list fir discrimination method based on high-efficiency liquid-phase fingerprint and discriminant analysis
US20230222641A1 (en) Method and apparatus for identifying characteristics of trading cards
Tochor et al. Automated egg-counting approaches for Aedes aegypti oviposition experiments
Radopoulou et al. Detection of multiple road defects for pavement condition assessment
JP3909483B2 (en) Method for creating standard image for coating film defect evaluation, recording medium recording the program, and recording medium recording the created standard image
CN111523605A (en) Image identification method and device, electronic equipment and medium
CN115493519A (en) Digital evaluation method for tea rope grade

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination