CN113763319B - Tea leaf strip forming rate detection method and device and computer readable storage medium - Google Patents
Tea leaf strip forming rate detection method and device and computer readable storage medium Download PDFInfo
- Publication number
- CN113763319B CN113763319B CN202110650727.4A CN202110650727A CN113763319B CN 113763319 B CN113763319 B CN 113763319B CN 202110650727 A CN202110650727 A CN 202110650727A CN 113763319 B CN113763319 B CN 113763319B
- Authority
- CN
- China
- Prior art keywords
- tea
- morphological
- detected
- strip
- discrimination coefficient
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 110
- 238000003860 storage Methods 0.000 title claims abstract description 14
- 241001122767 Theaceae Species 0.000 claims abstract description 394
- 230000000877 morphologic effect Effects 0.000 claims abstract description 237
- 238000005070 sampling Methods 0.000 claims abstract description 82
- 238000005096 rolling process Methods 0.000 claims abstract description 52
- 230000006870 function Effects 0.000 claims description 74
- 238000012937 correction Methods 0.000 claims description 60
- 238000000034 method Methods 0.000 claims description 37
- 238000012545 processing Methods 0.000 claims description 11
- 230000015572 biosynthetic process Effects 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 abstract description 9
- 238000004891 communication Methods 0.000 description 6
- 235000009024 Ceanothus sanguineus Nutrition 0.000 description 2
- 240000003553 Leptospermum scoparium Species 0.000 description 2
- 235000015459 Lycium barbarum Nutrition 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000796 flavoring agent Substances 0.000 description 2
- 235000019634 flavors Nutrition 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 238000012797 qualification Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 235000016299 Canarium odontophyllum Nutrition 0.000 description 1
- 244000001582 Canarium odontophyllum Species 0.000 description 1
- 241000037488 Coccoloba pubescens Species 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2431—Multiple classes
-
- 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
-
- 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
Abstract
The invention discloses a tea leaf strip forming rate detection method, which comprises the following steps: obtaining M x N strip forming rates of M tea leaves at N sampling points, and obtaining M x N morphological pictures of M tea leaves at N sampling points; constructing a strip rate detection model according to the M x N strip rates and the M x N morphological pictures; acquiring a to-be-detected morphological picture of tea leaves to be detected and a first strip forming rate of a first sampling point of the tea leaves to be detected; inputting the to-be-detected morphological picture and the first strip forming rate into the strip forming rate detection model to obtain the detection strip forming rate of the tea to be detected. The invention also discloses a tea leaf strip rate detection device and a computer readable storage medium. The invention can reduce the detection time of the tea leaf forming rate, improve the tea leaf forming rate detection efficiency, improve the tea leaf production efficiency, realize automatic judgment of the tea leaf forming rate, and further realize rapid judgment of the rolling degree of the tea leaf.
Description
Technical Field
The invention relates to the technical field of tea production and processing, in particular to a tea forming rate detection, a rolling qualification judging method, a rolling qualification judging device and a computer readable storage medium.
Background
At present, rolling is an important process in the tea processing process. Proper rolling not only shapes good tea leaves, but also improves the flavor quality of the tea leaves. In general, the degree of tea rolling is mainly determined by the tea rolling percentage, and when the tea rolling percentage reaches 85%, the degree is regarded as moderate rolling. The method for calculating the tea forming rate comprises the steps of taking out a certain weight of rolled leaf sample, manually selecting the formed leaves, and calculating the weight ratio of the formed leaves to obtain the forming rate, wherein the existing method for calculating the forming rate is generally carried out by adopting a manual counting method, and the forming rate of the tea and the time and labor consumption for judging the rolling degree of the tea are determined by adopting a manual detection method.
Disclosure of Invention
The invention mainly aims to provide a tea rolling degree judging method, a device and a computer readable storage medium, which aim to reduce the detection time of tea rolling degree, improve the detection efficiency of the tea rolling degree, improve the production efficiency of tea, realize automatic judgment of the tea rolling degree and realize quick judgment of the tea rolling degree.
In order to achieve the above object, the present invention provides a tea leaf rolling degree judging method, comprising the steps of:
obtaining M x N strip forming rates of M tea leaves at N sampling points, and obtaining M x N morphological pictures of M tea leaves at N sampling points;
constructing a strip rate detection model according to the M x N strip rates and the M x N morphological pictures;
acquiring a to-be-detected morphological picture of tea leaves to be detected and a first strip forming rate of a first sampling point of the tea leaves to be detected;
inputting the to-be-detected morphological picture and the first strip forming rate into the strip forming rate detection model to obtain the detection strip forming rate of the tea to be detected.
Optionally, the step of constructing a strip rate detection model according to m×n strip rates and m×n morphological pictures includes:
determining a first discrimination coefficient, a second discrimination coefficient, a third discrimination coefficient, a fourth discrimination coefficient and a fifth discrimination coefficient corresponding to the first to M-th tea leaves according to the M x N strip forming rates and the M x N morphological pictures;
determining a first correction function according to the first discrimination coefficients corresponding to the first to M-th tea leaves and the strip forming rate corresponding to the first time sampling points of the first to M-th tea leaves;
Determining a second correction function according to the second discrimination coefficients corresponding to the first to M-th tea leaves and the strip forming rate corresponding to the first time sampling points of the first to M-th tea leaves;
and the like, determining a fifth correction function according to the fifth discrimination coefficients corresponding to the first tea leaves to the M tea leaves and the strip forming rate corresponding to the first time sampling point of the first tea leaves to the M tea leaves.
Optionally, the step of determining the first discrimination coefficient, the second discrimination coefficient, the third discrimination coefficient, the fourth discrimination coefficient and the fifth discrimination coefficient corresponding to the first to the mth tea according to the m×n strip forming rates and the m×n morphological pictures includes:
determining m×n first morphology feature values, m×n second morphology feature values, m×n third morphology feature values and m×n fourth morphology feature values according to m×n morphology pictures;
determining a first discrimination coefficient, a second discrimination coefficient, a third discrimination coefficient, a fourth discrimination coefficient and a fifth discrimination coefficient corresponding to the first tea according to N first morphological feature values, N second morphological feature values, N third morphological feature values, N fourth morphological feature values and N banding rates corresponding to the first tea, wherein N is more than or equal to 5;
Determining a first discrimination coefficient, a second discrimination coefficient, a third discrimination coefficient, a fourth discrimination coefficient and a fifth discrimination coefficient corresponding to the second tea according to N first morphological feature values, N second morphological feature values, N third morphological feature values, N fourth morphological feature values and N stripe forming rates corresponding to the second tea;
and by analogy, determining a first discrimination coefficient, a second discrimination coefficient, a third discrimination coefficient, a fourth discrimination coefficient and a fifth discrimination coefficient corresponding to the M-th tea according to the N first morphological feature values, the N second morphological feature values, the N third morphological feature values, the N fourth morphological feature values and the N banding rates corresponding to the M-th tea.
Optionally, the step of determining m×n first morphology feature values, m×n second morphology feature values, m×n third morphology feature values, and m×n fourth morphology feature values according to m×n morphology pictures includes:
and processing the M.N morphological pictures based on a tea profile analysis program to obtain M.N first morphological feature values, M.N second morphological feature values, M.N third morphological feature values and M.N fourth morphological feature values.
Optionally, the step of inputting the to-be-detected morphological image and the first strip forming rate into the strip forming rate detection model to obtain the detection strip forming rate of the to-be-detected tea includes:
inputting the first strip forming rate into the first correction function, the second correction function, the third correction function, the fourth correction function and the fifth correction function respectively to obtain a first discrimination coefficient, a second discrimination coefficient, a third discrimination coefficient, a fourth discrimination coefficient and a fifth discrimination coefficient corresponding to tea leaves to be detected;
determining a first morphological characteristic value, a second morphological characteristic value, a third morphological characteristic value and a fourth morphological characteristic value corresponding to the tea to be detected according to the morphological picture to be detected;
and calculating the detection strip rate of the tea to be detected according to the first discrimination coefficient, the second discrimination coefficient, the third discrimination coefficient, the fourth discrimination coefficient and the fifth discrimination coefficient corresponding to the tea to be detected, and the first morphological characteristic value, the second morphological characteristic value, the third morphological characteristic value and the fourth morphological characteristic value corresponding to the tea to be detected.
Optionally, the step of determining the first morphological feature value, the second morphological feature value, the third morphological feature value and the fourth morphological feature value corresponding to the tea to be detected according to the morphological picture to be detected includes:
And processing the to-be-detected morphological picture based on a tea appearance analysis program to obtain a first morphological characteristic value, a second morphological characteristic value, a third morphological characteristic value and a fourth morphological characteristic value which correspond to the to-be-detected tea.
Optionally, after the step of inputting the to-be-detected morphological image and the first strip forming rate into the strip forming rate detection model to obtain the detection strip forming rate of the tea to be detected, the method includes:
detecting whether the detected banding rate is greater than or equal to a banding rate threshold;
and if the detected strip forming rate is greater than or equal to a strip forming rate threshold, judging that the tea to be detected is qualified in rolling.
Optionally, after the step of detecting whether the detected banding rate is greater than or equal to a banding rate threshold, the step of detecting comprises:
if the detected strip forming rate is smaller than the Yu Chengtiao rate threshold, judging that the tea to be detected is unqualified in rolling, and continuing rolling the tea to be detected.
In addition, in order to achieve the above object, the present invention also provides a tea leaf strip rate detection device, comprising: the tea leaf strip rate detection device comprises a memory, a processor and a tea leaf strip rate detection program which is stored in the memory and can run on the processor, wherein the tea leaf strip rate detection program realizes the steps of the tea leaf strip rate detection method when being executed by the processor.
In addition, in order to achieve the above object, the present invention also provides a computer-readable storage medium having stored thereon a tea leaf strip rate detection program which, when executed by a processor, implements the steps of the tea leaf strip rate detection method as described above.
The invention provides a tea leaf strip rate detection method, a device and a computer readable storage medium, which are used for obtaining M strip rates of M tea leaves at N sampling points and obtaining M morphological pictures of M tea leaves at N sampling points; constructing a strip rate detection model according to the M x N strip rates and the M x N morphological pictures; acquiring a to-be-detected morphological picture of tea leaves to be detected and a first strip forming rate of a first sampling point of the tea leaves to be detected; inputting the to-be-detected morphological picture and the first strip forming rate into the strip forming rate detection model to obtain the detection strip forming rate of the tea to be detected. Through the mode, the tea leaf rolling machine can reduce the detection time of the tea leaf rolling rate, improve the tea leaf rolling rate detection efficiency, improve the tea leaf production efficiency, automatically judge the tea leaf rolling rate, and further rapidly judge the rolling degree of the tea leaves.
Drawings
FIG. 1 is a schematic diagram of a terminal structure of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a first embodiment of a tea leaf strip rate detection method of the present invention;
FIG. 3 is a schematic flow chart of a second embodiment of the tea leaf strip rate detection method of the present invention;
fig. 4 is a schematic flow chart of a third embodiment of the tea leaf strip rate detection method of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The main solutions of the embodiments of the present invention are: obtaining M x N strip forming rates of M tea leaves at N sampling points, and obtaining M x N morphological pictures of M tea leaves at N sampling points; constructing a strip rate detection model according to the M x N strip rates and the M x N morphological pictures; acquiring a to-be-detected morphological picture of tea leaves to be detected and a first strip forming rate of a first sampling point of the tea leaves to be detected; inputting the to-be-detected morphological picture and the first strip forming rate into the strip forming rate detection model to obtain the detection strip forming rate of the tea to be detected.
The prior rolling is an important procedure in the tea processing process. Proper rolling not only shapes good tea leaves, but also improves the flavor quality of the tea leaves. In general, the degree of tea rolling is mainly determined by the tea rolling percentage, and when the tea rolling percentage reaches 85%, the degree is regarded as moderate rolling. The method for calculating the tea forming rate comprises the steps of taking out a certain weight of rolled leaf sample, manually selecting the formed leaves, and calculating the weight ratio of the formed leaves to obtain the forming rate, wherein the existing method for calculating the forming rate is generally carried out by adopting a manual counting method, and the forming rate of the tea and the time and labor consumption for judging the rolling degree of the tea are determined by adopting a manual detection method.
The invention aims to reduce the detection time of the tea leaf forming rate, improve the tea leaf forming rate detection efficiency, improve the tea leaf production efficiency, realize automatic judgment of the tea leaf forming rate and realize quick judgment of the tea leaf rolling degree.
As shown in fig. 1, fig. 1 is a schematic diagram of a terminal structure of a hardware running environment according to an embodiment of the present invention.
The terminal of the embodiment of the invention can be a PC, or can be mobile terminal equipment with a display function, such as a smart phone, a tablet personal computer and the like.
As shown in fig. 1, the terminal may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
Preferably, the terminal may further include a camera, an RF (Radio Frequency) circuit, a sensor, an audio circuit, a WiFi module, and the like. Among other sensors, such as light sensors, motion sensors, and other sensors. Specifically, the light sensor may include an ambient light sensor that may adjust the brightness of the display screen according to the brightness of ambient light, and a proximity sensor that may turn off the display screen and/or the backlight when the mobile terminal moves to the ear. As one of the motion sensors, the gravity acceleration sensor can detect the acceleration in all directions (generally three axes), and can detect the gravity and the direction when the mobile terminal is stationary, and the mobile terminal can be used for recognizing the gesture of the mobile terminal (such as horizontal and vertical screen switching, related games, magnetometer gesture calibration), vibration recognition related functions (such as pedometer and knocking), and the like; of course, the mobile terminal may also be configured with other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, an infrared sensor, and the like, which are not described herein.
It will be appreciated by those skilled in the art that the terminal structure shown in fig. 1 is not limiting of the terminal and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and a tea leaf strip rate detection program may be included in a memory 1005, which is a computer-readable storage medium.
In the terminal shown in fig. 1, the network interface 1004 is mainly used for connecting to a background server and performing data communication with the background server; the user interface 1003 is mainly used for connecting a client (user side) and performing data communication with the client; and the processor 1001 may be configured to call a tea leaf strip rate detection program stored in the memory 1005 and perform the following operations:
obtaining M x N strip forming rates of M tea leaves at N sampling points, and obtaining M x N morphological pictures of M tea leaves at N sampling points;
constructing a strip rate detection model according to the M x N strip rates and the M x N morphological pictures;
acquiring a to-be-detected morphological picture of tea leaves to be detected and a first strip forming rate of a first sampling point of the tea leaves to be detected;
inputting the to-be-detected morphological picture and the first strip forming rate into the strip forming rate detection model to obtain the detection strip forming rate of the tea to be detected.
Further, the processor 1001 may call the tea leaf strip rate detection program stored in the memory 1005, and further perform the following operations:
determining a first discrimination coefficient, a second discrimination coefficient, a third discrimination coefficient, a fourth discrimination coefficient and a fifth discrimination coefficient corresponding to the first to M-th tea leaves according to the M x N strip forming rates and the M x N morphological pictures;
determining a first correction function according to the first discrimination coefficients corresponding to the first to M-th tea leaves and the strip forming rate corresponding to the first time sampling points of the first to M-th tea leaves;
determining a second correction function according to the second discrimination coefficients corresponding to the first to M-th tea leaves and the strip forming rate corresponding to the first time sampling points of the first to M-th tea leaves;
and the like, determining a fifth correction function according to the fifth discrimination coefficients corresponding to the first tea leaves to the M tea leaves and the strip forming rate corresponding to the first time sampling point of the first tea leaves to the M tea leaves.
Further, the processor 1001 may call the tea leaf strip rate detection program stored in the memory 1005, and further perform the following operations:
determining m×n first morphology feature values, m×n second morphology feature values, m×n third morphology feature values and m×n fourth morphology feature values according to m×n morphology pictures;
Determining a first discrimination coefficient, a second discrimination coefficient, a third discrimination coefficient, a fourth discrimination coefficient and a fifth discrimination coefficient corresponding to the first tea according to N first morphological feature values, N second morphological feature values, N third morphological feature values, N fourth morphological feature values and N banding rates corresponding to the first tea, wherein N is more than or equal to 5;
determining a first discrimination coefficient, a second discrimination coefficient, a third discrimination coefficient, a fourth discrimination coefficient and a fifth discrimination coefficient corresponding to the second tea according to N first morphological feature values, N second morphological feature values, N third morphological feature values, N fourth morphological feature values and N stripe forming rates corresponding to the second tea;
and by analogy, determining a first discrimination coefficient, a second discrimination coefficient, a third discrimination coefficient, a fourth discrimination coefficient and a fifth discrimination coefficient corresponding to the M-th tea according to the N first morphological feature values, the N second morphological feature values, the N third morphological feature values, the N fourth morphological feature values and the N banding rates corresponding to the M-th tea.
Further, the processor 1001 may call the tea leaf strip rate detection program stored in the memory 1005, and further perform the following operations:
And processing the M.N morphological pictures based on a tea profile analysis program to obtain M.N first morphological feature values, M.N second morphological feature values, M.N third morphological feature values and M.N fourth morphological feature values.
Further, the processor 1001 may call the tea leaf strip rate detection program stored in the memory 1005, and further perform the following operations:
inputting the first strip forming rate into the first correction function, the second correction function, the third correction function, the fourth correction function and the fifth correction function respectively to obtain a first discrimination coefficient, a second discrimination coefficient, a third discrimination coefficient, a fourth discrimination coefficient and a fifth discrimination coefficient corresponding to tea leaves to be detected;
determining a first morphological characteristic value, a second morphological characteristic value, a third morphological characteristic value and a fourth morphological characteristic value corresponding to the tea to be detected according to the morphological picture to be detected;
and calculating the detection strip rate of the tea to be detected according to the first discrimination coefficient, the second discrimination coefficient, the third discrimination coefficient, the fourth discrimination coefficient and the fifth discrimination coefficient corresponding to the tea to be detected, and the first morphological characteristic value, the second morphological characteristic value, the third morphological characteristic value and the fourth morphological characteristic value corresponding to the tea to be detected.
Further, the processor 1001 may call the tea leaf strip rate detection program stored in the memory 1005, and further perform the following operations:
and processing the to-be-detected morphological picture based on a tea appearance analysis program to obtain a first morphological characteristic value, a second morphological characteristic value, a third morphological characteristic value and a fourth morphological characteristic value which correspond to the to-be-detected tea.
Further, the processor 1001 may call the tea leaf strip rate detection program stored in the memory 1005, and further perform the following operations:
detecting whether the detected banding rate is greater than or equal to a banding rate threshold;
and if the detected strip forming rate is greater than or equal to a strip forming rate threshold, judging that the tea to be detected is qualified in rolling.
Further, the processor 1001 may call the tea leaf strip rate detection program stored in the memory 1005, and further perform the following operations:
if the detected strip forming rate is smaller than the Yu Chengtiao rate threshold, judging that the tea to be detected is unqualified in rolling, and continuing rolling the tea to be detected.
Based on the hardware structure, the embodiment of the tea leaf strip rate detection method is provided.
The invention relates to a tea leaf strip rate detection method.
Referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of the tea leaf strip rate detection method of the present invention.
In the embodiment of the invention, the tea strip rate detection method is applied to a tea strip rate detection device, and comprises the following steps:
step S10, obtaining M x N strip forming rates of M tea leaves at N sampling points, and obtaining M x N morphological pictures of M tea leaves at N sampling points;
in this embodiment, in order to reduce the detection time of the tea leaf forming rate, improve the tea leaf forming rate detection efficiency, improve the tea leaf production efficiency, realize automatic judgment of the tea leaf forming rate, further realize quick judgment of the rolling degree of the tea leaf, the staff count M x N forming rates of M tea leaves at N sampling points, and input M x N forming rates of M tea leaves at N sampling points into the tea leaf forming rate detection device; the method comprises the steps that a worker takes out M tea leaves at N sampling points, takes morphology pictures of the M tea leaves at the N sampling points through a CCD camera, sends the morphology pictures of the M tea leaves at the N sampling points to a tea leaf strip forming rate detection device, and the tea leaf strip forming rate detection device obtains M x N strip forming rates of the M tea leaves at the N sampling points; the sampling points are sampling time points of selecting tea leaves at preset time intervals in the rolling process. The preset time may be 5 minutes. The rate of slivering before the start of rolling was 0, and 1 sampling point was set at 5min intervals after the start of rolling, at which time the rate of slivering gradually increased over time. Wherein, the morphological picture is a picture of the shape and state of the tea after being spread and stretched. The tea leaves can be selected from the group consisting of dove pits, longjing 43, fuding Dabai. The tea tree varieties A1, A2 and Am take the leaf sizes as classification basis, and the tea tree is classified into large leaf varieties and medium and small leaf varieties according to the leaf sizes.
Step S20, constructing a strip rate detection model according to M x N strip rates and M x N morphological pictures;
in this embodiment, the tea leaf strip rate detection device acquires m×n strip rates of M tea leaves at N sampling points, and acquires m×n morphological pictures of M tea leaves at N sampling points; the tea strip forming rate detection device constructs a strip rate detection model according to M x N forming rates and M x N morphological pictures.
Step S30, obtaining a to-be-detected morphological picture of tea leaves to be detected and a first strip forming rate of a first sampling point of the tea leaves to be detected;
in this embodiment, after the device for detecting She Chengtiao rate completes the construction of the strip forming rate detection model, the staff counts the first strip forming rate of the tea to be detected at the first sampling point, and inputs the first strip forming rate of the tea to be detected at the first sampling point into the device for detecting the strip forming rate of the tea; the method comprises the steps that a worker takes out tea leaves of the tea leaves to be detected at a first sampling point, takes a morphological picture of the tea leaves to be detected at the first sampling point through a CCD camera, and sends the morphological picture of the tea leaves to be detected at the first sampling point to a tea leaf strip forming rate detection device; the method comprises the steps that a tea forming rate detection device obtains a to-be-detected morphological picture of tea to be detected and a first forming rate of a first sampling point of the tea to be detected; the first sampling point is a sampling point 5min after the rolling starts.
And S40, inputting the to-be-detected morphological picture and the first strip forming rate into the strip forming rate detection model to obtain the detection strip forming rate of the tea to be detected.
In this embodiment, after obtaining a to-be-detected form image of tea leaves to be detected and obtaining a first strip forming rate of a first sampling point of the tea leaves to be detected, the She Chengtiao rate detection device inputs the to-be-detected form image and the first strip forming rate into the strip forming rate detection model to obtain a detection strip forming rate of the tea leaves to be detected. And further determining the rolling degree of the tea according to the detection strip forming rate of the tea to be detected.
Step S40, inputting the to-be-detected morphological picture and the first strip forming rate into the strip forming rate detection model to obtain a detection strip forming rate of the to-be-detected tea, may include:
step a1, detecting whether the detected banding rate is greater than or equal to a banding rate threshold;
in this embodiment, the She Chengtiao rate detecting means detects whether the detected strip rate is greater than or equal to a strip rate threshold after determining the detected strip rate of the tea leaves to be detected. Wherein the banding threshold may be 85%.
And a2, judging that the tea to be detected is qualified in rolling if the detected strip forming rate is greater than or equal to a strip forming rate threshold.
In this embodiment, when the She Chengtiao rate detecting device determines that the detected band forming rate is greater than or equal to the band forming rate threshold, the tea leaves to be detected are qualified for rolling.
After detecting whether the detected banding rate is greater than or equal to the banding rate threshold in step a1, it may include:
and b, if the detected strip rate is smaller than the Yu Chengtiao rate threshold, judging that the tea to be detected is unqualified in rolling, and continuing rolling the tea to be detected.
In this embodiment, when the She Chengtiao rate detecting device determines that the detected strip rate is less than the Yu Chengtiao rate threshold, the tea leaves to be detected are qualified in rolling.
According to the scheme, M strip forming rates of M tea leaves at N sampling points are obtained, and M morphological pictures of M tea leaves at N sampling points are obtained; constructing a strip rate detection model according to the M x N strip rates and the M x N morphological pictures; acquiring a to-be-detected morphological picture of tea leaves to be detected and a first strip forming rate of a first sampling point of the tea leaves to be detected; inputting the to-be-detected morphological picture and the first strip forming rate into the strip forming rate detection model to obtain the detection strip forming rate of the tea to be detected. Therefore, the detection time of the tea leaf forming rate is reduced, the tea leaf forming rate detection efficiency is improved, the tea leaf production efficiency is improved, the tea leaf forming rate is automatically judged, and the rolling degree of the tea leaves is rapidly judged.
Further, referring to fig. 3, fig. 3 is a schematic flow chart of a second embodiment of the tea leaf strip rate detection method of the present invention. Based on the embodiment shown in fig. 2, step S20 may construct a strip rate detection model according to m×n strip rates and m×n morphology pictures, and may include:
step S21, determining a first discrimination coefficient, a second discrimination coefficient, a third discrimination coefficient, a fourth discrimination coefficient and a fifth discrimination coefficient corresponding to the first to M-th tea leaves according to the M x N strip forming rates and the M x N morphological pictures;
in this embodiment, after m×n morphological images of M kinds of tea at N sampling points are obtained, the tea forming rate detection device determines first discrimination coefficients (a) corresponding to first to M-th kinds of tea according to m×n kinds of forming rates and m×n kinds of morphological images 1 、a 2 、……、a m ) Second discrimination coefficient (b) 1 、b 2 、……、b m ) Third discrimination coefficient (c) 1 、c 2 、……、c m ) Fourth discrimination coefficient (d) 1 、d 2 、……、d m ) And a fifth discrimination coefficient (e 1 、e 2 、……、e m )。
Step S21 determines a first discrimination coefficient, a second discrimination coefficient, a third discrimination coefficient, a fourth discrimination coefficient and a fifth discrimination coefficient corresponding to the first to the mth tea according to the m×n formation rates and the m×n morphological pictures, and may include:
step c1, determining m×n first morphology feature values, m×n second morphology feature values, m×n third morphology feature values and m×n fourth morphology feature values according to m×n morphology pictures;
In this embodiment, after m×n morphological images of M tea leaves at N sampling points are obtained, the tea leaf forming rate detection device determines m×n first morphological feature values X of M tea leaves at N sampling points according to m×n morphological images 1 M X N second form characteristic values X 2 M X N third morphological feature values X 3 And M X N fourth morphological feature values X 4 . Wherein the first morphological feature value X 1 To select the total area of tea, M is N second shape characteristic values X 2 To select the total perimeter of the tea leaves, M is N third morphological feature values X 3 To select the average area of tea, M is N fourth morphological feature values X 4 To select the average circumference of the tea.
Step c1 determines m×n first morphology feature values, m×n second morphology feature values, m×n third morphology feature values, and m×n fourth morphology feature values according to m×n morphology pictures, and may include:
and d, processing the M x N morphological pictures based on a tea appearance analysis program to obtain M x N first morphological feature values, M x N second morphological feature values, M x N third morphological feature values and M x N fourth morphological feature values. Wherein the tea appearance analysis program is Fi Tea Shape Analysis program;
Fi Tea Shape the Analysis procedure works on the principle of dividing the acquired tea sample image into a series of non-overlapping regions, i.e. image segmentation. Typical image segmentation techniques are thresholding and gradient segmentation (boundary tracking, boundary image binarization, laplace edge detection). Because the tea leaves are obviously distinguished from the background, the appearance analysis adopted in the test is carried out according to threshold segmentation, and the principle is as follows: setting a threshold value 'T', comparing the gray value of each pixel of the background and the target with the gray value of each pixel, defining all pixels smaller than or equal to the 'T' as a background area, otherwise defining the background area as a target area, deleting relevant information of the background area after the background area is separated from the target area, and recording the number of pixel points to obtain corresponding measurement indexes. The threshold value is selected by Otsu automatic threshold value determination method, namely, firstly calculating the histogram of the image and normalizing the gray value histogram Wherein i represents a gray value, ni represents the number of pixels of the gray value i,representing the total prime number of pixels. The image pixels are divided into background pixels and target pixels by a threshold T, the pixel range of a background region is 0-T, the target region is a region with gray values of T+1-255, and the probability distribution of the background region and the target region is shown in the formula:
wherein:representing a zero-order cumulative moment of the pixel histogram below the threshold;
representing a first order cumulative moment of the pixel histogram below the threshold;
representing the total mean value of the images;
optimum threshold T S Obtained by the formula:
wherein:
step c2, determining a first discrimination coefficient, a second discrimination coefficient, a third discrimination coefficient, a fourth discrimination coefficient and a fifth discrimination coefficient corresponding to the first tea according to N first morphological feature values, N second morphological feature values, N third morphological feature values, N fourth morphological feature values and N banding rates corresponding to the first tea, wherein N is more than or equal to 5;
in this embodiment, the tea leaf forming rate detecting device obtains m×n first morphology feature values, m×n second morphology feature values, m×n third morphology feature values, and m×n fourth morphology feature values of a tea leaf at N sampling points, and then sets N first morphology feature values X corresponding to the first tea leaf 1 N of the second form characteristic values X 2 N of the third morphological feature values X 3 N of the fourth morphological feature values X 4 N pieces of the strip forming rate input discriminant functions corresponding to the first tea, and determining a first discriminant coefficient a corresponding to the first tea 1 Second discrimination coefficient b 1 Third discrimination coefficient c 1 Fourth discrimination coefficient d 1 And a fifth discrimination coefficient e 1 Wherein N is more than or equal to 5; wherein the discriminant function may be F 1 =a 1 *X 1 +b 1 *X 2 +c 1 *X 3 +d 1 *X 4 +e 1 *1, wherein F 1 And N forming rates corresponding to the first tea.
Step c3 of determining a first discrimination coefficient, a second discrimination coefficient, a third discrimination coefficient, a fourth discrimination coefficient and a fifth discrimination coefficient corresponding to the second tea according to the N first morphological feature values, the N second morphological feature values, the N third morphological feature values, the N fourth morphological feature values and the N banding rates corresponding to the second tea;
in this embodiment, the tea leaf forming rate detecting device obtains m×n first morphology feature values, m×n second morphology feature values, m×n third morphology feature values, and m×n fourth morphology feature values of two kinds of tea leaves at N sampling points, and then sets N first morphology feature values X corresponding to the second kind of tea leaves 1 N of the second form characteristic values X 2 N of the third morphological feature values X 3 N of the fourth morphological feature values X 4 Inputting discrimination functions corresponding to the N slivering rates of the first tea, and determining a first discrimination coefficient a corresponding to the second tea 2 Second discrimination coefficient b 2 Third discrimination coefficient c 2 Fourth discrimination coefficient d 2 And a fifth discrimination coefficient e 2 Wherein N is more than or equal to 5; wherein the discriminant function may be F 2 =a 2 *X 1 +b 2 *X 2 +c 2 *X 3 +d 2 *X 4 +e 2 *1, wherein F 2 And N forming rates corresponding to the second tea.
And c4, by analogy, determining a first discrimination coefficient, a second discrimination coefficient, a third discrimination coefficient, a fourth discrimination coefficient and a fifth discrimination coefficient corresponding to the Mth tea according to the N first morphological feature values, the N second morphological feature values, the N third morphological feature values, the N fourth morphological feature values and the N stripe forming rates corresponding to the Mth tea.
In this embodiment, similarly, the tea leaf forming rate detecting device obtains M first morphology feature values, M second morphology feature values, M third morphology feature values and M fourth morphology feature values of M tea leaves at N sampling points, and then sets N first morphology feature values X corresponding to the M tea leaves 1 N of the second form characteristic values X 2 N of the third morphological feature values X 3 N of the fourth morphological feature values X 4 Inputting discrimination functions corresponding to the N slivering rates of the first tea, and determining a first discrimination coefficient a corresponding to the M th tea m Second discrimination coefficient b m Third discrimination coefficient c m Fourth discrimination coefficient d m And a fifth discrimination coefficient e m Wherein N is more than or equal to 5; wherein the discriminant function may be F m =a m *X 1 +b m *X 2 +c m *X 3 +d m *X 4 +e m *1, wherein F m And N forming rates corresponding to the M-th tea.
Step S22, determining a first correction function according to the first discrimination coefficients corresponding to the first to M-th tea leaves and the strip forming rate corresponding to the first time sampling points of the first to M-th tea leaves;
in this embodiment, the tea leaf forming rate detecting means obtains the forming rate corresponding to the first time sampling point of the first to M-th tea leaves after determining the first discrimination coefficients corresponding to the first to M-th tea leaves and obtaining the forming rate corresponding to the first time sampling point of the first to M-th tea leaves by applying the first discrimination coefficients (a 1 、a 2 、……、a m ) And the first time sampling point of the first to M-th tea leaves corresponds to the strip forming rate (z 1 、z 2 、……、z m ) Fitting to obtain a first correction function Y related to the first discrimination coefficient a That is Y a Regression equation with z, wherein the first correction function Y a The functional relationship between the banding rate corresponding to the first time sampling point can be Y a =0.0131z 2 -0.0072z+0.001. First correction function Y a Is a modified function of the undetermined coefficient a.
Step S23, determining a second correction function according to the second discrimination coefficients corresponding to the first to M-th tea leaves and the strip forming rate corresponding to the first time sampling points of the first to M-th tea leaves;
in this example, teaShe Chengtiao rate detecting means for detecting the first to M-th tea leaves by determining the second discrimination coefficients corresponding to the first to M-th tea leaves and obtaining the first time sampling points of the first to M-th tea leaves at which the first to M-th tea leaves are formed into strips (b 1 、b 2 、……、b m ) And the first time sampling point of the first to M-th tea leaves corresponds to the strip forming rate (z 1 、z 2 、……、z m ) Fitting to obtain a second correction function Y related to the second discrimination coefficient b That is Y b Regression equation with z, wherein the second correction function Y b The functional relationship between the banding rate corresponding to the first time sampling point can be Y b =0.0297z 2 -0.016z+0.0021. Second correction function Y b As a modified function of the undetermined coefficient b.
Specifically, the tea leaf forming rate detecting device determines the second discrimination coefficients corresponding to the first to M-th tea leaves and obtains the forming rate corresponding to the first time sampling points of the first to M-th tea leaves, and then determines the forming rate of the first to M-th tea leaves by applying the third discrimination coefficients (c 1 、c 2 、……、c m ) And the first time sampling point of the first to M-th tea leaves corresponds to the strip forming rate (z 1 、z 2 、……、z m ) Fitting to obtain a third correction function Y related to the third discrimination coefficient c That is Y c Regression equation with z, wherein the third correction function Y c The functional relationship between the banding rate corresponding to the first time sampling point can be Y c =0.0619z 2 -0.0327z+0.0043. First correction function Y c Is a modified function of the undetermined coefficient c.
Specifically, the tea forming rate detecting device determines the fourth discrimination coefficients corresponding to the first to M-th tea leaves and obtains the forming rate corresponding to the first time sampling point of the first to M-th tea leaves, and then, determines the fourth discrimination coefficients (d 1 、d 2 、……、d m ) And the first time sampling point of the first to M-th tea leaves corresponds to the strip forming rate (z 1 、z 2 、……、z m ) Fitting to obtain a fourth correction function Y related to the fourth discrimination coefficient d That is Y d Regression equation with z, wherein the fourth correction function Y d The functional relationship between the banding rate corresponding to the first time sampling point can be Y d =-1.0165z 2 +0.5443z-0.0717. Fourth correction function Y d Is a modified function of the undetermined coefficient d.
Step S24, and the like, until a fifth correction function is determined according to the fifth discrimination coefficients corresponding to the first to M-th tea leaves and the strip forming rate corresponding to the first time sampling points of the first to M-th tea leaves.
In this embodiment, the tea leaf forming rate detecting means obtains the forming rate corresponding to the first time sampling point of the first to mth tea leaves after determining the fifth discrimination coefficient corresponding to the first to mth tea leaves and obtaining the forming rate corresponding to the first time sampling point of the first to mth tea leaves by applying the first to mth tea leaves to the fifth discrimination coefficient (e 1 、e 2 、……、e m ) And the first time sampling point of the first to M-th tea leaves corresponds to the strip forming rate (z 1 、z 2 、……、z m ) Fitting to obtain a fifth correction function Y related to the fourth discrimination coefficient e That is Y e Regression equation with z, wherein the fifth correction function Y e The functional relationship between the banding rate corresponding to the first time sampling point can be Y e =-15.694z 2 +28.734z-5.4636. Fifth correction function Y e Is a modified function of the undetermined coefficient e.
According to the scheme, the first discrimination coefficient, the second discrimination coefficient, the third discrimination coefficient, the fourth discrimination coefficient and the fifth discrimination coefficient corresponding to the first tea to the M-th tea are determined according to the M x N strip forming rates and the M x N morphological pictures; determining a first correction function according to the first discrimination coefficients corresponding to the first to M-th tea leaves and the strip forming rate corresponding to the first time sampling points of the first to M-th tea leaves; determining a second correction function according to the second discrimination coefficients corresponding to the first to M-th tea leaves and the strip forming rate corresponding to the first time sampling points of the first to M-th tea leaves; and the like, determining a fifth correction function according to the fifth discrimination coefficients corresponding to the first tea leaves to the M tea leaves and the strip forming rate corresponding to the first time sampling point of the first tea leaves to the M tea leaves. Therefore, the accuracy of tea strip forming rate detection is improved, the detection time of the tea strip forming rate is shortened, the tea strip forming rate detection efficiency is improved, the tea production efficiency is improved, the tea strip forming rate is automatically judged, and the rolling degree of the tea is rapidly judged.
Further, referring to fig. 4, fig. 4 is a schematic flow chart of a third embodiment of the tea leaf strip rate detection method according to the present invention. Based on the embodiment shown in fig. 3, step S40 may include:
step S41, inputting the first forming rate into the first correction function, the second correction function, the third correction function, the fourth correction function and the fifth correction function respectively to obtain a first discrimination coefficient, a second discrimination coefficient, a third discrimination coefficient, a fourth discrimination coefficient and a fifth discrimination coefficient corresponding to the tea to be detected;
in this embodiment, the tea leaf strip rate detection device obtains the first strip rate of the tea leaves to be detected, and then inputs the first strip rate z into the first correction function Y a =0.0131z 2 -0.0072z+0.001, said second correction function Y b =0.0297z 2 -0.016z+0.0021, said third correction function Y c =0.0619z 2 -0.0327z+0.0043, said fourth correction function Y d =-1.0165z 2 +0.5443z-0.0717 and said fifth correction function Y e =-15.694z 2 In +28.734z-5.4636, a first discrimination coefficient a, a second discrimination coefficient b, a third discrimination coefficient c, a fourth discrimination coefficient d and a fifth discrimination coefficient e corresponding to the tea leaves to be detected are obtained. The first forming rate is the forming rate of the tea leaves taken out 5min after the tea leaves to be detected are rolled.
Step S42, determining a first morphological characteristic value, a second morphological characteristic value, a third morphological characteristic value and a fourth morphological characteristic value corresponding to the tea to be detected according to the morphological picture to be detected;
in this embodiment, after obtaining a to-be-detected morphological picture corresponding to a to-be-detected tea, the tea forming rate detecting device determines a first morphological feature value X corresponding to the to-be-detected tea according to the to-be-detected morphological picture 1 N of the second form characteristic values X 2 N of the third morphological feature values X 3 N of the fourth morphological feature values X 4 。
Step S42 may include determining, according to the to-be-detected morphological picture, a first morphological feature value, a second morphological feature value, a third morphological feature value, and a fourth morphological feature value corresponding to the tea to be detected, where the determining may include:
and e, processing the to-be-detected morphological picture based on a tea appearance analysis program to obtain a first morphological characteristic value, a second morphological characteristic value, a third morphological characteristic value and a fourth morphological characteristic value which correspond to the to-be-detected tea.
In this embodiment, after obtaining a to-be-detected morphological image corresponding to a to-be-detected tea, the tea forming rate detecting device processes the to-be-detected morphological image based on a tea appearance analysis program to obtain a first morphological feature value X corresponding to the to-be-detected tea 1 N of the second form characteristic values X 2 N of the third morphological feature values X 3 N of the fourth morphological feature values X 4 。
Step S43, calculating to obtain the detection strip rate of the tea to be detected according to the first discrimination coefficient, the second discrimination coefficient, the third discrimination coefficient, the fourth discrimination coefficient and the fifth discrimination coefficient corresponding to the tea to be detected, and the first morphological feature value, the second morphological feature value, the third morphological feature value and the fourth morphological feature value corresponding to the tea to be detected.
In the present embodiment, the tea leaf forming rate detecting device obtains a first discrimination coefficient a, a second discrimination coefficient b, a third discrimination coefficient c, a fourth discrimination coefficient d and a fifth discrimination coefficient e corresponding to the tea leaves to be detected, and obtainsFirst morphological feature value X corresponding to tea leaves to be detected 1 N of the second form characteristic values X 2 N of the third morphological feature values X 3 N of the fourth morphological feature values X 4 Then, inputting the first discrimination coefficient, the second discrimination coefficient, the third discrimination coefficient, the fourth discrimination coefficient, the fifth discrimination coefficient, the first morphological feature value, the second morphological feature value, the third morphological feature value and the fourth morphological feature value corresponding to the tea to be detected into a discrimination function F=a×X 1 +b*X 2 +c*X 3 +d*X 4 And in +e 1, calculating to obtain the detection strip forming rate F of the tea to be detected.
According to the scheme, the first strip forming rate is respectively input into the first correction function, the second correction function, the third correction function, the fourth correction function and the fifth correction function, so that a first discrimination coefficient, a second discrimination coefficient, a third discrimination coefficient, a fourth discrimination coefficient and a fifth discrimination coefficient corresponding to tea leaves to be detected are obtained; determining a first morphological characteristic value, a second morphological characteristic value, a third morphological characteristic value and a fourth morphological characteristic value corresponding to the tea to be detected according to the morphological picture to be detected; and calculating the detection strip rate of the tea to be detected according to the first discrimination coefficient, the second discrimination coefficient, the third discrimination coefficient, the fourth discrimination coefficient and the fifth discrimination coefficient corresponding to the tea to be detected, and the first morphological characteristic value, the second morphological characteristic value, the third morphological characteristic value and the fourth morphological characteristic value corresponding to the tea to be detected. Therefore, the detection time of the tea leaf forming rate is reduced, the tea leaf forming rate detection efficiency is improved, the tea leaf production efficiency is improved, the tea leaf forming rate is automatically judged, and the rolling degree of the tea leaves is rapidly judged.
The invention also provides a tea strip forming rate detection device.
The tea leaf strip forming rate detection device comprises: the tea leaf strip rate detection device comprises a memory, a processor and a tea leaf strip rate detection program which is stored in the memory and can run on the processor, wherein the tea leaf strip rate detection program realizes the steps of the tea leaf strip rate detection method when being executed by the processor.
The method implemented when the tea leaf strip rate detection program running on the processor is executed may refer to various embodiments of the tea leaf strip rate detection method of the present invention, and will not be described herein.
The invention also provides a computer readable storage medium.
The computer readable storage medium of the present invention stores thereon a tea leaf strip rate detection program which, when executed by a processor, implements the steps of the tea leaf strip rate detection method as described above.
The method implemented when the tea leaf strip rate detection program running on the processor is executed may refer to various embodiments of the tea leaf strip rate detection method of the present invention, and will not be described herein.
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 system 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 system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for description, and do not represent advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a computer readable storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as described above, comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (7)
1. A tea leaf strip forming rate detection method is characterized by comprising the following steps: the tea leaf strip rate detection method comprises the following steps:
obtaining M x N strip forming rates of M tea leaves at N sampling points, and obtaining M x N morphological pictures of M tea leaves at N sampling points;
constructing a strip rate detection model according to the M x N strip rates and the M x N morphological pictures;
acquiring a to-be-detected morphological picture of tea leaves to be detected and a first strip forming rate of a first sampling point of the tea leaves to be detected;
inputting the morphological picture to be detected and the first strip forming rate into the strip forming rate detection model to obtain the detection strip forming rate of the tea to be detected;
the step of constructing a strip rate detection model according to m×n strip rates and m×n morphological pictures includes:
determining a first discrimination coefficient, a second discrimination coefficient, a third discrimination coefficient, a fourth discrimination coefficient and a fifth discrimination coefficient corresponding to the first to M-th tea leaves according to the M x N strip forming rates and the M x N morphological pictures;
determining a first correction function according to the first discrimination coefficients corresponding to the first to M-th tea leaves and the strip forming rate corresponding to the first time sampling points of the first to M-th tea leaves;
Determining a second correction function according to the second discrimination coefficients corresponding to the first to M-th tea leaves and the strip forming rate corresponding to the first time sampling points of the first to M-th tea leaves;
and the like, determining a fifth correction function according to the fifth discrimination coefficients corresponding to the first tea leaves to the M tea leaves and the strip forming rate corresponding to the first time sampling point of the first tea leaves to the M tea leaves;
the step of determining the first discrimination coefficient, the second discrimination coefficient, the third discrimination coefficient, the fourth discrimination coefficient and the fifth discrimination coefficient corresponding to the first to the Mth tea leaves according to the M x N formation rates and the M x N morphological pictures comprises the following steps:
determining M x N first morphological feature values, M x N second morphological feature values, M x N third morphological feature values and M x N fourth morphological feature values according to M x N morphological pictures, wherein the first morphological feature values are total areas of selected tea leaves, the second morphological feature values are total circumferences of the selected tea leaves, the third morphological feature values are average areas of the selected tea leaves, and the fourth morphological feature values are average circumferences of the selected tea leaves;
determining a first discrimination coefficient, a second discrimination coefficient, a third discrimination coefficient, a fourth discrimination coefficient and a fifth discrimination coefficient corresponding to the first tea according to N first morphological feature values, N second morphological feature values, N third morphological feature values, N fourth morphological feature values and N banding rates corresponding to the first tea, wherein N is more than or equal to 5;
Determining a first discrimination coefficient, a second discrimination coefficient, a third discrimination coefficient, a fourth discrimination coefficient and a fifth discrimination coefficient corresponding to the second tea according to N first morphological feature values, N second morphological feature values, N third morphological feature values, N fourth morphological feature values and N stripe forming rates corresponding to the second tea;
and so on, determining a first discrimination coefficient, a second discrimination coefficient, a third discrimination coefficient, a fourth discrimination coefficient and a fifth discrimination coefficient corresponding to the M-th tea according to the N first morphological feature values, the N second morphological feature values, the N third morphological feature values, the N fourth morphological feature values and the N banding rates corresponding to the M-th tea;
the step of inputting the to-be-detected morphological picture and the first strip forming rate into the strip forming rate detection model to obtain the detection strip forming rate of the to-be-detected tea comprises the following steps:
inputting the first strip forming rate into the first correction function, the second correction function, the third correction function, the fourth correction function and the fifth correction function respectively to obtain a first discrimination coefficient, a second discrimination coefficient, a third discrimination coefficient, a fourth discrimination coefficient and a fifth discrimination coefficient corresponding to the tea to be detected;
Determining a first morphological characteristic value, a second morphological characteristic value, a third morphological characteristic value and a fourth morphological characteristic value corresponding to the tea to be detected according to the morphological picture to be detected;
and calculating the detection strip rate of the tea to be detected according to the first discrimination coefficient, the second discrimination coefficient, the third discrimination coefficient, the fourth discrimination coefficient and the fifth discrimination coefficient corresponding to the tea to be detected, and the first morphological characteristic value, the second morphological characteristic value, the third morphological characteristic value and the fourth morphological characteristic value corresponding to the tea to be detected.
2. The method of claim 1, wherein the determining M x N first morphology feature values, M x N second morphology feature values, M x N third morphology feature values, and M x N fourth morphology feature values from the M x N morphology pictures comprises:
and processing the M.N morphological pictures based on a tea profile analysis program to obtain M.N first morphological feature values, M.N second morphological feature values, M.N third morphological feature values and M.N fourth morphological feature values.
3. The method for detecting tea leaf strip rate according to claim 2, wherein the step of determining a first morphology feature value, a second morphology feature value, a third morphology feature value and a fourth morphology feature value corresponding to the tea leaf to be detected according to the morphology picture to be detected comprises:
And processing the to-be-detected morphological picture based on a tea appearance analysis program to obtain a first morphological characteristic value, a second morphological characteristic value, a third morphological characteristic value and a fourth morphological characteristic value which correspond to the to-be-detected tea.
4. The method for detecting tea leaf strip rate according to claim 1, wherein after the step of inputting the picture of the form to be detected and the first strip rate into the strip rate detection model to obtain the detected strip rate of the tea leaf to be detected, the method comprises:
detecting whether the detected banding rate is greater than or equal to a banding rate threshold;
and if the detected strip forming rate is greater than or equal to a strip forming rate threshold, judging that the tea to be detected is qualified in rolling.
5. A method of detecting tea leaf strip rate as claimed in claim 4 wherein, after the step of detecting whether the detected strip rate is greater than or equal to a strip rate threshold, comprising:
if the detected strip forming rate is smaller than the Yu Chengtiao rate threshold, judging that the tea to be detected is unqualified in rolling, and continuing rolling the tea to be detected.
6. The utility model provides a tealeaves strip rate detection device which characterized in that, tealeaves strip rate detection device includes: a memory, a processor and a tea leaf cut rate detection program stored on the memory and running on the processor, which when executed by the processor, performs the steps of the tea leaf cut rate detection method as claimed in any one of claims 1 to 5.
7. A computer-readable storage medium, wherein a tea leaf cut rate detection program is stored on the computer-readable storage medium, which when executed by a processor, implements the steps of the tea leaf cut rate detection method according to any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110650727.4A CN113763319B (en) | 2021-06-10 | 2021-06-10 | Tea leaf strip forming rate detection method and device and computer readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110650727.4A CN113763319B (en) | 2021-06-10 | 2021-06-10 | Tea leaf strip forming rate detection method and device and computer readable storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113763319A CN113763319A (en) | 2021-12-07 |
CN113763319B true CN113763319B (en) | 2024-01-05 |
Family
ID=78787442
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110650727.4A Active CN113763319B (en) | 2021-06-10 | 2021-06-10 | Tea leaf strip forming rate detection method and device and computer readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113763319B (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108563979A (en) * | 2017-12-29 | 2018-09-21 | 南京农业大学 | A method of based on the farmland image discriminating rice blast state of an illness of taking photo by plane |
CN110547344A (en) * | 2019-08-22 | 2019-12-10 | 湖南三十九铺茶业有限公司 | Tea rolling device |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2014078861A1 (en) * | 2012-11-19 | 2014-05-22 | Altria Client Services Inc. | On-line oil and foreign matter detection system and method employing hyperspectral imaging |
-
2021
- 2021-06-10 CN CN202110650727.4A patent/CN113763319B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108563979A (en) * | 2017-12-29 | 2018-09-21 | 南京农业大学 | A method of based on the farmland image discriminating rice blast state of an illness of taking photo by plane |
CN110547344A (en) * | 2019-08-22 | 2019-12-10 | 湖南三十九铺茶业有限公司 | Tea rolling device |
Non-Patent Citations (4)
Title |
---|
Real-time monitoring of optimum timing for harvesting fresh tea leaves based on machine vision;Zhang, L 等;INTERNATIONAL JOURNAL OF AGRICULTURAL AND BIOLOGICAL ENGINEERING;全文 * |
扁形茶外形指标分析软件设计及大佛龙井 外形品质识别模型构建;俞辉;中国优秀硕士学位论文全文数据库(第02期);全文 * |
自动化炒青绿茶生产线的设计与应用;谭俊峰 等;中国茶叶科技创新与产业发展学术研讨会论文集;全文 * |
计算机视觉技术在茶叶领域中的应用现状及展望;黄藩 等;茶叶科学;全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN113763319A (en) | 2021-12-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2019041519A1 (en) | Target tracking device and method, and computer-readable storage medium | |
US8897560B2 (en) | Determining the estimated clutter of digital images | |
US20190362144A1 (en) | Eyeball movement analysis method and device, and storage medium | |
EP3196758B1 (en) | Image classification method and image classification apparatus | |
CN108234882B (en) | Image blurring method and mobile terminal | |
CN112767366A (en) | Image recognition method, device and equipment based on deep learning and storage medium | |
US8643741B2 (en) | Orientation detection using image processing | |
US20140334734A1 (en) | Systems and Methods for Facial Age Identification | |
CN111935479B (en) | Target image determination method and device, computer equipment and storage medium | |
CN111882541A (en) | Defect detection method, device, equipment and computer readable storage medium | |
CN111080665B (en) | Image frame recognition method, device, equipment and computer storage medium | |
CN111507324A (en) | Card frame identification method, device, equipment and computer storage medium | |
CN110674873A (en) | Image classification method and device, mobile terminal and storage medium | |
CN110264093B (en) | Credit model establishing method, device, equipment and readable storage medium | |
CN114119948A (en) | Tea leaf identification method and device, electronic equipment and storage medium | |
CN109141249B (en) | Distance measuring method and computer-readable storage medium | |
US8731291B2 (en) | Estimating the clutter of digital images | |
CN113763319B (en) | Tea leaf strip forming rate detection method and device and computer readable storage medium | |
CN109147911B (en) | Method and device for displaying disease information and computer readable storage medium | |
CN112333537B (en) | Video integration method, device and computer readable storage medium | |
CN110796651A (en) | Image quality prediction method and device, electronic device and storage medium | |
CN109685069B (en) | Image detection method, device and computer readable storage medium | |
CN107945016B (en) | Variable value dimension increasing method and device and computer readable storage medium | |
CN113869336A (en) | Image identification searching method and related device | |
CN113537204A (en) | Small flame detection method based on infrared features and machine learning and computer device |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |