Tea identification method, recommended method, tea identification device, equipment and medium

Through the pre-processing and feature processing of tea images, the neural network is used to identify tea types, which solves the difficulties of consumers in identifying tea types and usage methods, and achieves accurate identification and recommendation of tea.

CN111753852BActive Publication Date: 2024-12-03CHONGQING CISDI AGRI DATA TECH CO LTD +2
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202010641537.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-07-06
Publication Date
2024-12-03
Estimated Expiration
2040-07-06

AI Technical Summary

Technical Problem

It is difficult for consumers to identify and understand the types and usage of tea.

Method used

By collecting tea leaves images, pre-processing and feature processing, including color feature processing and shape feature processing, the BP neural network and convolutional neural network are used to identify tea types and push related information.

Benefits of technology

It realizes accurate identification and recommendation of tea, solves the difficulties of consumers in identifying tea types and usage methods, and improves the recognition accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN111753852B_ABST
    Figure CN111753852B_ABST
Patent Text Reader

Abstract

The present invention provides a tea identification method, a recommendation method, a tea identification device, equipment and a medium. The tea identification method comprises: collecting tea images; obtaining image information through preprocessing, and performing feature processing on the image information to obtain tea features, wherein the feature processing includes at least one of the following: color feature processing and shape feature processing; and determining the corresponding tea type according to the tea features. Different types of tea have characteristic differences in color or shape, and the characteristics of the type of tea are obtained through color feature processing and / or shape feature processing to facilitate identification. The type of tea is identified by using image recognition technology to determine the type of tea, thereby solving the problem in the prior art that it is not easy to know the type of tea and the method of tasting.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of detection technology, and in particular to a tea identification method, a recommendation method, a tea identification device, equipment and a medium. Background Art

[0002] my country is a country with a large tea consumption and tea culture, and consumes a large amount of tea every year. There are many types of tea, and the corresponding popular science, culture, drinking methods, products and services are also different. When consumers first come into contact with tea or drink tea, it is not easy to know the types of tea and how to taste it. Summary of the invention

[0003] In view of the above-mentioned shortcomings of the prior art, the purpose of the present invention is to provide a tea identification method, a recommendation method, a tea identification device, equipment and a medium to solve the problem in the prior art that it is not easy to know the types of tea and how to taste it.

[0004] To achieve the above-mentioned object and other related objects, the present invention provides a tea identification method, comprising:

[0005] Collect tea leaves images;

[0006] After preprocessing, image information is obtained, and feature processing is performed on the image information to obtain tea features, wherein the feature processing includes at least one of the following: color feature processing and shape feature processing;

[0007] The corresponding tea type is determined according to the tea characteristics.

[0008] Optionally, the preprocessing includes binarization of the image, eigenvalue color processing, removing the background of the tea image, and acquiring image information.

[0009] Optionally, the color feature processing includes: providing a color feature algorithm to extract the color of each segment of the tea leaf segment and the image area or area percentage of the corresponding color segment, and the color feature algorithm includes an HSV model, a HIS model, and a YUI model.

[0010] Optionally, the color feature processing further includes: providing a BP neural network model;

[0011] For each image information i, the eigenvalues ​​of color feature extraction are M and used as the input layer, and the input layer is a 1*M matrix;

[0012] The hidden layer is a 1*P matrix;

[0013] The output layer is a 1*N matrix. When the image information i belongs to the nth type of tea, the output layer n is 1, otherwise it is 0, where N is the number of tea color types, the tea type is recorded as n, and the value of n ranges from 1 to N;

[0014] Set the excitation function and train the BP neural network model for each image information.

[0015] Optionally, the characteristic value of the image information to be tested is input into the BP neural network model, and the result is a 1*N vector, where the values ​​are all real numbers from 0 to 1, and the tea color type probability sequence {Ci} is obtained, where i ranges from 1 to N. The tea type is determined by the tea color type probability sequence {Ci} and the number of tea color types N.

[0016] Optionally, the shape feature processing includes: classifying according to the shape of tea leaves, obtaining the type of tea shapes and the number of tea shape types, providing a convolutional neural network model, training the convolutional neural network model through the image information, and inputting the image information into the convolutional neural network model to obtain a tea shape type probability sequence {Dj}, where j takes a value from 1 to M, M is the number of tea shape types, and determining the tea type through the tea shape type probability sequence {Dj} and the number of tea shape types M.

[0017] Optionally, the step of determining the corresponding tea type according to the tea characteristics includes: determining the type of tea according to the color type of tea and the shape type of tea, which is mathematically expressed as:

[0018] Ek=Ci*Dj

[0019] Among them, Ek is the probability of tea types, and k is the number of tea types.

[0020] Optionally, x pieces of image information extracted from the tea images are analyzed to obtain a probability sequence {{Ek}x}, where k is the type of tea and x is the number of image information. T% of the maximum value in {{Ek}x} is taken as the threshold, and a value greater than the threshold is recorded as 1, and a value less than the threshold is recorded as 0. The values ​​are expanded and similar items are merged to obtain {Ek′}, where Ek′ is an integer between 0 and 1. According to the number of tea types q that need to be recommended, the first q types in {Ek′} from large to small are taken.

[0021] A tea recommendation method, comprising:

[0022] Preset tea information corresponding to the tea, the tea information including at least one of the following: tea shape, product description, product advertisement;

[0023] Identify the corresponding tea type and push the corresponding tea information based on the tea type and probability.

[0024] A tea identification device, comprising:

[0025] A collection module, used for collecting tea leaves images;

[0026] The recognition module is used to obtain image information by preprocessing the tea image, and obtain tea features by feature processing of the image information. The feature processing includes at least one of the following: color feature processing, shape feature processing, and the corresponding tea type is determined according to the tea features.

[0027] A device comprising:

[0028] One or more processors; and one or more machine-readable media having instructions stored thereon, which, when executed by the one or more processors, cause the device to perform one or more of the methods described.

[0029] One or more machine-readable media are characterized in that instructions are stored thereon, which, when executed by one or more processors, cause the device to perform one or more of the methods described.

[0030] As described above, the tea identification method, recommendation method, tea identification device, equipment and medium provided by the present invention have the following beneficial effects:

[0031] Different types of tea have characteristic differences in color or shape, and the characteristics of the type of tea are obtained through color feature processing and / or shape feature processing to facilitate identification. The type of tea is identified using image recognition technology to determine the type of tea, thereby solving the problem in the prior art that it is not easy to know the type of tea and how to taste it. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 A schematic diagram of a process flow of a tea leaf identification method provided in an embodiment of the present invention.

[0033] Figure 2 A schematic diagram of a process for recommending tea leaves according to an embodiment of the present invention.

[0034] Figure 3 A schematic diagram of the structure of a tea leaf identification device provided in an embodiment of the present invention.

[0035] Figure 4 A schematic diagram of the hardware structure of a terminal device provided in an embodiment.

[0036] Figure 5 A schematic diagram of the hardware structure of a terminal device provided in another embodiment.

[0037] Component number description

[0038] 1100 Input Devices

[0039] 1101 First Processor

[0040] 1102 Output devices

[0041] 1103 First Memory

[0042] 1104 Communication Bus

[0043] 1200 Processing Components

[0044] 1201 Second processor

[0045] 1202 Second Memory

[0046] 1203 Communication Components

[0047] 1204 Power Supply Components

[0048] 1205 Multimedia Components

[0049] 1206 Voice Component

[0050] 1207 Input / Output Interface

[0051] 1208 Sensor Components DETAILED DESCRIPTION

[0052] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0053] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0054] See also Figure 1 The present invention provides a tea identification method, comprising:

[0055] S1: Collect tea images. For example, tea images can be collected through a mobile terminal or a client terminal to obtain tea images. The collected tea images can be analyzed at the terminal or sent to the cloud for analysis;

[0056] S2: After preprocessing, image information is obtained, and feature processing is performed on the image information to obtain tea features, wherein the feature processing includes at least one of the following: color feature processing and shape feature processing, using the feature differences in color or shape of different types of tea, and obtaining the features of the type of tea through color feature processing and / or shape feature processing to facilitate identification;

[0057] S3: Determine the corresponding tea type according to the tea characteristics. Use image recognition technology to identify the type of tea and determine the type of tea, solving the problem in the prior art that it is not easy to know the type of tea and the tasting method.

[0058] Furthermore, the preprocessing includes binarization of the image, feature value color processing, removing the background of the tea image, and obtaining image information. After the binarization step, the feature color processing can also filter the background of the tea image by setting a tea feature map threshold filter to avoid noise interference caused by the background pattern on image recognition. It can also be combined with a watershed algorithm, an open operation or a closed operation to remove the background image and improve the accuracy of tea recognition. For another example, the tea feature map threshold filter can use a mask of hue H (0-120), saturation S (0-255), and brightness V (0-100). The extracted tea images are arranged according to the image size, and generally no more than 20 images from large to small are taken for subsequent image analysis and recommendation, and the area of ​​the smallest image should generally not be less than 10% of the largest image. The extracted tea image is generally a single piece of tea.

[0059] In some implementations, the color feature processing includes: providing a color feature algorithm to extract the color of each segment of the tea leaf and the image area of ​​the segment, and the color feature algorithm includes an HSV model, an HIS model, and a YUI model. Mainly based on the hue H segmentation, the lightness V or the brightness I is supplemented to extract the color of the tea leaf segment, the image area of ​​the segment, and the image area percentage of the segment. The HSV color space value includes (H: 1-120), V (1-100) is the main area of ​​distinction, and H (0-180) S (0-255) V (0-255) is divided into M areas. The HIS, YUI and other methods are similar to HSV, and the color of the tea leaf segment, the image area of ​​the segment, and the image area percentage of the segment are extracted as feature values, and the number of feature values ​​is M.

[0060] In some implementations, the color feature processing further includes: providing a BP neural network model to perform model training on each image information, the BP neural network model including an input layer, a hidden layer, and an output layer;

[0061] For each image information i, the eigenvalues ​​of color feature extraction are M and used as the input layer, and the input layer is a 1*M matrix;

[0062] The hidden layer is a 1*P matrix;

[0063] The output layer is a 1*N matrix. When the image information i belongs to the nth type of tea, the output layer n is 1, otherwise it is 0, where N is the number of tea color types, the tea type is recorded as n, and the value of n ranges from 1 to N;

[0064] Train the BP neural network model and set the activation function to the sigmoid function. For example, the number of iterations is 200, the expected error is 0.1, and the learning rate is 0.05. The number of iterations, expected error, and learning rate can be adjusted according to the model training situation to obtain the BP neural network model. The activation function can also use the Tanh function or the ReLU function.

[0065] In some implementation processes, the characteristic values ​​of the image information to be tested are input into the BP neural network model, and the result is a 1*N vector, all of which are real numbers ranging from 0 to 1. The probability sequence of tea color types {Ci} is obtained, where i ranges from 1 to N. The type of tea is determined by the probability sequence of tea color types {Ci} and the number of tea color types N.

[0066] In some implementations, the shape feature processing includes: classifying tea leaves according to their shapes, obtaining tea shape types and the number of tea shape types, providing a convolutional neural network model, training the convolutional neural network model through the image information, and inputting the image information into the convolutional neural network model to obtain a tea shape type probability sequence {Dj}, where j ranges from 1 to M, M is the number of tea shape types, and determining the tea type through the tea shape type probability sequence {Dj} and the number of tea shape types M.

[0067] Optionally, the step of determining the corresponding tea type according to the tea characteristics includes: determining the type of tea according to the color type and the shape type of tea. For example, the shape of the tea image includes a single bud of a shrub or large-leaf variety, one bud and one leaf just beginning to unfold, one bud and one leaf, one bud and two leaves, one bud and two leaves just beginning to unfold, one bud and three leaves, one bud and four leaves, one bud and five leaves, including needle-shaped, curved and tight, curled, bead-shaped, orchid-shaped, single leaf, ball-shaped or round, etc., and its mathematical expression is:

[0068] Ek=Ci*Dj

[0069] Among them, Ek is the probability of tea types, and k is the number of tea types.

[0070] Optional,

[0071] We analyze the x pieces of image information extracted from the tea images and get the probability sequence {{Ek}x}, where k is the type of tea and x is the number of image information. We take t% of the maximum value in {{Ek}x} as the threshold, and those greater than the threshold are recorded as 1, and those less than the threshold are recorded as 0. We expand it and merge similar items to get {Ek′}, where Ek′ is an integer between 0 and 1. According to the number of tea types q that need to be recommended, we take the first q types from largest to smallest in {Ek′}.

[0072] You can also set up a correspondence table between tea features and tea types, and compare the tea features obtained by color feature processing and shape feature processing to get the type of tea. You can also compare the tea features obtained by tea feature processing or shape feature processing to get the type of tea, which makes it easier to know the type of tea and improve the accuracy of tea identification.

[0073] See also Figure 2 The present invention provides a tea recommendation method, comprising:

[0074] S10: Preset tea information corresponding to the tea leaves, the tea information including at least one of the following: tea shape, product description, and product advertisement;

[0075] S20: Identify the corresponding tea type, and push corresponding tea information according to the tea type.

[0076] A tea identification device, comprising:

[0077] A collection module 10, used for collecting tea leaves images;

[0078] The recognition module 20 is used to obtain image information by preprocessing the tea image, and to obtain tea features by feature processing of the image information. The feature processing includes at least one of the following: color feature processing, shape feature processing, and the corresponding tea type is determined according to the tea features.

[0079] The embodiment of the present application also provides a device, which may include: one or more processors; and one or more machine-readable media having instructions stored thereon, which, when executed by the one or more processors, enable the device to execute Figure 1In practical applications, the device can be used as a terminal device or a server. Examples of terminal devices may include: smart phones, tablet computers, e-book readers, MP3 (Moving Picture Experts Group Audio Layer III) players, MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, car computers, desktop computers, set-top boxes, smart TVs, wearable devices, etc. The embodiments of the present application do not limit specific devices.

[0080] The present application also provides a non-volatile readable storage medium, in which one or more modules (programs) are stored. When the one or more modules are applied to a device, the device can execute the embodiment of the present application. Figure 4 Instructions for the steps involved in a data processing method.

[0081] Figure 4 A schematic diagram of the hardware structure of a terminal device provided for an embodiment of the present application. As shown in the figure, the terminal device may include: an input device 1100, a first processor 1101, an output device 1102, a first memory 1103 and at least one communication bus 1104. The communication bus 1104 is used to realize the communication connection between the components. The first memory 1103 may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk storage. Various programs can be stored in the first memory 1103 to complete various processing functions and implement the method steps of this embodiment.

[0082] Optionally, the first processor 1101 may be implemented, for example, as a central processing unit (CPU), an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a controller, a microcontroller, a microprocessor or other electronic components, and the first processor 1101 is coupled to the input device 1100 and the output device 1102 via a wired or wireless connection.

[0083] Optionally, the input device 1100 may include multiple input devices, for example, at least one of a user interface for users, a device interface for devices, a software programmable interface, a camera, and a sensor. Optionally, the device interface for devices may be a wired interface for data transmission between devices, or a hardware insertion interface for data transmission between devices (such as a USB interface, a serial port, etc.); Optionally, the user interface for users may be, for example, a control button for users, a voice input device for receiving voice input, and a touch sensing device for users to receive user touch input (such as a touch screen with a touch sensing function, a touchpad, etc.); Optionally, the software programmable interface may be, for example, an entry for users to edit or modify programs, such as an input pin interface or an input interface of a chip; the output device 1102 may include output devices such as a display and a speaker.

[0084] In this embodiment, the processor of the terminal device includes functions for executing each module of the voice recognition device in each device. The specific functions and technical effects can be referred to the above embodiments and will not be repeated here.

[0085] Figure 5 A schematic diagram of the hardware structure of a terminal device provided for one embodiment of the present application. Figure 5 Yes Figure 4 A specific embodiment in the implementation process. As shown in the figure, the terminal device of this embodiment may include a second processor 1201 and a second memory 1202.

[0086] The second processor 1201 executes the computer program code stored in the second memory 1202 to implement the above embodiment. Figure 4 The method.

[0087] The second memory 1202 is configured to store various types of data to support operations on the terminal device. Examples of such data include instructions for any application or method used to operate on the terminal device, such as messages, pictures, videos, etc. The second memory 1202 may include a random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage.

[0088] Optionally, the second processor 1201 is arranged in the processing component 1200. The terminal device may further include: a communication component 1203, a power component 1204, a multimedia component 1205, a voice component 1206, an input / output interface 1207 and / or a sensor component 1208. The specific components included in the terminal device are set according to actual needs, and this embodiment does not limit this.

[0089] The processing component 1200 generally controls the overall operation of the terminal device. The processing component 1200 may include one or more second processors 1201 to execute instructions to complete all or part of the steps in the above-mentioned data processing method. In addition, the processing component 1200 may include one or more modules to facilitate the interaction between the processing component 1200 and other components. For example, the processing component 1200 may include a multimedia module to facilitate the interaction between the multimedia component 1205 and the processing component 1200.

[0090] The power supply component 1204 provides power to various components of the terminal device. The power supply component 1204 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the terminal device.

[0091] The multimedia component 1205 includes a display screen that provides an output interface between the terminal device and the user. In some embodiments, the display screen may include a liquid crystal display (LCD) and a touch panel (TP). If the display screen includes a touch panel, the display screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.

[0092] The voice component 1206 is configured to output and / or input voice signals. For example, the voice component 1206 includes a microphone (MIC), and when the terminal device is in an operating mode, such as a voice recognition mode, the microphone is configured to receive an external voice signal. The received voice signal can be further stored in the second memory 1202 or sent via the communication component 1203. In some embodiments, the voice component 1206 also includes a speaker for outputting voice signals.

[0093] The input / output interface 1207 provides an interface between the processing component 1200 and the peripheral interface modules, which may be click wheels, buttons, etc. These buttons may include but are not limited to: volume buttons, start buttons, and lock buttons.

[0094] The sensor component 1208 includes one or more sensors for providing various aspects of status assessment for the terminal device. For example, the sensor component 1208 can detect the open / closed state of the terminal device, the relative positioning of the components, and the presence or absence of contact between the user and the terminal device. The sensor component 1208 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact, including detecting the distance between the user and the terminal device. In some embodiments, the sensor component 1208 may also include a camera, etc.

[0095] The communication component 1203 is configured to facilitate wired or wireless communication between the terminal device and other devices. The terminal device can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In one embodiment, the terminal device may include a SIM card slot for inserting a SIM card, so that the terminal device can log in to a GPRS network and establish communication with a server via the Internet.

[0096] From the above, we can see that Figure 5 The communication component 1203, the voice component 1206, the input / output interface 1207, and the sensor component 1208 involved in the embodiment can all be used as Figure 4 Implementation method of the input device in the embodiment.

[0097] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. A tea leaf identification method, characterized in that: include: Collect tea leaves images; After preprocessing, image information is obtained, and feature processing is performed on the image information to obtain tea features, wherein the feature processing includes at least one of the following: color feature processing and shape feature processing; Determining the corresponding tea type according to the tea characteristics; Wherein, the color feature processing includes: providing BP neural network model training; For each image information i, the eigenvalues ​​of color feature extraction are M and used as the input layer, and the input layer is a 1*M matrix; The hidden layer is a 1*P matrix; The output layer is a 1*N matrix. When the image information i belongs to the nth type of tea, the output layer n is 1, otherwise it is 0, where N is the number of tea color types, the tea type is recorded as n, and the value of n ranges from 1 to N; Set the excitation function and train the BP neural network model for each image information; Input the feature value of the image information to be tested into the BP neural network model, and obtain the result as a 1*N vector, all of which are real numbers ranging from 0 to 1, to obtain the tea color type probability sequence {Ci}, where i ranges from 1 to N, and determine the tea type through the tea color type probability sequence {Ci} and the number of tea color types N; The shape feature processing includes: classifying according to the shape of tea leaves, obtaining the type of tea leaves and the number of tea leaves, providing a convolutional neural network model, training the convolutional neural network model through the image information, and inputting the image information into the convolutional neural network model to obtain a tea leaves shape type probability sequence {Dj}, where j ranges from 1 to M, and M is the number of tea leaves shape types, and determining the tea leaves type through the tea leaves shape type probability sequence {Dj} and the number of tea leaves shape types M; The step of determining the corresponding tea type according to the tea characteristics includes: determining the type of tea according to the color type of tea and the shape type of tea, which is mathematically expressed as: Ek=Ci*Dj Among them, Ek is the probability of tea types, and k is the number of tea types.

2. The tea identification method according to claim 1, characterized in that: The preprocessing includes binarization processing of the image, characteristic value color processing, removing the background of the tea image, and obtaining image information.

3. The tea identification method according to claim 1, characterized in that: The color feature processing includes: providing a color feature algorithm to extract the color of each segment of the tea leaf segment and the image area or area percentage of the corresponding color segment, and the color feature algorithm includes an HSV model, a HIS model, and a YUI model.

4. The tea identification method according to claim 1, characterized in that: We analyze the x pieces of image information extracted from the tea images and get the probability sequence {{Ek}x}, where k is the type of tea and x is the number of image information. We take t% of the maximum value in {{Ek}x} as the threshold, and those greater than the threshold are recorded as 1, and those less than the threshold are recorded as 0. We expand it and merge similar items to get {Ek′}, where Ek′ is an integer between 0 and 1. According to the number of tea types q that need to be recommended, we take the first q types from largest to smallest in {Ek′}.

5. A tea recommendation method, characterized in that: include: Preset tea information corresponding to the tea, the tea information including at least one of the following: tea shape, product description, product advertisement; Identify the corresponding tea type according to the method as described in any one of claims 1-4, and push corresponding tea information according to the tea type and probability.

6. A tea identification device, characterized in that: include: A collection module, used for collecting tea leaves images; The recognition module is used to obtain image information by preprocessing the tea image, and to obtain tea features by performing feature processing on the image information, wherein the feature processing includes at least one of the following: color feature processing and shape feature processing, and the corresponding tea type is determined according to the tea features; Wherein, the color feature processing includes: providing BP neural network model training; For each image information i, the eigenvalues ​​of color feature extraction are M and used as the input layer, and the input layer is a 1*M matrix; The hidden layer is a 1*P matrix; The output layer is a 1*N matrix. When the image information i belongs to the nth type of tea, the output layer n is 1, otherwise it is 0, where N is the number of tea color types, the tea type is recorded as n, and the value of n ranges from 1 to N; Set the excitation function and train the BP neural network model for each image information; Input the feature value of the image information to be tested into the BP neural network model, and obtain the result as a 1*N vector, all of which are real numbers ranging from 0 to 1, to obtain the tea color type probability sequence {Ci}, where i ranges from 1 to N, and determine the tea type through the tea color type probability sequence {Ci} and the number of tea color types N; The shape feature processing includes: classifying according to the shape of tea leaves, obtaining the type of tea leaves and the number of tea leaves, providing a convolutional neural network model, training the convolutional neural network model through the image information, and inputting the image information into the convolutional neural network model to obtain a tea leaves shape type probability sequence {Dj}, where j ranges from 1 to M, and M is the number of tea leaves shape types, and determining the tea leaves type through the tea leaves shape type probability sequence {Dj} and the number of tea leaves shape types M; The step of determining the corresponding tea type according to the tea characteristics includes: determining the type of tea according to the color type of tea and the shape type of tea, which is mathematically expressed as: Ek=Ci*Dj Among them, Ek is the probability of tea types, and k is the number of tea types.

7. A device, characterized in that: include: one or more processors; and One or more machine-readable media having instructions stored thereon, which when executed by the one or more processors, cause the device to perform the method as recited in one or more of claims 1-4.

8. One or more machine-readable media, characterized in that Instructions are stored thereon, which, when executed by one or more processors, cause the device to perform the method as claimed in one or more of claims 1-4.