Machine-picked fresh tea leaf intelligent sorting system and method based on machine vision

Abstract

The invention relates to the technical field of sorting after picking of fresh tea leaves, and discloses a machine-picked fresh tea leaf intelligent sorting system and method based on machine vision, and the system comprises a feeding discrete module, a primary sorting module, an intelligent sorting module and a database module. According to the method, machine-picked fresh tea leaves are scattered and flatly laid on a negative pressure conveying unit through a feeding scattering module and scattered to a primary sorting module through a discharging unit; the primary sorting module preliminarily classifies machine-picked fresh tea leaves and conveys the machine-picked fresh tea leaves to the intelligent sorting module. The intelligent sorting module collects image information of fresh tea leaves at all levels, extracts feature data of the fresh tea leaf images, compares and analyzes the feature data with the corresponding fresh tea leaf information in the database module, generates a grade judgment instruction of the fresh tea leaves and transmits a sorting instruction, and the sorting mechanism executes a sorting decision and completes grading. By combining an intelligent classification technology and a physical grading technology, the intelligent tea leaf sorting device realizes efficient and accurate intelligent sorting while ensuring the minimum damage and loss of fresh tea leaves.

Description

Technical Field

[0001] The present invention relates to the technical field of post-harvest fresh tea leaf sorting, and in particular to a system and method for intelligent sorting of machine-picked fresh tea leaves based on machine vision. Background Art

[0002] Tea is a beverage made from the tender buds, leaves or stems of the tea plant. It is rich in a variety of health-promoting ingredients such as tea polyphenols, caffeine, amino acids and vitamins. Tea provides fragrance, quenches thirst and refreshes the mind. It also plays an important social and ceremonial role in different cultures.

[0003] At present, tea leaves are generally picked by machine, especially in large-scale tea gardens. This method has significantly improved the picking efficiency and yield. Machine picking uses advanced mechanical equipment to remove tea leaves from tea trees through vibration, shearing and other methods. Although mechanical picking has obvious advantages in speed and cost, the quality and uniformity of tea leaves may be reduced because it cannot select tea buds as finely as manual picking.

[0004] Although some sorting equipment has emerged in the current market, aiming to replace manual labor to achieve large-scale sorting of machine-picked fresh tea leaves, in actual applications, such equipment has potential risks in the sorting process and may damage the fresh tea leaves. More importantly, the screening results often contain a lot of residual leaves and fragments, affecting the overall quality. In addition, these devices are still insufficient in the grading and processing of fresh tea leaves, and operators are often required to perform secondary grading of the screened fresh tea leaves, which increases labor and time costs.

[0005] Therefore, there is an urgent need to invent a sorting technology for machine-picked fresh tea leaves to solve the problem that tea sorting equipment in the prior art is prone to damage fresh tea leaves during the sorting process, and the sorting effect is poor, requiring manual secondary sorting, thereby increasing labor costs and time costs. Summary of the invention

[0006] In view of this, the present invention proposes a system and method for intelligent sorting of machine-picked fresh tea leaves based on machine vision, which overcomes the problems of low traditional sorting accuracy and large losses, and the need for manual secondary sorting, which increases labor and time costs.

[0007] The present invention proposes a machine vision-based intelligent sorting system for machine-picked fresh tea leaves, comprising:

[0008] The feeding discrete module includes a negative pressure conveying unit and a feeding unit; wherein the negative pressure conveying unit discretely adsorbs the fresh tea leaves in the feeding area to the conveyor belt and moves with the conveyor belt to the feeding unit. There is no negative pressure environment in the feeding unit area, and the fresh tea leaves fall freely to the next module due to their own gravity.

[0009] The primary sorting module is connected to the feeding discrete module, and includes a sorting unit, a shaking unit and a recycling unit; wherein the sorting unit is composed of 4 levels of sorting windows, each level of sorting window includes sieve holes of different sizes and densities, and buffer zones are set between the sorting windows for isolation, and the fresh tea leaves are graded in sequence according to their shape characteristics; the fresh tea leaves of each level after sorting pass through the recycling units of each level and fall into the next module one by one;

[0010] An intelligent sorting module is connected to the recycling unit of the primary sorting module, and adopts a multi-stage channel collaborative sorting method, including an image acquisition unit, an image transmission unit, an image analysis unit, a control unit and an airflow blowing unit; wherein the image acquisition unit acquires image information of fresh tea leaves, and transmits it to the image analysis unit, determines the type of fresh tea leaves and generates a determination instruction to transmit to each level of control unit, the control unit makes an operation instruction to the airflow blowing unit, and the airflow blowing unit performs the operation to complete the accurate classification of fresh tea leaves;

[0011] The database module includes a computer and a data transmission unit, a data trigger unit, a data storage unit and a data index unit, which are used to store and call image information of different forms of fresh tea leaves of various varieties and grades, and store newly collected image information of fresh tea leaves.

[0012] Furthermore, the discrete feeding module includes:

[0013] The negative pressure transmission unit is composed of a conveyor belt, a negative pressure chamber and an air compressor, wherein the conveyor belt is provided with evenly spaced small holes with a diameter of 1 mm, and each small hole in the negative pressure chamber can absorb fresh tea leaves;

[0014] The unloading unit is composed of an isolation chamber and a conveyor belt. When the conveyor belt passes through the isolation chamber, the negative pressure effect is released, the fresh tea leaves are no longer adsorbed, and they fall freely to the next unit.

[0015] The area of ​​the loading region of the entire loading discrete module is larger than the area of ​​the unloading region, so as to ensure that the sorted fresh tea leaves can be quickly dispersed.

[0016] Furthermore, the primary sorting module comprises:

[0017] The sorting unit comprises a vibration screening device and sorting windows for each level of tea leaves, wherein the inclination angle of the vibration screening device is between [25°, 40°], and the vibration frequency is between [25Hz, 35Hz];

[0018] The screen surface of the vibrating screen device is composed of four-level sorting windows composed of different screen holes arranged at different densities, and each sorting window has a different area, which gradually decreases from the first-level sorting area to the fourth-level sorting area;

[0019] The tilt angle, vibration frequency, sieve hole size, distribution area and buffer zone area of ​​each level of tea sorting window are adjusted according to the type and characteristics of fresh tea leaves, and the reference characteristic indicators are leaf length, leaf spread, weight and rolling friction coefficient of fresh tea leaves;

[0020] The recovery unit is connected with the sorting windows at each level, and receives the sorted fresh tea leaves at each level respectively, and utilizes the fresh tea leaves' own gravity to transport them one by one to the next module through a smooth track.

[0021] Furthermore, the intelligent sorting module includes:

[0022] The image acquisition unit includes a trigger device and a high-speed camera device. When the fresh tea leaves pass by, the trigger device transmits a signal to the high-speed camera device for image acquisition. The frame rate of the high-speed camera device cannot be lower than 100fps.

[0023] The image analysis unit includes a computer and an image preprocessing algorithm, a feature extraction algorithm, a pattern recognition algorithm, a decision-making algorithm and a data transmission interface, and the unit is associated with a database module; wherein the image analysis unit extracts the basic morphological features of the fresh tea leaves after preprocessing the received images such as noise reduction, enhancement, graying and segmentation, including basic morphological features such as area, perimeter, major axis, minor axis, etc., and complex morphological features including gray value, rectangularity, circularity, compactness, slenderness, etc.; by calling the image features of fresh tea leaves of different grades of the variety in the database module, the collected fresh tea leaves are judged and a decision instruction is made;

[0024] The control unit includes a computer, a data transmission channel and a control switch, and is connected to the image analysis unit. After receiving the judgment instruction of the image analysis unit, the control unit transmits the data information to the control switch;

[0025] The airflow blowing unit is connected to the control switch, and comprises an air blowing device and a valve switch, and blows out an airflow of a certain intensity according to the instruction of the control unit.

[0026] Compared with the prior art, the beneficial effect of the machine vision-based intelligent sorting system for fresh tea leaves picked by the machine of the present invention is that the fresh tea leaves are evenly distributed and presented in a non-overlapping state through the feeding discrete module, which provides ideal input conditions for subsequent sorting and effectively avoids the recognition errors caused by tea stacking in the traditional sorting process. At the same time, the primary sorting module realizes multi-level classification according to the shape characteristics of the fresh tea leaves, so that tea leaves of different levels can enter the next link in an orderly manner, laying the foundation for fine sorting. Such a grading method not only optimizes the sorting process, but also reduces the complexity and error of the initial screening. Secondly, the machine vision technology is introduced through the intelligent sorting module, combined with the image acquisition, transmission and analysis unit, to achieve efficient judgment and accurate classification of fresh tea leaves. The airflow blowing unit performs the sorting operation according to the instructions of the control unit, so that each fresh tea leaf can be accurately classified. This sorting method based on image analysis not only improves the sorting accuracy, but also can adapt to the morphological differences of different varieties of tea leaves, and has high flexibility and scalability. In addition, the addition of the database module enables the system to store a large amount of fresh tea leaf image information, forming a comprehensive knowledge base for multiple categories, and supporting the dynamic update and call of new data.

[0027] The present invention also provides a method for intelligent sorting of machine-picked fresh tea leaves based on machine vision, comprising the following steps:

[0028] S1: According to the shape characteristics of machine-picked fresh tea leaves, including leaf length, leaf spread, weight and rolling friction coefficient of fresh tea leaves, the fresh tea leaves are preliminarily sorted into grade I, grade II, grade III, grade IV, grade V and others;

[0029] S2: Through the multi-channel acquisition mode, the image information of fresh tea leaves of grades I to IV is collected respectively. After image preprocessing, the characteristic data of fresh tea leaves are extracted, including basic morphological features (A), such as area (A1), perimeter (A2), major axis (A3), minor axis (A4), etc., and complex morphological features (B), including gray value (B1), rectangularity (B2), circularity (B3), compactness (B4), slenderness (B5), etc.;

[0030] S3: Extract important features of fresh tea leaves, calculate the correlation between each feature of the basic morphological features and complex morphological features of fresh tea leaves and the corresponding features in the database, and extract the features with the greatest correlation respectively;

[0031] S4: According to the features extracted in S3, the fresh tea leaves of each grade are judged and selected through the association algorithm. If the fresh tea leaves meet the grade, no rejection instruction is given; if the fresh tea leaves do not meet the grade, a rejection instruction is given. The sorted tea leaves are divided into selected grade I, selected grade II, selected grade III, and selected grade IV.

[0032] S5: The fresh tea leaves rejected at each level are collected and sorted a second time.

[0033] Furthermore, in the step S1, the fresh tea leaves are preliminarily sorted into grade I, grade II, grade III, grade IV, grade V and other standards;

[0034] Among them: the main component of grade I tea leaves is a single bud; the main component of grade II tea leaves is one bud and one leaf; the main component of grade III tea leaves is one bud and two leaves; the main component of grade IV tea leaves is one bud and three leaves; the main component of grade V tea leaves is one bud and four leaves or one bud and five leaves.

[0035] Furthermore, in step S3, the important features of the fresh tea leaves are extracted in the following manner:

[0036] The basic morphological feature data (A1~A4) and complex morphological feature data (B1~B5) of fresh tea leaves are respectively calculated with the corresponding feature data of fresh tea leaves of each grade of the variety in the database module to obtain corresponding correlation coefficients kA1~kA4, kB1~kB5, where 1, 2, 3, 4, 5 represent the various grades of tea, namely grade I, grade II, grade III, grade IV, grade V and others, kAi is the correlation coefficient between the basic morphological features of fresh tea leaves and the corresponding feature data of samples in the database, kAi∈[0,1], i=1,2,3,4; kBj is the correlation coefficient between the complex morphological features of fresh tea leaves and the corresponding feature data of samples in the database, kBj∈[0,1], j=1,2,3,4,5; the two feature data sets with the largest correlation are extracted respectively: Amax∈{A1,A2,A3,A4} and Bmax∈{B1,B2,B3,B4,B5}.

[0037] Furthermore, in step S4, the grade of the fresh tea leaves is determined as follows:

[0038] Calculate the determination coefficient K = kA*0.6+kB*0.4, where kA is the correlation coefficient calculated by Amax, and kB is the correlation coefficient calculated by Bmax; when K>K0, the fresh tea leaves are determined to meet the grade and no rejection instruction is given; when K≤K0, the fresh tea leaves are determined to not meet the grade and a rejection instruction is given, where K0∈[0.6,1], and the value is determined comprehensively based on the type of tea, feature correlation and classification accuracy requirements.

[0039] Compared with the prior art, the beneficial effect of the machine vision-based intelligent sorting method for machine-picked fresh tea leaves of the present invention is that the tea leaves are classified into grades I-V and other categories by classifying the fresh tea leaves based on shape feature parameters (such as leaf length, leaf spread, weight and rolling friction coefficient) in the preliminary sorting stage. This process simplifies the complexity of subsequent sorting, provides a clear basis for further refined classification, and reduces the burden of data processing. Secondly, in the image information acquisition and analysis stage, through multi-channel acquisition mode and image preprocessing technology, basic morphological features including area, perimeter, major and minor axes, as well as complex morphological features such as grayscale value, rectangularity, and circularity can be extracted from the fresh tea leaves. These features are matched with the standard data in the database for correlation, and the most recognizable features are screened out for accurate judgment. This design based on multi-dimensional feature extraction and correlation analysis greatly improves the scientificity and reliability of the sorting results, can adapt to the differentiated characteristics of a variety of teas, and improves the intelligence level of sorting. Finally, through the execution of the association algorithm and sorting instructions, fresh tea leaves can be carefully selected and removed with high precision, and the removed parts can be sorted again to reduce resource waste. This double sorting mechanism not only ensures the quality of high-grade fresh tea leaves, but also effectively utilizes low-grade and marginal tea leaves, maximizing the sorting value. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0041] Figure 1 A functional block diagram of a machine vision-based intelligent sorting system for machine-picked fresh tea leaves provided in an embodiment of the present invention;

[0042] Figure 2 A flowchart of a method for intelligent sorting of machine-picked fresh tea leaves based on machine vision provided by an embodiment of the present invention;

[0043] Figure 3 A schematic diagram of the structure of a machine vision-based intelligent sorting system for machine-picked fresh tea leaves provided in an embodiment of the present invention;

[0044] Figure 4 A schematic structural diagram of a primary sorting module provided in an embodiment of the present invention.

[0045] Among them, 100, discrete feeding module; 200, primary sorting module; 220, vibration screening device; 230, recycling unit; 231, first recycling window; 232, second recycling window; 233, third recycling window; 234, fourth recycling window; 235, fifth recycling window; 300, intelligent sorting module; 310, first sorting end; 320, second sorting end; 330, third sorting end; 340, fourth sorting end; 350, fifth sorting end. DETAILED DESCRIPTION

[0046] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to be able to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, in the absence of conflict, the embodiments of the present invention and the features described in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0047] Tea is a beverage made from the tender buds, leaves or stems of the tea plant. It is rich in a variety of health-promoting ingredients such as tea polyphenols, caffeine, amino acids and vitamins. Tea provides fragrance, quenches thirst and refreshes the mind. It also plays an important social and ceremonial role in different cultures.

[0048] At present, tea leaves are generally picked by machine, especially in large-scale tea gardens. This method has significantly improved the picking efficiency and yield. Machine picking uses advanced mechanical equipment to remove tea leaves from tea trees through vibration, shearing and other methods. Although mechanical picking has obvious advantages in speed and cost, the quality and uniformity of tea leaves may be reduced because it cannot select tea buds as finely as manual picking.

[0049] Although some sorting equipment has emerged in the current market, aiming to replace manual labor to achieve large-scale sorting of machine-picked fresh tea leaves, in actual applications, such equipment has potential risks in the sorting process and may damage the fresh tea leaves. More importantly, the screening results often contain a lot of residual leaves and fragments, affecting the overall quality. In addition, these devices are still insufficient in the grading and processing of fresh tea leaves, and operators are often required to perform secondary grading of the screened fresh tea leaves, which increases labor and time costs.

[0050] In view of this, the present invention proposes a system and method for intelligent sorting of machine-picked fresh tea leaves based on machine vision, aiming to solve the problem in the current technology that tea sorting equipment is prone to damage fresh tea leaves during the sorting process, and the sorting effect is poor, requiring manual secondary sorting, thereby increasing labor costs and time costs.

[0051] like Figure 1 As shown, in some embodiments of the present application, this embodiment provides a machine vision-based intelligent sorting system for machine-picked fresh tea leaves, including: a feeding discrete module 100, a primary sorting module 200, an intelligent sorting module 300 and a database module.

[0052] Specifically, the feeding discrete module 100 includes a negative pressure transmission unit and a feeding unit; wherein, the negative pressure transmission unit discretely adsorbs the fresh tea leaves in the feeding area to the conveyor belt and moves with the conveyor belt to the feeding unit. There is no negative pressure environment in the feeding unit area, and the fresh tea leaves fall freely to the next module due to their own gravity; the primary sorting module 200 is connected to the feeding discrete module 100, and includes a sorting unit, a shaking unit and a recycling unit 230; wherein, the sorting units are graded in sequence according to the shape characteristics of the fresh tea leaves; the sorted fresh tea leaves of each level pass through the recycling units 230 of each level and fall into the next module one by one; the intelligent sorting module 300 is connected to the recycling unit 230 of the primary sorting module 200, and adopts a multi-function system. The method for coordinated sorting of tea leaves through grade channels comprises an image acquisition unit, an image transmission unit, an image analysis unit, a control unit and an air flow blowing unit; wherein the image acquisition unit acquires image information of fresh tea leaves and transmits it to the image analysis unit, determines the type of fresh tea leaves and generates a determination instruction which is transmitted to the control unit, the control unit gives an operation instruction to the air flow blowing unit, the air flow blowing unit executes the operation, and completes the accurate grading of fresh tea leaves; the database module comprises a computer and a data transmission unit, a data trigger unit, a data storage unit and a data index unit, which are used to store and call image information of fresh tea leaves of various varieties at various grades in different forms, and store newly acquired image information of fresh tea leaves.

[0053] It is understandable that the fresh tea leaves are discretely and evenly adsorbed onto the conveyor belt through the negative pressure transmission unit in the feeding discrete module 100, presenting a non-overlapping flat state. This design effectively avoids the problem of leaf stacking affecting the subsequent sorting accuracy, provides standardized initial conditions for the sorting module, and ensures the operational stability of the entire system. Secondly, in the primary sorting module, the tea leaves are primary graded according to the shape characteristics (such as length, width, etc.) of the fresh tea leaves by using a sorting unit composed of 4-level sorting windows, and the tea leaves of different grades are respectively dropped into the next module through the recovery unit 230. This module adopts a step-by-step sorting method to preliminarily classify the fresh tea leaves according to the basic morphological characteristics, providing basic data for subsequent more refined sorting. This grading mechanism combines the coordinated operation of the sorting unit and the transmission unit, so that the system can efficiently process large quantities of fresh tea leaves while reducing the complexity of the primary sorting link. Finally, the intelligent sorting module 300 and the database module jointly realize high-precision fresh tea leaf classification. The intelligent sorting module 300 obtains the image information of fresh tea leaves through the image acquisition unit, and uses the image analysis unit to extract multi-dimensional features, and compares and analyzes the standard morphological data of fresh tea leaves at all levels stored in the database module. Finally, the control unit generates an operation instruction to drive the airflow blowing unit to complete the grading operation. This intelligent sorting method combining machine vision and database can not only accurately determine the type and grade of fresh tea leaves, but also dynamically update and call newly collected image data, enhancing the system's adaptability to multiple varieties of tea.

[0054] Specifically, the feeding discrete module 100 includes: a negative pressure transmission unit consisting of a conveyor belt, a negative pressure chamber and an air compressor, wherein the transmission belt is provided with evenly spaced small holes with a diameter of 1 mm, and each small hole can adsorb fresh tea leaves through the negative pressure chamber; the unloading unit consists of an isolation chamber and a conveyor belt, when the conveyor belt passes through the isolation chamber, the negative pressure effect is released, the fresh tea leaves are no longer adsorbed, and they fall freely to the next unit; the loading area of ​​the entire feeding discrete module 100 is larger than the unloading area to ensure that the sorted fresh tea leaves are quickly dispersed.

[0055] It is understandable that the negative pressure transmission unit utilizes the synergistic effect of the conveyor belt, the negative pressure chamber and the air compressor to perform negative pressure adsorption on the fresh tea leaves through the small holes evenly arranged on the conveyor belt. Each small hole has a diameter of 1mm, which can produce a negative pressure effect suitable for adsorbing fresh tea leaves, ensuring that the fresh tea leaves can be firmly adsorbed on the surface of the conveyor belt. This adsorption mechanism not only avoids the problem of fresh tea leaves slipping or stacking during transportation, but also realizes the stable transportation and preliminary arrangement of tea leaves, providing an orderly basis for subsequent sorting. Secondly, the unloading unit realizes the precise release of fresh tea leaves through the structural design of the isolation chamber. When the conveyor belt passes through the isolation chamber, the negative pressure effect is released, and the fresh tea leaves are separated from the conveyor belt and fall into the next unit in a free fall. This process makes full use of the mechanical design and air pressure principles, and ensures that the fresh tea leaves can be dispersed according to the specified path and state by accurately controlling the timing of adsorption and release. This not only ensures the uniformity of the falling of fresh tea leaves, but also avoids accumulation or damage that may be caused by improper release. Finally, the module as a whole achieves an efficient dispersion effect through the optimized design of the area of ​​the loading area and the unloading area. The design of the loading area being larger than the unloading area increases the distribution space of fresh tea leaves during the negative pressure adsorption stage, thereby reducing the probability of fresh tea leaves piling up. The fresh tea leaves are further concentrated and evenly released through the gradually shrinking unloading area, ensuring the uniformity of dispersion efficiency and quality.

[0056] Specifically, the primary sorting module 200 includes: a sorting unit including a vibration screening device 220 and sorting windows for each level of tea leaves, wherein the inclination angle of the vibration screening device 220 is between [25°, 40°], and the vibration frequency is between [25Hz, 35Hz]; the screen surface of the vibration screening device is composed of 4-level sorting windows composed of different screen holes arranged with different densities, and the area of ​​each sorting window is different, wherein the area gradually decreases from the first-level sorting area to the fourth-level sorting area; the inclination angle, vibration frequency and the screen hole size, distribution area and buffer zone area of ​​each level of tea sorting windows are adjusted according to the type and characteristics of fresh tea leaves, and the reference characteristic indicators are the leaf length, leaf spread, weight and rolling friction coefficient of the fresh tea leaves; the recovery unit 230 is connected to the sorting windows at each level, respectively receives the sorted fresh tea leaves at each level, and uses the fresh tea leaves' own gravity to transmit them one by one to the next module through a smooth track.

[0057] Preferably, the sorting windows at each level are specifically a first recycling window 231 , a second recycling window 232 , a third recycling window 233 , a fourth recycling window 234 and a fifth recycling window 235 .

[0058] It is understandable that by setting the inclination angle of the screen surface of the vibration screening device 220 between 25° and 40°, combined with the change of the vibration frequency in the range of 25Hz to 35Hz, the fresh tea leaves are dispersed on the screen surface by mechanical vibration and gravity. By controlling the vibration frequency and inclination angle, the fresh tea leaves are moved orderly on the screen surface and slide to the corresponding sorting window. This vibration screening method can not only effectively reduce the possibility of fresh tea leaves piling up, but also flexibly adjust the parameters according to the characteristics of the leaves to ensure the efficiency and accuracy of the sorting process. Secondly, the design of the multi-level sorting window utilizes the gradual change principle of the mesh density and area to achieve the graded screening of fresh tea leaves. The screen surface is composed of 4-level sorting windows with different mesh densities. The mesh decreases step by step from the first to the fourth level, and the area of ​​the sorting window also gradually decreases, so that the fresh tea leaves are graded through different windows according to their size, shape and weight characteristics. The design parameters of the mesh and the window can be dynamically adjusted according to the characteristics of the fresh tea leaves (such as leaf length, leaf spread, weight, rolling friction coefficient, etc.), which enhances the adaptability of the system to different types of fresh tea leaves. This gradual screening mechanism can quickly separate different grades of fresh tea leaves while ensuring the accuracy and efficiency of the screening results. Finally, the recovery unit 230 achieves efficient transportation of the sorted fresh tea leaves through gravity transmission and track guidance. The fresh tea leaves in each sorting window are received by the recovery unit 230, and the fresh tea leaves slide naturally down the smooth track under the action of gravity, and are transferred to the next module one by one. This design simplifies the transportation process of fresh tea leaves, avoids damage to tea leaves caused by unnecessary mechanical operations, and ensures the separation status of fresh tea leaves of different grades, ensuring the working efficiency and accuracy of subsequent sorting modules.

[0059] Specifically, the intelligent sorting module 300 includes: an image acquisition unit including a trigger device and a high-speed camera device. When the fresh tea leaves pass by, the trigger device transmits a signal to the high-speed camera device for image acquisition. The frame rate of the high-speed camera device cannot be lower than 100fps; an image analysis unit including a computer and an image preprocessing algorithm, a feature extraction algorithm, a pattern recognition algorithm, a decision-making algorithm and a data transmission interface. The unit is associated with a database module; wherein the image analysis unit performs preprocessing such as noise reduction, enhancement, graying and segmentation on the received images, and then extracts the basic morphological features of the fresh tea leaves, including the basic shape. The method comprises the following steps: determining the image characteristics of fresh tea leaves of different grades of the variety by calling the image characteristics of fresh tea leaves of different grades in the database module, and making decision instructions; the control unit comprises a computer, a data transmission channel and a control switch, which is connected to the image analysis unit, and after receiving the judgment instruction of the image analysis unit, transmits the data information to the control switch; the airflow blowing unit is connected to the control switch, and comprises an air blowing device and a valve switch, and blows out an airflow of a certain intensity according to the instruction of the control unit.

[0060] It is understandable that the image acquisition unit is composed of a trigger device and a high-speed camera device. When the fresh tea leaves pass by, the trigger device sends a signal to activate the high-speed camera device for image acquisition. The frame rate of the high-speed camera device is set to no less than 100fps, which can ensure the clear capture of fast-moving fresh tea leaves. This design combining triggering and high-speed shooting ensures the timeliness and stability of image acquisition, and provides high-quality raw data for subsequent feature extraction and analysis. Secondly, the image analysis unit realizes the automatic grading of fresh tea leaves through multi-level image processing and intelligent algorithms. The unit optimizes the collected images using preprocessing algorithms (such as noise reduction, enhancement, graying, segmentation), and extracts the basic morphological features (such as area, perimeter, major axis, minor axis, etc.) and complex morphological features (such as gray value, rectangularity, circularity, compactness, slenderness, etc.) of fresh tea leaves through feature extraction algorithms. Subsequently, the image analysis unit calls the different grade feature information of fresh tea leaves of the same variety stored in the database module, combines the pattern recognition algorithm and the decision-making algorithm, judges the fresh tea leaves, and generates decision instructions. This design based on big data and intelligent algorithms not only improves the accuracy of sorting, but also adapts to the differences in characteristics of different tea varieties. Finally, the control unit and the airflow blowing unit realize the sorting of fresh tea leaves through intelligent command execution and airflow drive. After receiving the judgment command transmitted by the image analysis unit, the control unit transmits the signal to the valve switch of the airflow blowing unit. The airflow blowing unit, through the collaboration of the blowing device and the valve switch, blows out an airflow of suitable intensity according to the sorting requirements of different grades of fresh tea leaves, and completes the precise grading of fresh tea leaves. Through this combination of mechanical and algorithm design, the system can separate fresh tea leaves of different grades in real time and efficiently, provide high-quality sorting results for subsequent processing, and realize the full automation and intelligence of the sorting process.

[0061] Preferably, the air flow blowing unit is provided with a plurality of sorting ends for secondary selection and grading of the fresh tea leaves in each sorting window, wherein the plurality of sorting ends include at least a first sorting end 310, a second sorting end 320, a third sorting end 330, a fourth sorting end 340 and a fifth sorting end 350.

[0062] Compared with the prior art, the machine vision-based intelligent sorting system for fresh tea leaves picked by the machine of the present invention evenly distributes the fresh tea leaves and presents a non-overlapping state through the feeding discrete module 100, which provides ideal input conditions for subsequent sorting and effectively avoids the recognition errors caused by the stacking of tea leaves in the traditional sorting process. At the same time, the primary sorting module 200 realizes multi-level classification according to the shape characteristics of the fresh tea leaves, so that tea leaves of different levels can enter the next link in an orderly manner, laying the foundation for fine sorting. Such a grading method not only optimizes the sorting process, but also reduces the complexity and error of the initial screening. Secondly, the machine vision technology is introduced through the intelligent sorting module 300, and the image acquisition, transmission and analysis unit are combined to realize the efficient determination and accurate classification of fresh tea leaves. The airflow blowing unit performs the sorting operation according to the instructions of the control unit, so that each fresh tea leaf can be accurately classified. This sorting method based on image analysis not only improves the sorting accuracy, but also can adapt to the morphological differences of different varieties of tea leaves, and has high flexibility and scalability. In addition, the addition of the database module enables the system to store a large amount of fresh tea leaf image information, forming a comprehensive knowledge base for multiple categories, and supporting the dynamic update and call of new data.

[0063] Based on the above, if Figure 2 As shown, the present invention also provides a method for intelligent sorting of machine-picked fresh tea leaves based on machine vision, comprising the following steps:

[0064] S1: Based on the shape characteristics of machine-picked fresh tea leaves, including leaf length, leaf spread, weight and rolling friction coefficient of fresh tea leaves, the fresh tea leaves are preliminarily sorted into grade I, grade II, grade III, grade IV, grade V and others.

[0065] Specifically, in step S1, fresh tea leaves are preliminarily sorted into grade I, grade II, grade III, grade IV, grade V and other standards; among which: the main component of grade I fresh tea leaves is single bud; the main component of grade II fresh tea leaves is one bud and one leaf; the main component of grade III fresh tea leaves is one bud and two leaves; the main component of grade IV fresh tea leaves is one bud and three leaves; the main component of grade V fresh tea leaves is one bud and four leaves and one bud and five leaves.

[0066] It is understandable that the grading of tea leaves is achieved by analyzing its physical parameters such as leaf length, leaf spread, weight and rolling friction coefficient. Specifically, these shape characteristics are used as the basic basis to classify the development status of fresh tea leaves from buds to leaves into different grades. By quantitatively evaluating these characteristics, the initial sorting of fresh tea leaves can be effectively achieved, and they can be divided into grades I to V, as well as other categories according to the number and development of buds and leaves. This method can provide accurate and reliable standards in the initial sorting stage, thereby providing data support for subsequent fine sorting. In the sorting standard, the division basis of grades I to V is clear, representing different degrees of development of fresh tea leaves. Grade I fresh tea leaves are mainly composed of single buds and belong to the category of tea with the best quality. Grade II to Grade V fresh tea leaves represent single buds with different numbers of leaves. The quality of these grades of tea usually decreases with the increase of leaves. The more leaves they contain, the longer the processing time required for subsequent processing. Through this classification based on the number of leaves, high-quality fresh tea leaves can be quickly and effectively screened out and separated from lower-grade tea leaves, laying the foundation for the precision of post-sorting processing. Finally, by combining quantified physical characteristics with sorting standards, the sorting method can adapt to the differences in different types of fresh tea leaves and when they are picked. By matching the physical characteristics of fresh tea leaves with tea grade standards, the sorting process is not only scientific and reasonable, but can also be flexibly adjusted according to the characteristics of the specific picked tea leaves.

[0067] S2: Through the multi-channel acquisition mode, the image information of fresh tea leaves of grades I to IV is collected respectively. After image preprocessing, the characteristic data of fresh tea leaves are extracted, including basic morphological features (A), such as area (A1), perimeter (A2), major axis (A3), minor axis (A4), etc., and complex morphological features (B), including gray value (B1), rectangularity (B2), roundness (B3), compactness (B4), slenderness (B5), etc.

[0068] S3: Extract important features of fresh tea leaves, calculate the correlation between each feature of the basic morphological features and complex morphological features of fresh tea leaves and the corresponding features in the database, and extract the features with the highest correlation.

[0069] Specifically, in step S3, the important features of fresh tea leaves are extracted as follows: the basic morphological feature data (A1~A4) and complex morphological feature data (B1~B5) of fresh tea leaves are respectively calculated with the corresponding feature data of fresh tea leaves of each grade of the variety in the database module. The corresponding correlation coefficients kA1~kA4, kB1~kB5, wherein 1, 2, 3, 4, 5 represent the various grades of tea, i.e. grade I, grade II, grade III, grade IV, grade V and others; kAi is the correlation coefficient between the basic morphological features of fresh tea leaves and the corresponding feature data of samples in the database, kAi∈[0,1], i=1,2,3,4; kBj is the correlation coefficient between the complex morphological features of fresh tea leaves and the corresponding feature data of samples in the database, kBj∈[0,1], j=1,2,3,4,5; and the two feature data sets with the largest correlation are extracted respectively: Amax∈{A1,A2,A3,A4} and Bmax∈{B1,B2,B3,B4,B5}.

[0070] It is understandable that in step S3, the basic morphological features (such as area, perimeter, major axis, minor axis, etc.) and complex morphological features (such as gray value, rectangularity, circularity, compactness, slenderness, etc.) of fresh tea leaves are first extracted, and these features are used to compare with the corresponding data of fresh tea leaf samples in the database. By calculating the correlation coefficient (kA1-kB5) between each feature and the corresponding variety and grade fresh tea leaf feature data in the database, the system can quantify the degree of association between different features and the variety and grade of fresh tea leaves, thereby providing a scientific basis for subsequent sorting. Secondly, the correlation coefficient calculation ensures that the system can dynamically adjust the matching degree between the specific morphological features of fresh tea leaves and the samples in the database by quantifying the degree of association between the features. The correlation coefficients kAi and kBj between the features are both between 0 and 1, indicating the similarity between different features and sample data. In this way, the system can identify the features that are most closely related to the grade distribution of fresh tea leaves from the basic morphological features (A series) and complex morphological features (B series) of fresh tea leaves, ensuring the accuracy and efficiency of feature screening. Finally, the process of extracting the maximum correlation feature enables the system to accurately classify and judge the fresh tea leaves based on their morphological characteristics (Amax and Bmax). Amax and Bmax represent the maximum correlation features corresponding to the fresh tea leaf varieties and grades in the basic and complex morphological characteristics, respectively.

[0071] S4: Based on the features extracted in S3, the fresh tea leaves of each grade are judged and selected through the association algorithm. If the fresh tea leaves are judged to meet the grade, no rejection instruction is given; if the fresh tea leaves are judged not to meet the grade, a rejection instruction is given. The sorted tea leaves are divided into selected grade I, selected grade II, selected grade III and selected grade IV.

[0072] Specifically, in step S4, the grade of fresh tea leaves is determined as follows: calculate the determination coefficient K = kA*0.6+kB*0.4, where kA is the correlation coefficient calculated by Amax, and kB is the correlation coefficient calculated by Bmax; when K>K0, the fresh tea leaves are determined to meet the grade and no rejection instruction is given; when K≤K0, the fresh tea leaves are determined to not meet the grade and a rejection instruction is given, where K0∈[0.6,1], and the value is determined comprehensively based on the type of tea, feature relevance and classification accuracy requirements.

[0073] It can be understood that in step S4, the grade of fresh tea leaves is determined by calculating the determination coefficient K, which is obtained by weighted combination of the correlation coefficient of basic morphological features (kA) and the correlation coefficient of complex morphological features (kB). Specifically, kA and kB represent the correlation of Amax and Bmax features extracted from S3, respectively, and these features reflect the degree of matching between fresh tea leaves and samples in the database. By assigning a weight of 60% to kA and a weight of 40% to kB, the determination coefficient K obtained integrates the performance of fresh tea leaves in morphological characteristics, thereby achieving an accurate assessment of the grade of fresh tea leaves. Secondly, the setting of the determination coefficient K ensures that the system can compare the characteristic values ​​of fresh tea leaves with the standards in the database, and determine whether the fresh tea leaves meet a specific grade by setting the threshold value K0. When K is greater than the threshold value K0, the fresh tea leaves are determined to meet the grade and no elimination is required; when K is less than or equal to K0, the fresh tea leaves are considered to not meet the grade, and the system will generate an elimination instruction. This threshold K0 can be adjusted within the range of [0.6,1] and is determined comprehensively based on the type of tea, feature relevance, and accuracy of classification requirements, thereby ensuring the accuracy and adaptability of sorting. Finally, based on the sorting mechanism of the determination coefficient, the system can effectively classify fresh tea leaves into different grades. Through the determination coefficient K, fresh tea leaves will be accurately classified into selected grades I, II, III, and IV. Fresh tea leaves that meet the grade standards will be retained, while those that do not meet the standards will be eliminated.

[0074] S5: The fresh tea leaves rejected at each level are collected and sorted a second time.

[0075] It can be understood that a machine vision-based intelligent sorting method for machine-picked fresh tea leaves in an embodiment of the present invention, by classifying fresh tea leaves based on shape feature parameters (such as leaf length, leaf spread, weight and rolling friction coefficient) in the preliminary sorting stage, preliminarily divides the tea leaves into grades I-V and other categories. This process simplifies the complexity of subsequent sorting, provides a clear basis for further refined classification, and reduces the burden of data processing. Secondly, in the image information acquisition and analysis stage, through multi-channel acquisition mode and image preprocessing technology, basic morphological features including area, perimeter, major and minor axes, as well as complex morphological features such as grayscale value, rectangularity, and circularity can be extracted from fresh tea leaves. These features are matched with the standard data in the database for correlation, and the most recognizable features are selected for accurate judgment. This design based on multi-dimensional feature extraction and correlation analysis greatly improves the scientificity and reliability of the sorting results, and can adapt to the differentiated characteristics of a variety of teas, and improves the intelligence level of sorting. Finally, through the execution of the association algorithm and sorting instructions, fresh tea leaves can be carefully selected and removed with high precision, and the removed parts can be sorted again to reduce resource waste. This double sorting mechanism not only ensures the quality of high-grade fresh tea leaves, but also effectively utilizes low-grade and marginal tea leaves, maximizing the sorting value.

[0076] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0077] The present application is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0078] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0079] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0080] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A machine vision-based intelligent sorting system for machine-picked fresh tea leaves, characterized in that: include: The feeding discrete module includes a negative pressure conveying unit and a feeding unit; wherein the negative pressure conveying unit discretely adsorbs the fresh tea leaves in the feeding area to the conveyor belt and moves with the conveyor belt to the feeding unit. There is no negative pressure environment in the feeding unit area, and the fresh tea leaves fall freely to the next module due to their own gravity. The primary sorting module is connected to the feeding discrete module, and includes a sorting unit, a shaking unit and a recycling unit; wherein the sorting unit is composed of 4 levels of sorting windows, each level of sorting window includes sieve holes of different sizes and densities, and buffer zones are set between the sorting windows for isolation, and the fresh tea leaves are graded in sequence according to their shape characteristics; the fresh tea leaves of each level after sorting pass through the recycling units of each level and fall into the next module one by one; An intelligent sorting module is connected to the recycling unit of the primary sorting module, and adopts a multi-stage channel collaborative sorting method, including an image acquisition unit, an image transmission unit, an image analysis unit, a control unit and an airflow blowing unit; wherein the image acquisition unit acquires image information of fresh tea leaves, and transmits it to the image analysis unit, determines the type of fresh tea leaves and generates a determination instruction to transmit to each level of control unit, the control unit makes an operation instruction to the airflow blowing unit, and the airflow blowing unit performs the operation to complete the accurate classification of fresh tea leaves; The database module includes a computer and a data transmission unit, a data trigger unit, a data storage unit and a data index unit, which are used to store and call image information of different forms of fresh tea leaves of various varieties and grades, and store newly collected image information of fresh tea leaves.

2. The machine vision-based intelligent sorting system for fresh tea leaves picked by machines according to claim 1, characterized in that: The discrete feeding module comprises: The negative pressure transmission unit is composed of a conveyor belt, a negative pressure chamber and an air compressor, wherein the conveyor belt is provided with evenly spaced small holes with a diameter of 1 mm, and each small hole in the negative pressure chamber can absorb fresh tea leaves; The unloading unit is composed of an isolation chamber and a conveyor belt. When the conveyor belt passes through the isolation chamber, the negative pressure effect is released, the fresh tea leaves are no longer adsorbed, and they fall freely to the next unit. The area of ​​the loading region of the entire loading discrete module is larger than the area of ​​the unloading region, so as to ensure that the sorted fresh tea leaves can be quickly dispersed.

3. The machine vision-based intelligent sorting system for fresh tea leaves picked by machines as claimed in claim 1, characterized in that: The primary sorting module comprises: The sorting unit comprises a vibration screening device and sorting windows for each level of tea leaves, wherein the inclination angle of the vibration screening device is between [25°, 40°], and the vibration frequency is between [25Hz, 35Hz]; The screen surface of the vibrating screen device is composed of four-level sorting windows composed of different screen holes arranged at different densities, and each sorting window has a different area, which gradually decreases from the first-level sorting area to the fourth-level sorting area; The tilt angle, vibration frequency, sieve hole size, distribution area and buffer zone area of ​​each level of tea sorting window are adjusted according to the type and characteristics of fresh tea leaves, and the reference characteristic indicators are leaf length, leaf spread, weight and rolling friction coefficient of fresh tea leaves; The recovery unit is connected with the sorting windows at each level, and receives the sorted fresh tea leaves at each level respectively, and utilizes the fresh tea leaves' own gravity to transport them one by one to the next module through a smooth track.

4. The machine vision-based intelligent sorting system for fresh tea leaves picked by machines as claimed in claim 1, characterized in that: The intelligent sorting module comprises: The image acquisition unit includes a trigger device and a high-speed camera device. When the fresh tea leaves pass by, the trigger device transmits a signal to the high-speed camera device for image acquisition. The frame rate of the high-speed camera device cannot be lower than 100fps. The image analysis unit includes a computer and an image preprocessing algorithm, a feature extraction algorithm, a pattern recognition algorithm, a decision-making algorithm and a data transmission interface, and the unit is associated with a database module; wherein the image analysis unit extracts the basic morphological features of the fresh tea leaves after preprocessing the received images such as noise reduction, enhancement, graying and segmentation, including basic morphological features such as area, perimeter, major axis, minor axis, etc., and complex morphological features including gray value, rectangularity, circularity, compactness, slenderness, etc.; by calling the image features of fresh tea leaves of different grades of the variety in the database module, the collected fresh tea leaves are judged and a decision instruction is made; The control unit includes a computer, a data transmission channel and a control switch, and is connected to the image analysis unit. After receiving the judgment instruction of the image analysis unit, the control unit transmits the data information to the control switch; The airflow blowing unit is connected to the control switch, and comprises an air blowing device and a valve switch, and blows out an airflow of a certain intensity according to the instruction of the control unit.

5. A method for intelligent sorting of machine-picked fresh tea leaves based on machine vision, applicable to a system for intelligent sorting of machine-picked fresh tea leaves based on machine vision as claimed in any one of claims 1 to 4, characterized in that: include: S1: According to the shape characteristics of machine-picked fresh tea leaves, including the number of leaf buds, leaf length, leaf spread, weight and rolling friction coefficient of the fresh tea leaves, the fresh tea leaves are preliminarily sorted into grade I, grade II, grade III, grade IV, grade V and others; S2: Through the multi-channel acquisition mode, the image information of fresh tea leaves of grades I to IV is collected respectively. After image preprocessing, the characteristic data of fresh tea leaves are extracted, including basic morphological features (A), such as area (A1), perimeter (A2), major axis (A3), minor axis (A4), etc., and complex morphological features (B), including gray value (B1), rectangularity (B2), circularity (B3), compactness (B4), slenderness (B5), etc.; S3: Extract important features of fresh tea leaves, calculate the correlation between each feature of the basic morphological features and complex morphological features of fresh tea leaves and the corresponding features in the database, and extract the features with the greatest correlation respectively; S4: Based on the features extracted in S3, the fresh tea leaves of each grade sorted out in the primary process are identified and selected through an association algorithm. When it is determined that the fresh tea leaves meet a certain grade, instructions are sent to the tea sorting organization at that grade to select and grade the tea leaves of each grade. The sorted tea leaves are divided into selected grade I, selected grade II, selected grade III, and selected grade IV.

6. The method for intelligent sorting of machine-picked fresh tea leaves based on machine vision according to claim 5 is characterized in that: In step S1, the fresh tea leaves are preliminarily sorted into grade I, grade II, grade III, grade IV, grade V and other standards; Among them: the main component of grade I tea leaves is a single bud; the main component of grade II tea leaves is one bud and one leaf; the main component of grade III tea leaves is one bud and two leaves; the main component of grade IV tea leaves is one bud and three leaves; the main component of grade V tea leaves is one bud and four leaves or one bud and five leaves.

7. The method for intelligent sorting of machine-picked fresh tea leaves based on machine vision according to claim 5, characterized in that: In step S3, the important features of the fresh tea leaves are extracted in the following manner: The basic morphological feature data (A1~A4) and complex morphological feature data (B1~B5) of fresh tea leaves are respectively calculated with the corresponding feature data of fresh tea leaves of each grade of the variety in the database module to obtain corresponding correlation coefficients kA1~kA4, kB1~kB5, where 1, 2, 3, 4, 5 represent the various grades of tea, namely grade I, grade II, grade III, grade IV, grade V and others, kAi is the correlation coefficient between the basic morphological features of fresh tea leaves and the corresponding feature data of samples in the database, kAi∈[0,1], i=1,2,3,4; kBj is the correlation coefficient between the complex morphological features of fresh tea leaves and the corresponding feature data of samples in the database, kBj∈[0,1], j=1,2,3,4,5; the two feature data sets with the largest correlation are extracted respectively: Amax∈{A1,A2,A3,A4} and Bmax∈{B1,B2,B3,B4,B5}.

8. The method for intelligent sorting of machine-picked fresh tea leaves based on machine vision according to claim 5, characterized in that: In step S4, the method for determining the grade of the fresh tea leaves is: Calculate the determination coefficient K = kA*0.6+kB*0.4, where kA is the correlation coefficient calculated by Amax, and kB is the correlation coefficient calculated by Bmax; when K>K0, the fresh tea leaves are determined to meet the grade and no rejection instruction is given; when K≤K0, the fresh tea leaves are determined to not meet the grade and a rejection instruction is given, where K0∈[0.6,1], and the value is determined comprehensively based on the type of tea, feature correlation and classification accuracy requirements.

Images