Cigarette paper quality detection method, device, system and equipment based on machine vision

Abstract

The application provides a cigarette paper quality detection method, device, system and equipment based on machine vision, which comprises the following steps: collecting a to-be-detected cigarette paper image, and calibrating a spectral response curve of the to-be-detected cigarette paper image through an RGB color model, so that the RGB value of the to-be-detected cigarette paper image is converted into light reflectivity; converting the to-be-detected cigarette paper image into a corresponding color space based on the light reflectivity, and performing image segmentation based on the color space, so as to separate the background and the to-be-detected cigarette paper in the to-be-detected cigarette paper image; and extracting the component features of the to-be-detected cigarette paper according to the color difference between the component of the to-be-detected cigarette paper and the background, so as to obtain the detection result of the component of the to-be-detected cigarette paper. The application can automatically and objectively measure the content of cut tobacco and tobacco sheet and other related parameters in the cigarette paper based on machine vision, and is used for judging the quality of the cigarette paper.

Description

Technical Field

[0001] This application relates to the tobacco industry, and in particular to a method, apparatus, system and equipment for quality inspection of cigarette paper based on machine vision. Background Technology

[0002] Specialty cigarette paper containing shredded tobacco and tobacco sheets is a completely new product. Currently, there is no evidence of its commercial production, nor are there any reports of its applications. Therefore, there are no standard methods or instruments for measuring the content, morphology, and distribution of shredded tobacco and tobacco sheets in this specialty cigarette paper.

[0003] Based on their principles, the main quantitative measurement methods can be divided into two categories: visual inspection and image and machine vision measurement technology. Among them, visual inspection, such as the determination of dust content in cigarette paper, has the problems of overly subjective quantitative rules and large errors in the test results, resulting in poor data comparability and inaccurate result judgment. At the same time, considering the distribution of tobacco fiber, visual inspection is basically not feasible and has very low efficiency.

[0004] Therefore, there is an urgent need for a method and device that can automatically and objectively measure the quality indicators of cigarette paper, and to automatically measure the content of tobacco shreds and tobacco sheets and other related parameters in cigarette paper. Summary of the Invention

[0005] In view of the shortcomings of the prior art described above, the purpose of this application is to provide a method, apparatus, system and equipment for detecting the quality of cigarette paper based on machine vision, so as to solve the technical problem that the quality indicators of cigarette paper cannot be measured automatically and objectively in the prior art.

[0006] To achieve the above and other related objectives, this application provides a machine vision-based method for inspecting the quality of cigarette paper. The method includes: acquiring an image of cigarette paper to be tested, and calibrating the spectral response curve of the image of the cigarette paper to be tested using an RGB color model to convert the RGB values ​​of the image of the cigarette paper to be tested into light reflectance; converting the image of the cigarette paper to be tested into a corresponding color space based on the light reflectance, and performing image segmentation based on the color space to separate the background and the cigarette paper to be tested in the image of the cigarette paper to be tested; and extracting the component features of the cigarette paper to be tested based on the color difference between the components of the cigarette paper to be tested and the background to obtain the detection results of the components of the cigarette paper to be tested.

[0007] In one embodiment of this application, the method further includes: acquiring local background color parameters of the cigarette paper image to be tested, in order to compensate for the non-uniformity of illumination and field of view.

[0008] In one embodiment of this application, the step of converting the image of the cigarette paper to be tested into a corresponding color space based on the light reflectance, and performing image segmentation based on the color space, includes: converting the RGB color model of the image of the cigarette paper to be tested into an HSV color model based on the light reflectance, and performing color difference analysis in the HSV color space to identify the cigarette paper to be tested; preprocessing the image of the cigarette paper to be tested, performing image segmentation through HSV parameter values ​​to distinguish the components of the cigarette paper to be tested from the background; and separating the interconnected components of the different components of the cigarette paper to be tested, and independently identifying each component of the cigarette paper to be tested.

[0009] In one embodiment of this application, the preprocessing includes noise reduction and filtering to improve the quality of the cigarette paper image to be tested.

[0010] In one embodiment of this application, the image segmentation based on the color space to separate the background and the cigarette paper to be tested in the image of the cigarette paper to be tested includes: setting a preset range of color parameters for the cigarette paper to be tested, classifying images within the preset range of color parameters as the cigarette paper to be tested, and classifying images outside the preset range of color parameters as the background; or, setting a preset value of color difference between the cigarette paper to be tested and the background, classifying images equal to or exceeding the preset value of color difference as the cigarette paper to be tested, and classifying images not exceeding the preset value of color difference as the background.

[0011] In one embodiment of this application, the components of the cigarette paper to be tested include: tobacco shreds, tobacco sheets, EBA, dust, and pulp stains.

[0012] In one embodiment of this application, the cigarette paper image to be tested is a two-dimensional network structure, and the components of the cigarette paper to be tested are the portions between two nodes in the network structure; wherein, the distance between each node in the cigarette paper image to be tested represents the length of the tobacco shreds; the average width of the objects between each node in the cigarette paper image to be tested represents the width of the tobacco shreds; the area fraction of the tobacco shreds represents the content of the tobacco shreds; and the standard deviation of the area fraction of the tobacco shreds in a local part of the cigarette paper image to be tested represents the distribution characteristics of the tobacco shreds.

[0013] To achieve the above and other related objectives, this application provides a machine vision-based cigarette paper quality inspection device, comprising: an image acquisition module for acquiring an image of the cigarette paper to be tested, and calibrating the spectral response curve of the image of the cigarette paper to be tested using an RGB color model to convert the RGB values ​​of the image of the cigarette paper to be tested into light reflectance; an image processing module for converting the image of the cigarette paper to be tested into a corresponding color space based on the light reflectance, and performing image segmentation based on the color space to separate the background and the cigarette paper to be tested in the image of the cigarette paper to be tested; and extracting the component features of the cigarette paper to be tested based on the color difference between the components of the cigarette paper to be tested and the background to obtain the detection results of the components of the cigarette paper to be tested.

[0014] To achieve the above and other related objectives, this application provides a machine vision-based cigarette paper quality inspection system, comprising: an illumination device for providing illumination light with adjustable color temperature and intensity; an imaging device for projecting the cigarette paper to be tested onto the sensor plane of a camera device; a camera device for converting the light intensity digitally into an image of the cigarette paper to be tested; an image processing device as described in claim 8 for detecting the quality of the cigarette paper based on machine vision; and a paper feeding device for driving the cigarette paper to be tested to move at a uniform speed.

[0015] To achieve the above and other related objectives, this application provides a computer device, including: a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program stored in the memory to cause the device to perform the method described above.

[0016] In summary, the machine vision-based method, apparatus, system, and equipment for detecting the quality of cigarette paper provided in this application have the following beneficial effects: This application can automatically and objectively measure the content of tobacco shreds and tobacco sheets and other related parameters in cigarette paper, which can be used to determine the quality of cigarette paper. Attached Figure Description

[0017] Figure 1 The diagram shown is a flowchart illustrating a machine vision-based cigarette paper quality inspection method according to one embodiment of this application.

[0018] Figure 2A The image shown is an image of the cigarette paper to be tested, collected in one embodiment of this application.

[0019] Figure 2B The diagram shows the correspondence between a cigarette paper image and the HSV color space in one embodiment of this application.

[0020] Figure 2C The diagram shows the display of the cigarette paper components in the HSV color space according to one embodiment of this application.

[0021] Figure 3 This is a cigarette paper composition analysis report shown in one embodiment of this application.

[0022] Figure 4 The diagram shown is a schematic representation of a machine vision-based cigarette paper quality inspection device according to one embodiment of this application.

[0023] Figure 5 The diagram shown is an actual application illustration of a machine vision-based cigarette paper quality inspection system according to one embodiment of this application.

[0024] Figure 6 The diagram shown is a structural schematic of a computer device according to an embodiment of this application. Detailed Implementation

[0025] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, unless otherwise specified, the following embodiments and features described therein can be combined with each other.

[0026] It should be noted that in the following description, reference is made to the accompanying drawings, which illustrate several embodiments of this application. It should be understood that other embodiments may also be used, and changes in mechanical composition, structure, electrical system, and operation may be made without departing from the spirit and scope of this application. The following detailed description should not be considered limiting, and the scope of the embodiments of this application is defined only by the claims of the published patent. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application. Spatially related terms, such as “upper,” “lower,” “left,” “right,” “below,” “below,” “lower part,” “above,” “upper part,” etc., may be used herein to illustrate the relationship between one element or feature shown in the figures and another element or feature.

[0027] Throughout this specification, unless otherwise expressly specified and limited, the terms "installation," "connection," "linking," "fixing," and "holding" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0028] Furthermore, as used herein, the singular forms “a,” “an,” and “the” are intended to include the plural forms as well, unless the context indicates otherwise. The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data used can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. It should be further understood that the terms “comprising,” “including,” indicate the presence of the stated features, operations, elements, components, items, kinds, and / or groups, but do not exclude the presence, occurrence, or addition of one or more other features, operations, elements, components, items, kinds, and / or groups. The terms “or” and “and / or” as used herein are to be interpreted as inclusive, or mean any one or any combination thereof. Thus, “A, B, or C” or “A, B, and / or C” means “any one of: A; B; C; A and B; A and C; B and C; A, B, and C.” An exception to this definition will only occur if the combination of elements, functions, or operations is inherently mutually exclusive in some way.

[0029] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for explaining the present invention and are not intended to limit the invention.

[0030] To address the existing problems, this application proposes a machine vision-based method, apparatus, system, and equipment for detecting the quality of cigarette paper, used to determine the quality of cigarette paper and to solve the technical problem that existing technologies cannot automatically and objectively measure the quality indicators of cigarette paper.

[0031] like Figure 1 The diagram shown is a flowchart illustrating a machine vision-based cigarette paper quality inspection method according to an embodiment of this application. The method includes the following steps:

[0032] Step S1: Acquire an image of the cigarette paper to be tested, and calibrate the spectral response curve of the cigarette paper image using an RGB color model to convert the RGB values ​​of the cigarette paper image into light reflectance.

[0033] It should be noted that the image of the cigarette paper to be tested needs to be acquired under preset backing and lighting conditions to ensure controllability of variables and improve measurement accuracy. Combined with Figure 2A It can be seen that this is the image of the cigarette paper to be tested that was collected.

[0034] Specifically, the preset backing conditions use a white, opaque backing material to maintain constant measurement conditions, thereby improving measurement accuracy and stability. The preset lighting conditions use a white light source with adjustable color temperature and light intensity, such as a white LED ring light source.

[0035] It should be noted that the cigarette paper to be tested is a special cigarette paper containing tobacco shreds and tobacco sheets. The main quality indicators of the cigarette paper are the content, morphology, coverage and corresponding distribution of tobacco shreds and tobacco sheets.

[0036] Step S2: Based on the light reflectance, convert the image of the cigarette paper to be tested into the corresponding color space, and perform image segmentation based on the color space to separate the background and the cigarette paper to be tested in the image of the cigarette paper to be tested.

[0037] In one embodiment of this application, the step of converting the image of the cigarette paper to be tested into a corresponding color space based on the light reflectance, and performing image segmentation based on the color space, includes: converting the RGB color model of the image of the cigarette paper to be tested into an HSV color model based on the light reflectance, and performing color difference analysis in the HSV color space to identify the cigarette paper to be tested; preprocessing the image of the cigarette paper to be tested, performing image segmentation through HSV parameter values ​​to distinguish the components of the cigarette paper to be tested from the background; and separating the interconnected components of the different components of the cigarette paper to be tested, and independently identifying each component of the cigarette paper to be tested.

[0038] like Figure 2B The diagram shown illustrates the correspondence between a cigarette paper image and the HSV color space in one embodiment of this application. Figure 2C The diagram shows the display of the cigarette paper components in the HSV color space according to one embodiment of this application.

[0039] In one embodiment of this application, the step of performing image segmentation based on the color space to separate the background and the cigarette paper to be tested in the image of the cigarette paper to be tested includes: setting a preset range of color parameters for the cigarette paper to be tested, classifying images within the preset range of color parameters as the cigarette paper to be tested, and classifying images outside the preset range of color parameters as the background; or, setting a preset value of color difference between the cigarette paper to be tested and the background, classifying images equal to or exceeding the preset value of color difference as the cigarette paper to be tested, and classifying images not exceeding the preset value of color difference as the background.

[0040] It should be noted that this application provides at least two methods for identifying the components of the cigarette paper to be tested:

[0041] Method 1: Fully customizable settings; set the preset range of color parameters for the components of the cigarette paper to be tested, that is, fully customize the values ​​of color gamut (H), saturation (S), and brightness (V) corresponding to the HSV color model, and classify images that fall within the preset range of color parameters as components of the cigarette paper to be tested, and images that do not fall within the preset range of color parameters as background.

[0042] Method 2: Semi-automatic recognition; compare the color of each pixel in the image of the cigarette paper to be tested with the background, and identify pixels with color differences exceeding a preset range as components of the cigarette paper to be tested.

[0043] In one embodiment of this application, the preprocessing includes noise reduction and filtering to improve the quality of the cigarette paper image to be tested.

[0044] It should be noted that the components of the cigarette paper to be tested include: tobacco shreds, tobacco sheets, EBA, dust, and pulp stains.

[0045] In one embodiment of this application, the method further includes: acquiring local background color parameters of the cigarette paper image to be tested, in order to compensate for the non-uniformity of illumination and field of view.

[0046] Step S3: Based on the color difference between the components of the cigarette paper to be tested and the background, extract the component characteristics of the cigarette paper to be tested to obtain the detection results of the components of the cigarette paper to be tested.

[0047] In one embodiment of this application, the cigarette paper image to be tested is a two-dimensional network structure, and the components of the cigarette paper to be tested are the portions between two nodes in the network structure; wherein, the distance between each node in the cigarette paper image to be tested represents the length of the tobacco shreds; the average width of the objects between each node in the cigarette paper image to be tested represents the width of the tobacco shreds; the area fraction of the tobacco shreds represents the content of the tobacco shreds; and the standard deviation of the area fraction of the tobacco shreds in a local part of the cigarette paper image to be tested represents the distribution characteristics of the tobacco shreds.

[0048] Specifically, the image of the cigarette paper to be tested is divided into several uniform small regions, the percentage of tobacco area in each small region is calculated separately, and the uniformity of tobacco distribution is characterized by the standard deviation of the total area percentage.

[0049] It should be noted that the cigarette paper has a large number of interwoven fibers, and the image of the cigarette paper to be tested constitutes a two-dimensional network. The part between two nodes in the network structure is used as the component of the cigarette paper to be tested for identification.

[0050] Specifically, the components to be tested are separated and identified based on the color difference between each pixel of the cigarette paper image and the corresponding background, in order to obtain, as shown below. Figure 3The analysis report of the components of the cigarette paper to be tested is shown.

[0051] like Figure 4 The diagram shown illustrates a module schematic of a machine vision-based cigarette paper quality inspection device according to an embodiment of this application. The machine vision-based cigarette paper quality inspection device 400 includes:

[0052] The image acquisition module 410 is used to acquire an image of the cigarette paper to be tested, and to calibrate the spectral response curve of the cigarette paper image to be tested using an RGB color model, so that the RGB values ​​of the cigarette paper image to be tested are converted into light reflectance.

[0053] The image processing module 420 is used to convert the image of the cigarette paper to be tested into a corresponding color space based on the light reflectance, and to perform image segmentation based on the color space to separate the background and the cigarette paper to be tested in the image of the cigarette paper to be tested; and to extract the component features of the cigarette paper to be tested based on the color difference between the components of the cigarette paper to be tested and the background, so as to obtain the detection results of the components of the cigarette paper to be tested.

[0054] It should be understood that the division of the various modules in the above device is merely a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, these modules can be implemented entirely in software via processing element calls; they can be fully implemented in hardware; or some modules can be implemented by processing element calls to software, while others are implemented in hardware. For example, the image processing module 420 can be a separate processing element, or it can be integrated into a chip in the above device. Alternatively, it can be stored as program code in the memory of the above device, and its functions can be called and executed by a processing element of the above device. The implementation of other modules is similar. Moreover, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element mentioned here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each of the above modules can be completed through integrated logic circuits in the hardware of the processor element or through software instructions.

[0055] For example, these modules can be one or more integrated circuits configured to implement the above methods, such as one or more Application Specific Integrated Circuits (ASICs), one or more digital signal processors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs). As another example, when a module is implemented using processing element scheduler code, the processing element can be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. Furthermore, these modules can be integrated together to form a system-on-a-chip (SOC).

[0056] like Figure 5 The diagram shown illustrates a practical application of a machine vision-based cigarette paper quality inspection system according to one embodiment of this application. The system includes:

[0057] Lighting devices used to provide lighting with adjustable color temperature and light intensity;

[0058] An imaging device is used to project the cigarette paper to be tested onto the sensor plane of a camera device;

[0059] A camera device is used to convert digital light intensity into an image of the cigarette paper to be tested;

[0060] The image processing device described above (i.e., the machine vision-based cigarette paper quality inspection device) is used to inspect the quality of cigarette paper based on machine vision.

[0061] The paper feeding device is used to drive the cigarette paper to be tested to move at a constant speed.

[0062] It should be noted that the image processing device can perform operations such as... Figure 1 The method shown.

[0063] like Figure 6 The diagram shown illustrates the structure of a computer device 600 according to an embodiment of this application. The computer device 600 includes a memory 610 and a processor 620; the memory 610 stores computer instructions; the processor 620 executes the computer instructions to implement... Figure 1 The method described.

[0064] In some embodiments, the number of the memory 610 and the processor 620 in the computer device 600 can be one or more, while Figure 6 Each example is taken as an instance.

[0065] In one embodiment of this application, the processor 620 in the computer device 600 will perform as follows: Figure 1 The steps described involve loading one or more instructions corresponding to the process of an application into memory 610, and then having processor 620 run the application stored in memory 610, thereby achieving the following: Figure 1 The method described.

[0066] The memory 610 may include random access memory (RAM) or non-volatile memory, such as at least one disk storage device. The memory 610 stores an operating system and operating instructions, executable modules or data structures, or subsets thereof, or extended sets thereof. The operating instructions may include various operation instructions used to implement various operations. The operating system may include various system programs used to implement various basic business processes and handle hardware-based tasks.

[0067] The processor 620 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0068] In some specific applications, the various components of the computer device 600 are coupled together through a bus system, which may include, in addition to a data bus, a power bus, a control bus, and a status signal bus, etc. However, for clarity, in... Figure 6 All kinds of buses are referred to as bus systems.

[0069] In summary, this application provides a machine vision-based method for detecting the quality of cigarette paper, comprising: acquiring an image of cigarette paper to be tested, and calibrating the spectral response curve of the image of the cigarette paper to be tested using an RGB color model to convert the RGB values ​​of the image of the cigarette paper to be tested into light reflectance; converting the image of the cigarette paper to be tested into a corresponding color space based on the light reflectance, and performing image segmentation based on the color space to separate the background and the cigarette paper to be tested in the image of the cigarette paper to be tested; and extracting the component features of the cigarette paper to be tested based on the color difference between the components of the cigarette paper to be tested and the background to obtain the detection results of the components of the cigarette paper to be tested.

[0070] This application is based on the ability of machine vision to automatically and objectively measure the content of tobacco shreds and tobacco sheets in cigarette paper and other related parameters, in order to determine the quality of cigarette paper.

[0071] This application effectively overcomes the various shortcomings of the prior art and has high industrial application value.

[0072] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can 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 those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A machine vision-based method for inspecting the quality of cigarette paper, characterized in that, The method includes: Images of the cigarette paper to be tested are acquired under preset backing and lighting conditions, and the spectral response curve of the cigarette paper image is calibrated using an RGB color model to convert the RGB values ​​of the cigarette paper image into light reflectance. The preset backing conditions use a white, opaque backing material to maintain constant measurement conditions. The preset lighting conditions use a white light source with adjustable color temperature and light intensity. Based on the light reflectance, the image of the cigarette paper to be tested is converted into a corresponding color space, and image segmentation is performed based on the color space to separate the background and the cigarette paper to be tested in the image; wherein, the conversion of the image of the cigarette paper to be tested into a corresponding color space based on the light reflectance and the image segmentation based on the color space includes: Based on the light reflectance, the RGB color model of the cigarette paper image to be tested is converted into an HSV color model, and color difference analysis is performed in the HSV color space to identify the cigarette paper to be tested. The image of the cigarette paper to be tested is preprocessed, and image segmentation is performed using HSV parameter values ​​to distinguish the components of the cigarette paper to be tested from the background. The different components of the cigarette paper to be tested that are interconnected are separated, and each component of the cigarette paper to be tested is independently identified; The step of performing image segmentation based on the color space to separate the background and the cigarette paper in the image of the cigarette paper to be tested includes: Set a preset range for the color parameters of the cigarette paper to be tested, and classify images within the preset range as the cigarette paper to be tested, while classifying images outside the preset range as the background; or... Set a preset value for the color difference between the cigarette paper to be tested and the background. Images that are equal to or exceed the preset value for color difference are classified as the cigarette paper to be tested, while images that do not exceed the preset value for color difference are classified as the background. Based on the color difference between the components of the cigarette paper to be tested and the background, the component features of the cigarette paper to be tested are extracted to obtain the detection results of the components of the cigarette paper to be tested; wherein, the components of the cigarette paper to be tested include: tobacco shreds, tobacco sheets, EBA, dust and pulp spots; the image of the cigarette paper to be tested is a two-dimensional network structure, and the components of the cigarette paper to be tested are the parts between two nodes in the network structure; Wherein, the distance between each node in the cigarette paper image to be tested represents the length of the tobacco shreds; the average width of the objects between each node in the cigarette paper image to be tested represents the width of the tobacco shreds; the area fraction of the tobacco shreds represents the content of the tobacco shreds; and the standard deviation of the area fraction of the tobacco shreds in a local part of the cigarette paper image to be tested represents the distribution characteristics of the tobacco shreds.

2. The machine vision-based cigarette paper quality inspection method according to claim 1, characterized in that, The method further includes: acquiring local background color parameters of the cigarette paper image to be tested in order to compensate for the non-uniformity of illumination and field of view.

3. The machine vision-based cigarette paper quality inspection method according to claim 1, characterized in that, The preprocessing includes noise reduction and filtering to improve the quality of the cigarette paper image to be tested.

4. A machine vision-based cigarette paper quality inspection device, characterized in that, include: The image acquisition module is used to acquire images of the cigarette paper to be tested under preset background conditions and preset lighting conditions, and to calibrate the spectral response curve of the cigarette paper image to be tested using an RGB color model so that the RGB values ​​of the cigarette paper image to be tested are converted into light reflectance. The image processing module is used to convert the image of the cigarette paper to be tested into a corresponding color space based on the light reflectance, and to perform image segmentation based on the color space to separate the background and the cigarette paper to be tested in the image of the cigarette paper to be tested; and to extract the component features of the cigarette paper to be tested based on the color difference between the components of the cigarette paper to be tested and the background, so as to obtain the detection results of the components of the cigarette paper to be tested. The preset backing conditions use a white, opaque backing material to maintain constant measurement conditions; the preset lighting conditions use a white light source with adjustable color temperature and light intensity; the components of the cigarette paper to be tested include: tobacco shreds, tobacco sheets, EBA, dust, and pulp spots; the image of the cigarette paper to be tested is a two-dimensional network structure, and the components of the cigarette paper to be tested are the portions between two nodes in the network structure; wherein, the distance between each node in the image of the cigarette paper to be tested represents the length of the tobacco shreds; the average width of the objects between each node in the image of the cigarette paper to be tested represents the width of the tobacco shreds; the area fraction of the tobacco shreds represents the content of the tobacco shreds; and the standard deviation of the area fraction of the tobacco shreds in a local area of ​​the image of the cigarette paper to be tested represents the distribution characteristics of the tobacco shreds. The image processing module is further configured to convert the RGB color model of the cigarette paper image to be tested into an HSV color model based on the light reflectance, and perform color difference analysis in the HSV color space to identify the cigarette paper to be tested; preprocess the cigarette paper image to be tested, perform image segmentation through HSV parameter values ​​to distinguish the components of the cigarette paper to be tested from the background; separate the interconnected components of the different cigarette paper to be tested, and independently identify each component of the cigarette paper to be tested; The image processing module is further configured to set a preset range of color parameters for the cigarette paper to be tested, classifying images within the preset range of color parameters as the cigarette paper to be tested, and images outside the preset range of color parameters as the background; or... Set a preset value for the color difference between the cigarette paper to be tested and the background. Images that are equal to or exceed the preset value for color difference are classified as the cigarette paper to be tested, while images that do not exceed the preset value for color difference are classified as the background.

5. A machine vision-based cigarette paper quality inspection system, characterized in that, include: Lighting devices used to provide lighting with adjustable color temperature and light intensity; An imaging device is used to project the cigarette paper to be tested onto the sensor plane of a camera device; A camera device is used to convert digital light intensity into an image of the cigarette paper to be tested; The image processing apparatus as described in claim 4 is used to detect the quality of cigarette paper based on machine vision; The paper feeding device is used to drive the cigarette paper to be tested to move at a constant speed.

6. A computer device, characterized in that, The device includes: a memory and a processor; The memory is used to store a computer program; the processor is used to execute the computer program stored in the memory to cause the device to perform the method as described in any one of claims 1 to 3.

Images