Cigarette packet processing table state detection and model construction method, device and system and medium

Abstract

The invention provides a cigarette packet processing table state detection and model construction method, device and system and a medium. An image acquisition device is used for shooting a cigarette packet picture on a production line and transmitting the picture to an image processing device; and the image processing device adopts a convolutional neural network to read the state of the cigarette packet identified by a pre-trained cigarette packet identification model and outputs the identified state to a production line control system so as to achieve the purpose of controlling the next production action. The image processing device outputs the recognized state and the original image to the image output device; and the image output device displays the image and the state in a manner visible to human eyes. The cigarette packet identification model training method comprises the steps that cigarette packet images of various states on multiple pairs of production lines are shot in advance and transmitted to the model training system, and the model training system adopts a convolutional neural network to train a cigarette packet identification model. Therefore, the state of the cigarette packet processing table is identified in a machine learning mode, the production efficiency is improved, and the working intensity of workers is reduced.

Description

Technical Field

[0001] This application relates to the field of industrial automation technology, and particularly to a method, device, system, and medium for detecting the state of a cigarette packet handling table and constructing a model. Background Art

[0002] The current judgment of the state of the cigarette packet handling table on the cigarette making production line mainly relies on manual operation. Each production line requires at least one staff member to make on-site judgments. Increasing the production line requires adding corresponding workers. When the workers are not on the production line, the on-site production will be interrupted, and the next step can only be carried out after waiting for the manual judgment to be completed. The overall production efficiency is low, and the dependence on people is high. With the increase of production lines and the need to increase production, the existing manual judgment method can no longer meet the production requirements. Therefore, how to reduce the dependence on manual labor and reduce the labor intensity of staff while ensuring the smooth progress of production has become a technical problem to be solved in the identification of the state of cigarette packets on the handling table.

[0003] Application Content

[0004] In view of the above-mentioned disadvantages of the prior art, the purpose of this application is to provide a method, device, system, and medium for detecting the state of a cigarette packet handling table and constructing a model to solve the problems in the prior art.

[0005] To achieve the above object and other related objects, the first aspect of this application provides a cigarette packet handling table state detection system applicable to the unpacking area production line of the cigarette making pretreatment section, including: an image acquisition device for acquiring cigarette packet image information in the handling table area; the acquisition range of the image acquisition device covers the handling table area, and the handling table area is for placing cigarette packets conveyed by a conveying device; an image processing device communicatively connected to the image acquisition device to receive the cigarette packet image information; the image processing device uses a trained cigarette packet state detection model based on a neural network to perform cigarette packet state recognition on the received cigarette packet image information and output a cigarette packet state recognition result; an image output device communicatively connected to the image processing device to receive the original cigarette packet image information and the cigarette packet state recognition result and display them externally.

[0006] In some embodiments of the first aspect of this application, the cigarette packet state recognition result includes a state of no cigarette packet, a state of being covered with a plastic bag, a state of being covered with kraft paper, or a state of being covered with no packaging.

[0007] In some embodiments of the first aspect of the present application, the system further includes: a control device communicatively connected to the image acquisition device and the image processing device; wherein, when the area of the processing table changes, the control device issues a corresponding control instruction to the image acquisition device to cause the image acquisition device to acquire an image of the area of the processing table; the control device also receives the cigarette pack status recognition result from the image processing device.

[0008] In some embodiments of the first aspect of the present application, the image output module includes a display screen.

[0009] In some embodiments of the first aspect of the present application, the cigarette pack status detection model based on a neural network includes a Keras convolutional neural network model.

[0010] To achieve the above object and other related objects, a second aspect of the present application provides a method for detecting the status of a cigarette pack processing table applicable to the production line of the unpacking area in the pre-treatment section of cigarette making, including: obtaining image information of a cigarette pack to be detected; using a trained cigarette pack status detection model to identify the status of the cigarette pack to be detected; wherein, the cigarette pack status includes a plastic bag covering status, a kraft paper covering device, a status without any packaging covering, or other statuses; outputting the original image and the status recognition result of the cigarette pack to be detected outward.

[0011] To achieve the above object and other related objects, a third aspect of the present application provides a method for constructing a cigarette pack status detection model, including: obtaining multiple images of a cigarette pack in various statuses; performing status annotation on the collected cigarette pack images, and the annotated statuses include a status without a cigarette pack, a plastic bag covering status, a kraft paper covering status, or a status without any packaging covering; using the images annotated with the cigarette pack status as model training data to input into a Keras convolutional neural network, performing machine learning and training on the Keras convolutional neural network, and accordingly obtaining a cigarette pack status detection model.

[0012] To achieve the above object and other related objects, a fourth aspect of the present application provides a device for detecting the status of a cigarette pack processing table applicable to the production line of the unpacking area in the pre-treatment section of cigarette making, including an image acquisition module for obtaining image information of a cigarette pack to be detected; a cigarette pack status recognition module for using a trained cigarette pack status detection model to identify the status of the cigarette pack to be detected; wherein, the cigarette pack status includes a plastic bag covering status, a kraft paper covering device, a status without any packaging covering, or other statuses; an output module for outputting the original image and the status recognition result of the cigarette pack to be detected outward.

[0013] To achieve the above object and other related objects, a fifth aspect of the present application provides a device for constructing a cigarette pack state detection model, including: an image acquisition module for acquiring multiple images of a cigarette pack in multiple states; a state annotation module for annotating the state of the acquired cigarette pack images, and the annotated states include no cigarette pack state, plastic bag covering state, kraft paper covering state, or no any packaging covering state; a model construction module for taking the images annotated with the cigarette pack state as model training data and inputting them into a Keras convolutional neural network, performing machine learning and training on the Keras convolutional neural network, and thereby obtaining a cigarette pack state detection model.

[0014] To achieve the above object and other related objects, a sixth aspect of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method is implemented.

[0015] As described above, the cigarette pack processing table state detection and model construction method, device, system and medium of the present application have the following beneficial effects: The present invention uses an image acquisition device to take pictures of cigarette packs on a production line and transmit them to an image processing device. The image processing device uses a convolutional neural network to read a pre-trained cigarette pack recognition model to identify the state of the cigarette pack (covered with a plastic bag, covered with kraft paper, not covered with any packaging, and other states), and outputs the identified state to the production line control system to achieve the purpose of controlling the next production action. The image processing device outputs the identified state and the original image to an image output device; the image output device displays the image and the state in a visible manner to the human eye. The cigarette pack recognition model training method includes pre-taking multiple images of cigarette packs in various states on a production line and transmitting them to a model training system, and the model training system uses a convolutional neural network to train the cigarette pack recognition model. Therefore, by using machine learning to identify the state of the cigarette pack processing table, the production efficiency is improved and the working intensity of workers is reduced. Description of the Drawings

[0016] Figure 1 It shows a schematic structural diagram of a cigarette pack processing table state detection system applicable to the unpacking area production line of the primary processing section of cigarette making in an embodiment of the present application.

[0017] Figure 2 It shows a schematic flow diagram of a cigarette pack processing table state detection method applicable to the unpacking area production line of the primary processing section of cigarette making in an embodiment of the present application.

[0018] Figure 3 It shows a schematic flow diagram of a method for constructing a cigarette pack state detection model in an embodiment of the present application.

[0019] Figure 4It shows a schematic structural diagram of a cigarette pack processing table state detection device applicable to the unpacking area production line in the primary processing section of cigarette making in an embodiment of the present application.

[0020] Figure 5 It shows a schematic structural diagram of a device for constructing a cigarette pack state detection model in an embodiment of the present application. Detailed implementation manners

[0021] The following uses specific specific examples to illustrate the implementation manners of the present application. Those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in this specification. The present application can also be implemented or applied through other different specific implementation manners. 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 application. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0022] It should be noted that in the following description, reference is made to the accompanying drawings, which describe several embodiments of the present application. It should be understood that other embodiments can also be used, and mechanical composition, structure, electrical, and operational changes can be made without departing from the spirit and scope of the present application. The following detailed description should not be considered restrictive, and the scope of the embodiments of the present application is only defined by the claims of the published patent. The terms used here are only for describing specific embodiments and are not intended to limit the present application. Spatially related terms, such as "upper", "lower", "left", "right", "below", "beneath", "lower part", "above", "upper part", etc., may be used in the text to facilitate the description of the relationship between one element or feature shown in the figure and another element or feature.

[0023] In the present application, unless otherwise clearly specified and defined, terms such as "install", "connect", "link", "fix", "hold" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific situations.

[0024] Furthermore, as used herein, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly dictates otherwise. 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 preclude 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" used herein are to be construed as inclusive, or meaning any one or any combination. Thus, "A, B, or C" or "A, B, and / or C" means "any of the following: A; B; C; A and B; A and C; B and C; A, B, and C". Exceptions to this definition occur only when the combination of elements, functions, or operations are inherently mutually exclusive in some manner.

[0025] The present invention discloses a detection scheme for the state of a cigarette pack handling table on the production line in the unpacking area of the pre-treatment section of a cigarette making line, belonging to the field of industrial automation. The detection method includes an image acquisition device taking pictures of cigarette packs on the production line and transmitting them to an image processing device. The image processing device uses a convolutional neural network to read a pre-trained cigarette pack recognition model to identify the state of the cigarette pack (covered with a plastic bag, covered with kraft paper, not covered with any packaging, and other states), and outputs the identified state to the production line control system to achieve the purpose of controlling the next production action. The image processing device outputs the identified state and the original image to an image output device; the image output device displays the image and the state in a visible manner to the human eye. The method for training the cigarette pack recognition model includes pre-taking multiple pictures of cigarette packs in various states on the production line and transmitting them to a model training system. The model training system uses a convolutional neural network to train the cigarette pack recognition model. Therefore, by means of machine learning, the state of the cigarette pack handling table is recognized, improving production efficiency and reducing the working intensity of workers.

[0026] In order to make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the technical solutions in the embodiments of the present invention are further described in detail below through the following embodiments in combination with the accompanying drawings. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the invention.

[0027] As Figure 1As shown in the figure, it shows a schematic structural diagram of a cigarette pack processing table state detection system applicable to the unpacking area production line in the primary processing section of cigarette making. It includes a control device 11, an image acquisition device 12, an image processing device 13, an image output device 14, a conveying device 15, a processing table 16, a cigarette pack 17, a covering 18, and a captured picture 19. Among them, a communication connection is established between the image acquisition device 12 and the image processing device 13. The acquisition range of the image acquisition device 12 is aligned with the area of the processing table 16. When the cigarette pack 17 is transported to the position of the processing table 16 by the conveying device 15 (such as a conveyor belt), the image acquisition device 12 acquires the image information of the cigarette pack 17 and sends it to the image processing device 13. The image processing device 13 identifies the state of the cigarette pack based on the acquired original image of the cigarette pack 17. For example, it identifies that the cigarette pack 17 is in a state covered by a plastic bag, a state covered by kraft paper, a state without any packaging cover, or other states, etc. A communication connection is also established between the image processing device 13 and the image output device 14, so as to send both the original image of the cigarette pack and the identified state of the cigarette pack to the image output device 14. The image output device 14 displays both the original image of the cigarette pack and the identified state of the cigarette pack in a visible way to the human eye (including but not limited to dynamic images, static images, text, voice, etc.).

[0028] Specifically, the specific operation process of the cigarette pack processing table state detection system on the unpacking area production line in the primary processing section of cigarette making in this embodiment is as follows:

[0029] In the first step, the image acquisition device 12 pre - shoots multiple images of the cigarette pack 17 on the processing table 16. In order to obtain more training data, multiple images (such as at least 3 images) are taken for each cigarette pack state. The acquired cigarette pack images are state - labeled, and the labeled states include but are not limited to the state of no cigarette pack, the state covered by a plastic bag, the state covered by kraft paper, the state without any packaging cover, etc. The images labeled with the cigarette pack state are used as model training data and input into the Keras convolutional neural network. Machine learning and training are performed on the Keras convolutional neural network, and after the training is completed, it is saved, thus obtaining a cigarette pack state detection model. It should be understood that the Keras convolutional neural network is a high - level neural network designed for supporting rapid experiments, with features such as simple and fast prototype design, supporting CNN and RNN or the combination of both, seamless switching between CPU and GPU, etc.

[0030] In the second step, when there is a change in the processing table 16, the control device 11 sends a control instruction to the image acquisition device 12 to make the image acquisition device 12 start shooting the cigarette pack to be detected on the processing table 16. It should be understood that the control device 11 referred to in this embodiment can be, for example, a computer, a central console, or other devices.

[0031] In some embodiments, the image acquisition device 12 is fixed above the assembly line, covering the processing table area with its shooting range, so that the state of the cigarette packets can be clearly captured from above.

[0032] In some embodiments, the image acquisition device 12 uses a network camera with a resolution of 720P or higher to acquire images, and the captured images are transmitted externally via Ethernet. However, in addition, the image acquisition device can also be a camera module, which includes a camera device, a storage device, and a processing device; the camera device includes, but is not limited to, a camera, a video camera, a camera module integrated with an optical system or a CCD chip, a camera module integrated with an optical system and a CMOS chip, etc.

[0033] In the third step, the image acquisition device 12 transmits the captured images of the cigarette packets to be detected to the image processing device 13.

[0034] In the fourth step, the image processing device 13 calls the trained cigarette packet state detection model to identify the state of the current cigarette packet to be detected. Specifically, the image processing device 13 inputs the received image data of the cigarette packet to be detected into the cigarette packet state detection model, and the cigarette packet state detection model outputs cigarette packet state information after identification, such as information indicating that the cigarette packet is covered with a plastic bag, kraft paper, not covered with any packaging, or other states.

[0035] In some examples, the image processing device 13 can be a processor such as ARM (Advanced RISC Machines), FPGA (Field Programmable Gate Array), SoC (System on Chip), DSP (Digital Signal Processing), or MCU (Microcontroller Unit); it can also be a personal computer such as a desktop computer, a laptop computer, a tablet computer, a smart phone, a smart TV, or a personal digital assistant (PDA for short). The specific form of the image processing device 13 is not limited in this embodiment.

[0036] In the fifth step, the image processing device 13 sends the recognition result to the control device 11 for the control device 11 to perform the next action according to the recognition result. It should be noted that the next actions that the control device 11 can perform include, but are not limited to, controlling the conveyor belt to transfer the cigarette packet to the next link, or controlling the packaging equipment to package the cigarette packet in a state without any packaging, etc. The specific actions are not limited in this embodiment.

[0037] In the sixth step, the image processing device 13 sends the original image of the cigarette pack to be detected and the recognition result to the image output device 14, and the image output device 14 displays them externally in the form of text, pictures, voice, etc. In some examples, the image output device 14 can be a screen that supports the Windows 7 or higher operating system and has a resolution of 800*600 or higher.

[0038] As Figure 2 shown, a flowchart of the method for detecting the state of a cigarette pack processing table applicable to the unpacking area production line of the primary processing section of cigarette making is shown. It should be understood that the method for detecting the state of a cigarette pack processing table applicable to the unpacking area production line of the primary processing section of cigarette making in this embodiment is applied to the image processing device in the above embodiment.

[0039] Step S201: Obtain the image information of the cigarette pack to be detected.

[0040] In this embodiment, the image information of the cigarette pack to be detected can be obtained from an image acquisition device aligned with the processing table area. Among them, the image acquisition device can use a network camera with a clarity of 720P or higher for image acquisition, and the captured image is transmitted externally in the form of Ethernet. However, in addition, the image acquisition device can also be a camera module, and the camera module includes a camera device, a storage device, and a processing device; the camera device includes but is not limited to a camera, a video camera, a camera module integrated with an optical system or a CCD chip, a camera module integrated with an optical system and a CMOS chip, etc.

[0041] Step S202: Use a trained cigarette pack state detection model to identify the state of the cigarette pack to be detected; among them, the cigarette pack state includes the plastic bag covering state, the kraft paper covering device, the state of no any packaging covering, or other states.

[0042] Step S203: Output the original image and the state recognition result of the cigarette pack to be detected externally.

[0043] In some examples, the image processing device sends the original image and the state recognition result of the cigarette pack to be detected to an image output device (such as a display screen) to display the original image and the state recognition result of the cigarette pack to be detected.

[0044] In some examples, the image processing device sends the state recognition result of the cigarette pack to be detected to a control device, and the control device performs the next action according to the state recognition result. It should be noted that the next actions that the control device can perform include but are not limited to controlling the conveyor belt to convey the cigarette pack to the next link, or controlling the packaging equipment to package the cigarette pack in the state of no any packaging covering, etc., which are not limited in this embodiment.

[0045] As Figure 3As shown in the figure, it shows a schematic flowchart of a method for constructing a cigarette pack status detection model in an embodiment of the present invention. It should be understood that in this embodiment, the cigarette pack status detection model can be applied to the image processing device in the above-mentioned embodiment; or the cigarette pack status detection model can also be constructed by using a cloud server, which establishes a communication connection with the image processing device, and the image processing device can call the model from the cloud server when it needs to use the cigarette pack status detection model.

[0046] Step S301: Obtain multiple images of the cigarette pack in multiple states.

[0047] In this embodiment, the cigarette pack image information can be obtained from the image acquisition device in the alignment processing table area. Among them, the image acquisition device can use a network camera with a definition of 720P or above for image acquisition, and the captured images are transmitted externally in the form of Ethernet. However, in addition, the image acquisition device can also be a camera module, and the camera module includes a camera device, a storage device, and a processing device; the camera device includes, but is not limited to, a camera, a video camera, a camera module integrated with an optical system or a CCD chip, a camera module integrated with an optical system and a CMOS chip, etc.

[0048] Step S302: Perform status annotation on the collected cigarette pack images, and the annotated statuses include no cigarette pack status, plastic bag covering status, kraft paper covering status, or no any packaging covering status.

[0049] Step S303: Input the images marked with the cigarette pack status as model training data into the Keras convolutional neural network, perform machine learning and training on the Keras convolutional neural network, and accordingly obtain a cigarette pack status detection model. It should be understood that the Keras convolutional neural network is a high-level neural network, born to support rapid experiments, with simple and fast prototype design, supporting CNN and RNN or the combination of the two, seamless CPU and GPU switching, etc.

[0050] As Figure 4 shown, it shows a schematic structural diagram of a cigarette pack processing table status detection device applicable to the unpacking area production line of the wire making pretreatment section in an embodiment of the present invention. The cigarette pack processing table status detection device 400 includes an image acquisition module 401, a cigarette pack status recognition module 402, and an output module 403.

[0051] The image acquisition module 401 is used to acquire the image information of the cigarette pack to be detected; the cigarette pack status recognition module 402 is used to identify the cigarette pack status of the cigarette pack to be detected by using the trained cigarette pack status detection model; among them, the cigarette pack status includes plastic bag covering status, kraft paper covering device, no any packaging covering status or other status; the output module 403 is used to output the original image of the cigarette pack to be detected and the status recognition result outward.

[0052] It should be noted that the implementation of the cigarette packet handling table state detection method applicable to the unpacking area production line in the silk making pretreatment section in this embodiment is similar to that in the above embodiment, so it will not be elaborated here. In addition, it should be understood that the division of each module of the above device is only a logical function division. In actual implementation, it can be fully or partially integrated into a physical entity, or physically separated. And these modules can all be implemented in the form of software called by processing elements; they can also all be implemented in hardware form; or some modules can be implemented in the form of software called by processing elements, and some modules can be implemented in hardware form. For example, the cigarette packet state recognition module can be a separately established processing element, or can be integrated in a certain chip of the above device. In addition, it can also be stored in the memory of the above device in the form of program code, and called and executed by a certain processing element of the above device to perform the functions of the above cigarette packet state recognition module. The implementation of other modules is similar. In addition, all or part of these modules can be integrated together or can be independently implemented. 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 by the integrated logic circuit in the processor element or the instruction in software form.

[0053] For example, the above modules can be one or more integrated circuits configured to implement the above method, such as: one or more Application Specific Integrated Circuits (ASICs), or, one or more digital signal processors (DSPs), or, one or more Field Programmable Gate Arrays (FPGAs), etc. Again, when a certain module above is implemented in the form of a processing element scheduling program code, the processing element can be a general-purpose processor, such as a Central Processing Unit (CPU) or other processors that can call program code. Again, these modules can be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0054] As Figure 5 shown, a schematic structural diagram of a device for constructing a cigarette packet state detection model in an embodiment of the present invention is shown. The model construction device 500 includes an image acquisition module 501, a state annotation module 502, and a model construction module 503.

[0055] The image acquisition module 501 is used to acquire multiple images of the cigarette pack in multiple states; the state annotation module 502 is used to perform state annotation on the acquired cigarette pack images, and the annotated states include no cigarette pack state, plastic bag covering state, kraft paper covering state, or no covering state by any packaging; the model construction module 503 is used to input the images annotated with the cigarette pack state as model training data into the Keras convolutional neural network, perform machine learning and training on the Keras convolutional neural network, and thereby obtain a cigarette pack state detection model.

[0056] It should be noted that the implementation manner of the method for constructing the cigarette pack state detection model in this embodiment is similar to that in the above-mentioned embodiment, so it will not be elaborated here. In addition, it should be understood that the division of each module of the above device is only a logical function division. In actual implementation, it can be fully or partially integrated into a physical entity, or physically separated. And these modules can all be implemented in the form of software called by a processing element; they can also all be implemented in the form of hardware; they can also be partially implemented in the form of software called by a processing element and partially implemented in the form of hardware. For example, the model construction module can be a separately established processing element, or can be integrated in a certain chip of the above device. In addition, it can also be stored in the memory of the above device in the form of program code, and called and executed by a certain processing element of the above device to perform the functions of the above model construction module. The implementation of other modules is similar. In addition, all or part of these modules can be integrated together or can be independently implemented. 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 by the integrated logic circuit in the processor element or the instruction in the form of software.

[0057] The present invention also provides a computer-readable storage medium, on which a first computer program and / or a second computer program are stored. When the first computer program is executed by a processor, it implements the method for detecting the state of the cigarette pack processing table applicable to the unboxing area production line of the wire-making pretreatment section; when the second computer program is executed by a processor, it implements the method for constructing the cigarette pack state detection model.

[0058] Those of ordinary skill in the art can understand that all or part of the steps for implementing the above method embodiments can be completed by hardware related to a computer program. The aforementioned computer program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiments; and the aforementioned storage medium includes: ROM, RAM, magnetic disk, or optical disk and other various media that can store program codes.

[0059] In summary, the present application provides a method, apparatus, system and medium for detecting the state of a cigarette pack handling table and constructing a model. The present invention uses an image acquisition device to capture pictures of cigarette packs on a production line and transmit them to an image processing device. The image processing device uses a convolutional neural network to read a pre-trained cigarette pack recognition model to identify the state of the cigarette pack (covered with a plastic bag, covered with kraft paper, not covered with any packaging, and other states), and outputs the identified state to the production line control system to achieve the purpose of controlling the next production action. The image processing device outputs the identified state and the original image to an image output device; the image output device displays the image and the state in a visible manner to the human eye. The method for training the cigarette pack recognition model includes pre-shooting multiple images of cigarette packs in various states on a production line and transmitting them to a model training system, and the model training system uses a convolutional neural network to train the cigarette pack recognition model. Therefore, by using machine learning to identify the state of the cigarette pack handling table, the production efficiency is improved and the working intensity of workers is reduced. Therefore, the present application effectively overcomes various shortcomings in the prior art and has high industrial utilization value.

[0060] The above embodiments are only illustrative of the principles and effects of the present application, and are not used to limit the present application. Any person familiar with this technology can modify or change the above embodiments without departing from the spirit and scope of the present application. Therefore, all equivalent modifications or changes completed by those with ordinary knowledge in the technical field without departing from the spirit and technical ideas disclosed in the present application should still be covered by the claims of the present application.

Claims

1. A state detection system for a cigarette packet handling table in the unpacking area production line of the silk preparation pre-treatment section, characterized in that, Including: An image acquisition device for acquiring image information of cigarette packets in the processing table area; The acquisition range of the image acquisition device covers the processing table area, and the processing table area is for placing cigarette packets conveyed by a conveying device; An image processing device communicatively connected to the image acquisition device to receive the cigarette packet image information; the image processing device uses a trained cigarette packet state detection model based on a neural network to identify the cigarette packet state of the received cigarette packet image information and outputs a cigarette packet state recognition result; An image output device communicatively connected to the image processing device to receive the original cigarette packet image information and the cigarette packet state recognition result and display them externally.

2. The cigarette pack processing table state detection system according to claim 1, wherein The cigarette packet state recognition result includes a state of no cigarette packet, a state of being covered with a plastic bag, a state of being covered with kraft paper, or a state of being covered with no packaging.

3. The cigarette pack processing table state detection system according to claim 1, wherein, The system further includes: A control device communicatively connected to the image acquisition device and the image processing device; wherein, when the processing table area changes, the control device issues a corresponding control instruction to the image acquisition device to cause the image acquisition device to acquire an image of the processing table area; the control device also receives the cigarette packet state recognition result from the image processing device.

4. The cigarette pack processing table state detection system according to claim 1, characterized in that The image output module includes a display screen.

5. The cigarette pack processing table state detection system according to claim 1, characterized in that, The cigarette packet state detection model based on a neural network includes a Keras convolutional neural network model.

6. A method for detecting the state of a cigarette pack handling table applicable to the production line of the unpacking area in the primary processing section of cigarette making, characterized in that, Including: Obtaining image information of a cigarette packet to be detected; Using a trained cigarette packet state detection model to identify the cigarette packet state of the cigarette packet to be detected; wherein, the cigarette packet state includes a state of being covered with a plastic bag, a state of being covered with kraft paper, a state of being covered with no packaging, or other states; Outputting the original image of the cigarette packet to be detected and the state recognition result externally.

7. A method for constructing a cigarette pack status detection model, characterized in that, Including: Obtaining multiple images of a cigarette packet in multiple states; Performing state annotation on the acquired cigarette packet images, and the annotated states include a state of no cigarette packet, a state of being covered with a plastic bag, a state of being covered with kraft paper, or a state of being covered with no packaging; Taking the images annotated with the cigarette packet state as model training data and inputting them into a Keras convolutional neural network, performing machine learning and training on the Keras convolutional neural network, and thereby obtaining a cigarette packet state detection model.

8. A state detection device for a cigarette pack handling table applicable to the unpacking area production line in the primary processing section of cigarette making, characterized in that, Including: An image acquisition module for obtaining image information of a cigarette packet to be detected; A cigarette packet state recognition module for using a trained cigarette packet state detection model to identify the cigarette packet state of the cigarette packet to be detected; wherein, the cigarette packet state includes a state of being covered with a plastic bag, a state of being covered with kraft paper, a state of being covered with no packaging, or other states; An output module for outputting the original image of the cigarette packet to be detected and the state recognition result externally.

9. An apparatus for constructing a cigarette pack state detection model, characterized in that, Including: An image acquisition module for obtaining multiple images of a cigarette packet in multiple states; A state annotation module for performing state annotation on the acquired cigarette packet images, and the annotated states include a state of no cigarette packet, a state of being covered with a plastic bag, a state of being covered with kraft paper, or a state of being covered with no packaging; A model construction module, which is used to input an image marked with the status of a cigarette pack as model training data into a Keras convolutional neural network, perform machine learning and training on the Keras convolutional neural network, and thereby obtain a cigarette pack status detection model.

10. A computer-readable storage medium having a first computer program and / or a second computer program stored thereon, characterized in that, When the first computer program is executed by a processor, it implements the cigarette pack processing table status detection method applicable to the unpacking area production line of the wire making pretreatment section as described in claim 6; when the second computer program is executed by a processor, it implements the method for constructing a cigarette pack status detection model as described in claim 7.

Images