A label missing detection and rejection device based on machine vision

Abstract

The utility model discloses a kind of label missing detection rejection devices based on machine vision, including support, camera, host computer, control cabinet and rejection mechanism, support is set after the labeling station of assembly line;Camera, host computer, control cabinet and rejection mechanism are all set on support, camera is located above assembly line, and camera is set directly opposite assembly line, camera is electrically connected with host computer and control cabinet respectively;Rejection mechanism includes driving mechanism and push plate, driving mechanism is electrically connected with control cabinet, push plate is set in driving mechanism output end, and driving mechanism is used to drive push plate reciprocating motion along the width of assembly line.The technical effect reached is as follows:full-automatic detection can be realized, greatly reduces the missed detection rate and misjudgment rate, and at the same time, the product with missing label can be automatically rejected, the detection speed is fast, the accuracy is high, the operation efficiency of production line can be greatly improved, and the after-sales cost increase and brand reputation loss risk caused by missing label product flowing into market are effectively reduced.

Description

Technical Field

[0001] This utility model relates to the field of industrial automation inspection technology, specifically to a labeling and rejection device based on machine vision for detecting and removing missing labels. Background Technology

[0002] In modern industrial production, product labeling is a crucial step, and the accuracy and completeness of labeling directly affect the product's appearance, information delivery, and market image. Traditional labeling operations rely heavily on manual labor, and even with the increasing prevalence of automated labeling equipment, it remains difficult to completely eliminate the problem of missing labels. Currently used detection methods have several limitations:

[0003] 1. Manual inspection: Inefficient, labor-intensive, and long working hours can easily lead to worker fatigue, thereby reducing the accuracy of inspection, resulting in a high rate of missed detections, and the labor cost is constantly rising.

[0004] 2. Traditional sensor detection: such as photoelectric sensors, can only detect the presence or absence of objects, but cannot accurately determine whether the label is correctly pasted, which is prone to misjudgment. They are also difficult to effectively identify complex situations such as label misalignment or partial pasting.

[0005] With the expansion of production scale and the increasing requirements for product quality, there is an urgent need for a high-efficiency and accurate labeling and labeling detection device. Utility Model Content

[0006] Therefore, this utility model provides a machine vision-based labeling and missing label detection and rejection device to solve the above-mentioned problems in the prior art.

[0007] To achieve the above objectives, this utility model provides the following technical solution:

[0008] According to a first aspect of the present invention, a labeling omission detection and rejection device based on machine vision includes a bracket, a camera, a host, a control cabinet and a rejection mechanism, wherein the bracket is arranged after the labeling station of the production line.

[0009] The camera, the host, the control cabinet, and the rejection mechanism are all mounted on the bracket. The camera is located above the production line and faces the production line. The camera is electrically connected to the host and the control cabinet respectively.

[0010] The rejection mechanism includes a drive mechanism and a pusher plate. The drive mechanism is electrically connected to the control cabinet, and the pusher plate is disposed at the output end of the drive mechanism. The drive mechanism is used to drive the pusher plate to reciprocate along the width of the production line.

[0011] Furthermore, it also includes a reflector and a photoelectric sensor, which are respectively disposed on both sides of the production line, and are disposed corresponding to each other. Both the reflector and the photoelectric sensor are located below the camera, and the photoelectric sensor is electrically connected to the control cabinet.

[0012] Furthermore, it also includes a fill light and a light source controller. The fill light is positioned facing the production line and is positioned corresponding to the camera. The fill light is electrically connected to the light source controller, and the light source controller is electrically connected to the control cabinet.

[0013] Furthermore, supplementary lights are provided on both sides of the production line.

[0014] Furthermore, the driving mechanism is a cylinder, the air inlet pipe of the cylinder is equipped with a solenoid valve, the cylinder is located on one side of the production line, the output shaft of the cylinder is arranged perpendicular to the length direction of the production line, and the push plate is arranged at the end of the output shaft of the cylinder.

[0015] Furthermore, it also includes a display screen, which is mounted on the bracket and electrically connected to the control cabinet and the main unit.

[0016] Furthermore, the display screen is a touch screen.

[0017] Furthermore, it also includes guide rods, which are respectively provided on both sides of the production line.

[0018] Furthermore, it also includes a recycling box, which is disposed on one side of the production line and is disposed corresponding to the rejection mechanism.

[0019] This invention has the following advantages: A camera can capture photos of the labeled product, which are then sent to the host computer for processing. The host computer compares the captured product photos with a standard photo of the labeled product to determine if there are any missing labels. If no missing labels are found, the product proceeds to the next process. If missing labels are found, the host computer sends a corresponding signal to the control cabinet, which in turn sends a signal to the rejection mechanism. The rejection mechanism uses a push plate to remove the missing-labeled product from the production line. The entire device achieves fully automated detection, significantly reducing the missed detection rate and false detection rate compared to manual detection and traditional sensor detection. It also automatically removes missing-labeled products, offering fast detection speed and high accuracy, greatly improving production line efficiency and effectively reducing the risk of increased after-sales costs and brand reputation damage caused by missing-labeled products entering the market. Attached Figure Description

[0020] To more clearly illustrate the embodiments of this utility model or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are merely exemplary, and those skilled in the art can derive other embodiments based on the provided drawings without creative effort.

[0021] The structures, proportions, sizes, etc. illustrated in this specification are only for the purpose of assisting those skilled in the art in understanding and reading the content disclosed herein, and are not intended to limit the implementation conditions of this utility model. Therefore, they have no substantial technical significance. Any modifications to the structure, changes in the proportional relationships, or adjustments to the size, without affecting the effects and purposes that this utility model can produce, should still fall within the scope of the technical content disclosed in this utility model.

[0022] Figure 1 This is a perspective view of a machine vision-based labeling and missing label detection and rejection device provided for some embodiments of the present invention.

[0023] Figure 2 This is a front view of a machine vision-based labeling and missing label detection and rejection device provided for some embodiments of the present invention.

[0024] In the diagram: 1. Reflector, 2. Photoelectric sensor, 3. Fill light, 4. Light source controller, 5. Camera, 6. Display screen, 7. Guide rod, 8. Production line, 9. Labeling machine, 10. Push plate, 11. Cylinder, 12. Main unit, 13. Control cabinet, 14. Solenoid valve. Detailed Implementation

[0025] The following specific embodiments illustrate the implementation of this utility model. Those skilled in the art can easily understand other advantages and effects of this utility model from the content disclosed in this specification. Obviously, the described embodiments are only some, not all, of the embodiments of this utility model. Based on the embodiments of this utility model, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of this utility model.

[0026] Example 1

[0027] like Figure 1 and Figure 2 As shown, a labeling omission detection and rejection device based on machine vision in the first aspect embodiment of this utility model includes a bracket, a camera 5, a host 12, a control cabinet 13 and a rejection mechanism. The bracket is equipped with a label omission detection station, which is located after the labeling station of the production line 8.

[0028] Camera 5, host 12, control cabinet 13 and rejection mechanism are all mounted on the bracket. Camera 5 is an industrial camera. Camera 5 is located above the production line 8 and is positioned directly facing the production line 8. Camera 5 is electrically connected to host 12 and control cabinet 13 respectively. Camera 5 is used to take photos of the products after labeling. The installation position of camera 5 must ensure that it can clearly capture the surface image of the labeled products.

[0029] The rejection mechanism includes a drive mechanism and a pusher plate 10. The drive mechanism is electrically connected to the control cabinet 13. The pusher plate 10 is located at the output end of the drive mechanism. The drive mechanism is used to drive the pusher plate 10 to reciprocate along the width of the conveyor line 8.

[0030] In this embodiment, it should be noted that a reflector 1 and a photoelectric sensor 2 are also included. The reflector 1 and the photoelectric sensor 2 are respectively arranged on both sides of the production line 8. The reflector 1 and the photoelectric sensor 2 are arranged corresponding to each other. The reflector 1 and the photoelectric sensor 2 are both located below the camera 5. The photoelectric sensor 2 is electrically connected to the control cabinet 13.

[0031] The host 12 is equipped with an image processing and analysis module. Specifically, the host 12 consists of image processing software and a computer, used to receive and process image data captured by the camera 5. First, the received image is preprocessed, including grayscale conversion, filtering, and noise reduction, to remove interference information from the image. Then, edge detection and feature extraction algorithms are used to identify label outlines, feature points, and other information in the image, and compared with pre-stored standard label images to determine if there are any missing labels. It can accurately identify various missing label situations, including complete missing labels, partial missing labels, and misjudgments caused by label offset. This analysis and processing technology uses existing technology. The control cabinet 13 is used to receive signals sent by the host 12 and control the start-up and operation of various components.

[0032] During use, the entire device operates as follows: When there is no product between reflector 1 and photoelectric sensor 2, the signal emitted by photoelectric sensor 2 is reflected back to photoelectric sensor 2 after being reflected by reflector 1. Photoelectric sensor 2 then transmits a signal to control cabinet 13. Control cabinet 13 determines that there is no product between reflector 1 and photoelectric sensor 2, and the camera does not need to take a picture. When there is a product between reflector 1 and photoelectric sensor 2, the signal emitted by photoelectric sensor 2 is blocked by the product and cannot be reflected back to photoelectric sensor 2. At this time, photoelectric sensor 2 sends a signal to control cabinet 13. Control cabinet 13 determines that there is a product between reflector 1 and photoelectric sensor 2, and then sends a signal to camera 5 to take a picture. Camera 5 takes a picture of the product and sends the photo to host 12 for processing. Host 12 compares the product photo with a standard photo of the labeled product to determine if there are any missing labels. If there are no missing labels, the product proceeds to the next process. If there are missing labels, host 12 sends a signal to control cabinet 13, which in turn sends a signal to rejection mechanism. The rejection mechanism uses push plate 10 to remove the product with missing labels from the production line. This system enables automated detection with high speed, matching the production speed of the labeling equipment. It eliminates the need for manual inspection of each product, avoiding the inefficiency of manual inspection and improving the overall operating efficiency of the production line.

[0033] The technical effects achieved by this embodiment are as follows: the entire device can achieve fully automatic detection, which greatly reduces the missed detection rate and false detection rate compared with manual detection and traditional sensor detection. At the same time, it can automatically remove products with missing labels. The detection speed is fast and the accuracy is high, which can greatly improve the operating efficiency of the production line and effectively reduce the risk of increased after-sales costs and brand reputation damage caused by products with missing labels entering the market.

[0034] Example 2

[0035] like Figure 1 and Figure 2 As shown in the figure, another labeling and missing label detection and rejection device based on machine vision is provided in this embodiment. Its structure includes all the contents of Embodiment 1. Only the different parts are described below.

[0036] In this embodiment, a fill light 3 and a light source controller 4 are also included. The fill light 3 is arranged facing the production line 8 and is arranged correspondingly to the camera 5. The fill light 3 is used to provide supplementary lighting during the shooting process to ensure the clarity of the photos taken by the camera 5. The fill light 3 is electrically connected to the light source controller 4, and the light source controller 4 is electrically connected to the control cabinet 13. The light source controller 4 is used to adjust the light source intensity.

[0037] In this embodiment, it should be noted that supplementary lights 3 are provided on both sides of the production line 8. The supplementary lights 3 are backlights. During use, appropriate lighting methods and intensities are selected according to the material, color and other characteristics of the product and label to enhance the contrast and clarity of the image and highlight the label features.

[0038] The technical effect achieved by this embodiment is that by setting up the supplementary light 3 and the light source controller 4, the clarity of the product photos captured by the camera 5 can be effectively guaranteed, further ensuring the accuracy of missing label detection.

[0039] Example 3

[0040] like Figure 1 and Figure 2 As shown in the figure, another labeling and missing label detection and rejection device based on machine vision is provided in this embodiment. Its structure includes all the contents of Embodiment 1. Only the different parts are described below.

[0041] In this embodiment, the driving mechanism adopts a cylinder 11. A solenoid valve 14 is provided on the air inlet pipe of the cylinder 11. The cylinder 11 is located on one side of the production line 8. The output shaft of the cylinder 11 is arranged perpendicular to the length direction of the production line 8. The push plate 10 is arranged at the end of the output shaft of the cylinder 11.

[0042] In this embodiment, it should be noted that a recycling box is also included. The recycling box is set on one side of the production line 8, and the recycling box and the rejection mechanism are set in correspondence. The recycling box is used to collect rejected products with missing labels. During operation, when a product is found to have missing labels, the output shaft of the cylinder 11 extends and pushes the product with missing labels from the production line 8 into the recycling box using the push plate 10.

[0043] The technical effect achieved by this embodiment is that by setting up a recycling box, products with missing labels can be collected, making it convenient for them to be centrally processed.

[0044] Example 4

[0045] like Figure 1 and Figure 2 As shown in the figure, another labeling and missing label detection and rejection device based on machine vision is provided in this embodiment. Its structure includes all the contents of Embodiment 1. Only the different parts are described below.

[0046] In this embodiment, a display screen 6 is also included. The display screen 6 is mounted on a bracket and is electrically connected to the control cabinet 13 and the host 12.

[0047] In this embodiment, it should be noted that the display screen 6 is a touch screen, which is used to display the test results, production data statistics, etc. in real time, such as the number of products tested and the number of products that were missed in labeling.

[0048] Furthermore, it also includes guide rods 7, which are arranged along the length of the assembly line 8. Guide rods 7 are provided on both sides of the width of the assembly line 8, and the guide rods 7 are used to guide the products to move along the length of the assembly line 8.

[0049] The technical effect achieved by this embodiment is that by setting up the display screen 6, the test results, production data statistics and other information can be displayed in real time.

[0050] Although the present invention has been described in detail above with general descriptions and specific embodiments, some modifications or improvements can be made to it, which will be obvious to those skilled in the art. Therefore, all such modifications or improvements made without departing from the spirit of the present invention fall within the scope of protection claimed by the present invention.

[0051] The terms such as "upper," "lower," "left," "right," and "middle" used in this specification are merely for clarity of description and are not intended to limit the scope of implementation of this utility model. Any changes or adjustments to their relative relationships, without substantially altering the technical content, shall also be considered within the scope of implementation of this utility model.

Claims

1. A machine vision-based labeling and missing label detection and rejection device, characterized in that, Includes a bracket, camera (5), host (12), control cabinet (13) and rejection mechanism, wherein the bracket is set after the labeling station of the production line (8); The camera (5), the host (12), the control cabinet (13) and the rejection mechanism are all mounted on the bracket. The camera (5) is located above the production line (8) and is positioned directly facing the production line (8). The camera (5) is electrically connected to the host (12) and the control cabinet (13) respectively. The rejection mechanism includes a drive mechanism and a push plate (10). The drive mechanism is electrically connected to the control cabinet (13). The push plate (10) is disposed at the output end of the drive mechanism. The drive mechanism is used to drive the push plate (10) to reciprocate along the width of the production line (8).

2. The labeling and rejection device based on machine vision according to claim 1, characterized in that, It also includes a reflector (1) and a photoelectric sensor (2). The reflector (1) and the photoelectric sensor (2) are respectively arranged on both sides of the production line (8). The reflector (1) and the photoelectric sensor (2) are arranged corresponding to each other. The reflector (1) and the photoelectric sensor (2) are both located below the camera (5). The photoelectric sensor (2) is electrically connected to the control cabinet (13).

3. The labeling and rejection device based on machine vision according to claim 1, characterized in that, It also includes a fill light (3) and a light source controller (4). The fill light (3) is positioned facing the production line (8), and the fill light (3) is positioned corresponding to the camera (5). The fill light (3) is electrically connected to the light source controller (4), and the light source controller (4) is electrically connected to the control cabinet (13).

4. The labeling and rejection device based on machine vision according to claim 3, characterized in that, The fill lights (3) are respectively provided on both sides of the production line (8).

5. The labeling and rejection device based on machine vision according to claim 1, characterized in that, The driving mechanism is a cylinder (11), and the air inlet pipe of the cylinder (11) is equipped with a solenoid valve (14). The cylinder (11) is located on one side of the production line (8), and the output shaft of the cylinder (11) is arranged perpendicular to the length direction of the production line (8). The push plate (10) is arranged at the end of the output shaft of the cylinder (11).

6. The labeling and rejection device based on machine vision according to claim 1, characterized in that, It also includes a display screen (6), which is mounted on the bracket and is electrically connected to the control cabinet (13) and the host (12).

7. The labeling and rejection device based on machine vision according to claim 6, characterized in that, The display screen (6) is a touch screen.

8. The labeling and rejection device based on machine vision according to claim 1, characterized in that, It also includes guide rods (7), which are provided on both sides of the production line (8).

9. A labeling and rejection device based on machine vision according to claim 1, characterized in that, It also includes a recycling box, which is disposed on one side of the production line (8) and is disposed corresponding to the rejection mechanism.

Images