Liquid skin care product filling and sealing machine sealing detection method, device and equipment

Abstract

The application discloses a sealing detection method, device and equipment of a liquid skin care product filling and sealing machine. The method comprises the following steps: obtaining an initial image collected by an image collection device and screening a bag body image corresponding to each sealing bag body from the initial image; according to a preset image cutting rule, cutting a corresponding sealing area image from the bag body image and judging whether the image size of the sealing area image matches the sealing parameter to obtain a matching judgment result; if the matching judgment result is matched, performing a blur degree detection on the sealing area image and a transmission speed collected by a transmission detector to obtain a quality detection value; checking whether the quality detection value matches a matching check rule to obtain a check result; and judging whether the detection result of the bag body image is passed according to the check result. Through the above method, the image size matching judgment and the quality detection value matching check are performed respectively, the detection result of whether the bag body image is passed is obtained, and the detection accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent detection, and particularly to a sealing detection method, device and equipment for a liquid skin care product filling and sealing machine. Background Art

[0002] In order to preserve and transport liquid skin care products, it is necessary to put the liquid skin care products into a bag body for sealing. However, during the automatic sealing process of the bag body by the filling and sealing machine, there may be sealing defects, resulting in the bag body being not tightly sealed or not completely sealed, causing the skin care products to leak during subsequent packing and transportation, causing great losses to the enterprise. To avoid the problem of sealing defects, the existing technology usually detects the sealed bag body of the skin care products by a detector on one side of the bag body, and detects whether the sealing is qualified by comparing the appearance difference between the sealing area and other areas of the bag body. However, the detector will have visual fatigue after long-term detection, affecting the reliability of the detection, resulting in inaccurate sealing detection. Therefore, there is a problem of poor detection accuracy in the existing technical methods for sealing detection of liquid skin care product bag bodies. Summary of the Invention

[0003] Embodiments of the present invention provide a sealing detection method, device and equipment for a liquid skin care product filling and sealing machine, aiming to solve the problem of poor detection accuracy in the existing technical methods for sealing detection of liquid skin care product bag bodies.

[0004] In a first aspect, embodiments of the present invention provide a sealing detection method for a liquid skin care product filling and sealing machine. The method is applied to a detection terminal, and the detection terminal is respectively communicatively connected to an image acquisition device and a transmission detector to implement data information transmission. The method includes:

[0005] Obtain an initial image collected by the image acquisition device, and screen out a bag body image corresponding to each sealed bag body from the initial image according to a preset image screening template;

[0006] Intercept a corresponding sealing area image from the bag body image according to a preset image intercepting rule;

[0007] Judge whether the image size of the sealing area image matches a preset sealing parameter, and obtain a corresponding matching judgment result;

[0008] If the matching judgment result is a match, perform blurriness detection on the sealing area image and the transmission speed collected by the transmission detector according to a preset detection strategy, and obtain a corresponding quality detection value;

[0009] Verify whether the quality detection value matches a preset matching verification rule, and obtain a corresponding verification result;

[0010] If the verification result is a match, the detection result of the current bag image is determined to be passed;

[0011] If the matching judgment result or the verification result is not a match, the detection result of the current bag image is determined to be unsuccessful.

[0012] Secondly, embodiments of the present invention provide a sealing detection device for a liquid skincare product filling and sealing machine, wherein the device is disposed in a detection terminal, and the detection terminal is communicatively connected to an image acquisition device and a transmission detector to realize data information transmission. The sealing detection device for the liquid skincare product filling and sealing machine is used to perform the sealing detection method for the liquid skincare product filling and sealing machine as described in the first aspect above, and the device includes:

[0013] The image filtering unit is used to acquire the initial image acquired by the image acquisition device, and to filter the bag images corresponding to each sealing bag body from the initial image according to the preset image filtering template;

[0014] An image cropping unit is used to crop the corresponding sealing area image from the bag image according to a preset image cropping rule;

[0015] The matching judgment result acquisition unit is used to determine whether the image size of the sealing area image matches the preset sealing parameters, and obtain the corresponding matching judgment result;

[0016] The quality detection value acquisition unit is used to perform ambiguity detection on the sealed area image and the transmission speed acquired by the transmission detector according to a preset detection strategy if the matching judgment result is a match, and obtain the corresponding quality detection value.

[0017] The verification result acquisition unit is used to verify whether the quality detection value matches the preset matching verification rules and obtain the corresponding verification result.

[0018] The first determination unit is used to determine that the detection result of the current bag image is passed if the verification result is a match.

[0019] The second determination unit is used to determine that the detection result of the current bag image is not passed if the matching judgment result or the verification result is not a match.

[0020] Thirdly, embodiments of the present invention also provide a sealing detection device for a liquid skin care product filling and sealing machine, wherein the sealing detection device includes a machine base, a detection terminal, a transmission component, a lighting lamp, an image acquisition device, a transmission detector, a rotary motor, a paddle, and a guide groove;

[0021] The transmission component is mounted on the machine base, the guide groove is mounted on the transmission component, and the lighting lamp and the image acquisition device are mounted opposite each other on both sides of the transmission component; the transmission detector is connected to a transmission shaft in the transmission component; the paddle is mounted in the center of the guide groove; the output shaft of the rotary motor is fixedly connected to a gear, the lower end of the paddle is slidably connected to a rack, and the rack meshes with the gear;

[0022] The detection terminal includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0023] Memory, used to store computer programs;

[0024] The processor, when executing a program stored in memory, implements the sealing detection method of the liquid skin care product filling and sealing machine as described in the first aspect above.

[0025] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the sealing detection method for a liquid skincare product filling and sealing machine as described in the first aspect above.

[0026] This invention provides a sealing detection method, apparatus, and equipment for a liquid skincare product filling and sealing machine. The method includes: acquiring an initial image from an image acquisition device and filtering it to obtain bag images corresponding to each sealing bag; extracting the corresponding sealing area image from the bag image according to preset image cropping rules and determining whether the image size of the sealing area image matches the sealing parameters to obtain a matching judgment result; if the matching judgment result is a match, performing ambiguity detection on the sealing area image and the transmission speed acquired by the transmission detector according to a preset detection strategy to obtain a quality detection value; verifying whether the quality detection value matches the matching verification rules to obtain a verification result; and determining whether the bag image detection result passes based on the verification result. Through the above method, by acquiring an initial image and filtering bag images, performing image size matching judgment and quality detection value matching verification respectively, and obtaining a detection result indicating whether the bag image passes, accurate detection of whether the bag seal is qualified can be achieved, significantly improving the efficiency and accuracy of sealing detection for liquid skincare product bags. Attached Figure Description

[0027] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0028] Figure 1 This is a flowchart of the sealing detection method for a liquid skin care product filling and sealing machine provided in an embodiment of the present invention;

[0029] Figure 2 This is a schematic diagram illustrating an application scenario of the sealing detection method for a liquid skincare product filling and sealing machine provided in an embodiment of the present invention.

[0030] Figure 3 This is a structural diagram of the sealing detection device for a liquid skin care product filling and sealing machine provided in an embodiment of the present invention;

[0031] Figure 4 Another structural diagram of the sealing detection device for the liquid skin care product filling and sealing machine provided in this embodiment of the invention;

[0032] Figure 5 This is a top view of the sealing detection device for a liquid skin care product filling and sealing machine provided in an embodiment of the present invention;

[0033] Figure 6 Another top view of the sealing detection device for a liquid skin care product filling and sealing machine provided in an embodiment of the present invention;

[0034] Figure 7 This is a partial structural diagram of the sealing detection device of the liquid skin care product filling and sealing machine provided in an embodiment of the present invention;

[0035] Figure 8 This is a partial structural diagram of the sealing detection device of the liquid skin care product filling and sealing machine provided in an embodiment of the present invention;

[0036] Figure 9 This is a partial structural diagram of the sealing detection device of the liquid skin care product filling and sealing machine provided in an embodiment of the present invention;

[0037] Figure 10 A schematic block diagram of a sealing detection device for a liquid skin care product filling and sealing machine provided in an embodiment of the present invention;

[0038] Figure 11 A schematic block diagram of a computer device provided in an embodiment of the present invention;

[0039] Reference numerals: 1. Machine base; 10. Detection terminal; 101. Transmission component; 21. Illumination lamp; 20. Image acquisition device; 30. Transmission detector; 40. Rotary motor; 102. Paddle; 103. Guide groove; 104. Gear; 105. Rack; 106. Connecting column; 107. Circular protrusion; 108. Long groove. Detailed Implementation

[0040] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0041] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0042] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0043] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0044] Please see Figure 1 and Figure 2 , Figure 1 This is a flowchart illustrating the sealing detection method for a liquid skincare product filling and sealing machine provided in this embodiment of the invention. Figure 2This is a schematic diagram illustrating an application scenario of the sealing detection method for a liquid skincare product filling and sealing machine provided in this embodiment of the invention. The sealing detection method is applied in a detection terminal 10, which is communicatively connected to an image acquisition device 20 and a transmission detector 30 to transmit data. The detection terminal 10 is also communicatively connected to a rotary motor 40. The sealing detection method is executed by application software installed in the detection terminal 10. The detection terminal 10 is a terminal device used to execute the sealing detection method of the liquid skincare product filling and sealing machine to detect the sealing quality of the sealed bags. The detection terminal 10 can be a desktop computer, laptop computer, tablet computer, or server terminal. The image acquisition device 20 is used to acquire images of the parallel-moving sealed bags to obtain bag images. The image acquisition device 20 can be a high-definition camera. The transmission detector 30 is used to detect the speed of the translation of the sealed bags to obtain the transmission speed. The rotary motor 40 drives a paddle to move to classify the sealed bags. Figure 1 As shown, the method includes steps S110 to S170.

[0045] S110. Obtain the initial image acquired by the image acquisition device, and select the bag image corresponding to each sealed bag body from the initial image according to the preset image filtering template.

[0046] The image acquisition device can continuously acquire initial images, with a certain interval between adjacent initial images; for example, the interval can be set to 0.2 seconds. This results in a large number of acquired initial images, many of which contain repetitive content. To reduce the number of images for subsequent analysis, an image filtering template can be used to filter out one bag image corresponding to each sealed bag from the initial images; the remaining images are directly discarded and not analyzed further. In this application, the bags used for filling skincare products are semi-transparent, thus possessing a certain degree of light transmittance.

[0047] In one embodiment, step S110 includes the following steps: determining whether the front edge of the upstream bag in the initial image reaches the starting position set in the image filtering template; if the front edge of the bag reaches the starting position, acquiring the initial image as the bag image corresponding to the bag and determining the bag as the downstream bag; if the front edge of the bag does not reach the starting position, continuing to acquire the next image as the initial image and returning to execute the step of determining whether the front edge of the upstream bag in the initial image reaches the starting position set in the image filtering template; determining whether the rear edge of the downstream bag in each subsequently acquired initial image passes through the starting position; if the rear edge of the downstream bag in each subsequently acquired initial image passes through the starting position, continuing to acquire the next image as the initial image and returning to execute the step of determining whether the front edge of the upstream bag in the initial image reaches the starting position set in the image filtering template; if the rear edge of the downstream bag in each subsequently acquired initial image does not pass through the starting position, continuing to acquire subsequent initial images and returning to execute the step of determining whether the rear edge of the downstream bag in each subsequently acquired initial image passes through the starting position.

[0048] Specifically, the image filtering template has a set starting position, and a vertical baseline can be drawn in the initial image based on this starting position. Taking the bag as transported from right to left as an example, the bag corresponding to the right side of the initial image is the upstream bag, and the bag corresponding to the left side of the initial image is the downstream bag. It can be determined whether the left side of the baseline contains part of the image of the upstream bag, thereby determining whether the front edge of the upstream bag has reached the starting position. If the left side of the baseline contains part of the image of the upstream bag, it is determined that the front edge of the upstream bag has reached the starting position. Since multiple initial images are acquired continuously, if it is determined that the front edge of the upstream bag has reached the starting position, the front edge of the upstream bag will not exceed the starting position by a long distance (the front edge of the upstream bag will only slightly exceed the starting position).

[0049] If the leading edge of the upstream bag reaches the starting position, the currently acquired initial image is used as the bag image corresponding to that bag; at this point, the current bag needs to be labeled as the downstream bag. If the leading edge of the bag has not reached the starting position, the next initial image is acquired and the judgment process for that initial image is executed.

[0050] After acquiring an image of the bag, this bag is marked as the downstream bag. Subsequent initial images are then acquired, and it is determined whether the rear edge of the downstream bag passes through the starting position. Specifically, it is determined whether the right side of the baseline corresponding to the starting position still contains a portion of the downstream bag's image. If it does not contain a portion of the downstream bag's image, it indicates that the rear edge of the downstream bag has passed through the starting position; if it does, it indicates that the rear edge of the downstream bag has not passed through the starting position. If the rear edge of the downstream bag passes through the starting position in a subsequently acquired initial image, subsequent images are acquired as initial images, and the process returns to the step of determining whether the front edge of the upstream bag has reached the starting position in the initial image. If the rear edge of the downstream bag does not pass through the starting position in a subsequently acquired initial image, subsequent initial images are acquired, and the process of determining whether the rear edge of the downstream bag has passed through the starting position is repeated. Only images of bags identified as bags are retained; other images are discarded.

[0051] S120. According to the preset image cropping rules, the corresponding sealing area image is cropped from the bag image.

[0052] Furthermore, according to the image cropping rules, the corresponding sealing area image is cropped from the bag image, so the sealing area image only contains the image information of the sealed area.

[0053] In one embodiment, step S120 includes the following steps: cropping the bag image according to the cropping area in the image cropping rules to obtain a corresponding initial cropped image; performing boundary recognition on the initial cropped image according to the recognition parameters in the image cropping rules to obtain a corresponding sealing boundary; and cropping the initial cropped image according to the sealing boundary to obtain a sealing area image corresponding to the sealing boundary.

[0054] Specifically, the bag image can be cropped according to the cropping area in the image cropping rules. Since the height of the sealing area is roughly within a certain height range, and the two sides of the bag can be accurately determined, the cropping area in the image cropping rules can be set according to the height range corresponding to the sealing area and the two sides of the bag. The initial cropped image is obtained based on the cropping area, and the initial cropped image contains the sealing area and the image information around the sealing area.

[0055] To further obtain an image containing only the sealed area, boundary recognition can be performed on the initial cropped image based on the recognition parameters in the image cropping rules. Specifically, the pixel difference value between each pixel in the initial cropped image and the edge pixels can be calculated, and it can be determined whether the pixel difference value is greater than the recognition parameters to perform boundary recognition. If the pixel difference value of a pixel is greater than the recognition parameters, then the pixel is determined to be the pixel corresponding to the sealed area; if the pixel difference value of a pixel is not greater than the recognition parameters, then the pixel is determined to be a pixel outside the sealed area. Through the above method, the boundary between the pixels in the sealed area and the pixels outside the sealed area can be determined as the sealed boundary.

[0056] The initial cropped image is cropped based on the sealing boundary, and the image inside the sealing boundary is obtained to obtain the sealing area image.

[0057] S130. Determine whether the image size of the sealing area image matches the preset sealing parameters, and obtain the corresponding matching judgment result.

[0058] Furthermore, the image size of the sealed area can be obtained, and it can be determined whether the image size matches the sealing parameters.

[0059] In one embodiment, step S130 includes the following steps: obtaining the horizontal length and sealing width of the sealing area image as the corresponding image size; determining whether the image size matches the sealing parameters to obtain the corresponding matching judgment result.

[0060] The horizontal length and sealing width of the sealing area image can be obtained as the corresponding image dimensions. The horizontal length is the length of the sealing area image in the horizontal transport direction of the sealed bag, and the sealing width is the vertical width of the sealing area image. The sealing parameters include a length parameter range and a width parameter range. It can determine whether the horizontal length in the image dimensions is within the length parameter range and whether the sealing width is within the width parameter range. If the horizontal length is within the length parameter range and the sealing width is within the width parameter range, a matching judgment result is obtained; if the horizontal length or sealing width is not within the corresponding parameter range, a mismatch judgment result is obtained.

[0061] S140. If the matching judgment result is a match, perform ambiguity detection on the sealed area image and the transmission speed acquired by the transmission detector according to the preset detection strategy to obtain the corresponding quality detection value.

[0062] If the matching judgment result is a match, then according to the detection strategy, ambiguity detection is performed on the image of the sealed area and the transmission speed acquired by the transmission detector to obtain a quality detection value that reflects the ambiguity of the sealed area.

[0063] In one embodiment, step S140 includes the following steps: obtaining a brightness coefficient corresponding to the sealed area image and the reference image according to the brightness resolution rule in the detection strategy; the reference image is a local image in the initial cropped image corresponding to the reference area set in the detection strategy; obtaining a blur coefficient corresponding to the sealed area image according to the blur resolution rule in the detection strategy; and detecting the brightness coefficient, the blur coefficient, and the transmission speed according to the comprehensive quality detection rule in the detection strategy to obtain the corresponding quality detection value.

[0064] The detection strategy includes brightness resolution rules, which can be used to obtain the brightness coefficients of the sealed area image and the reference image. Based on industrial production practices, the sealed area undergoes heat sealing, resulting in a decrease in light transmittance compared to the unsealed area due to the adhesion of multiple layers of plastic film (usually no less than two layers). Therefore, the brightness of the sealed area is lower than that of the surrounding area. The relevant physical principle is that the heat sealing process causes the plastic films on both sides to adhere, and the heating disrupts the regular arrangement of molecules within the plastic film (thermal motion intensifies random molecular motion, which returns to rest upon cooling, leading to an irregular molecular arrangement within the plastic film, thus reducing the brightness and increasing the blurriness of the sealed area). Based on the reference area set in the detection strategy, a local image corresponding to the reference area can be obtained from the initially captured image. The reference area is located at a specific position outside the sealed area. The average brightness value of each pixel in the reference image is obtained as the reference brightness average value corresponding to the reference image.

[0065] Furthermore, the brightness value of each pixel in the sealed area image can be obtained, and the ratio between the brightness value of each pixel in the sealed area image and the average reference brightness value can be calculated to obtain the brightness coefficient corresponding to each pixel.

[0066] Furthermore, the blur coefficient of the sealed area image is obtained according to the blur resolution rules in the detection strategy; the blur coefficient is used to reflect the degree of blur of the sealed area image; the larger the blur coefficient, the more blurred the image; the smaller the blur coefficient, the clearer the image.

[0067] Specifically, the sealed area image is converted to grayscale to obtain the corresponding grayscale image. Since the major axis of the sealed area image is horizontal, the upper edge of the grayscale image parallel to the horizontal direction is obtained (the analysis method for the lower edge is the same, and the analysis method for the left and right edges is similar, only the direction changes). The extension direction of the upper edge is also horizontal. A sampling line is taken in the vertical direction of the upper edge, and the grayscale value of each pixel is read sequentially along the sampling line from the dark area to the bright area. I ( x i),in x i These are the coordinates of the sampling points (unit: pixels, e.g.) x 1=0, x 2=1, ..., x n = n- 1). The number of pixels included in the sampling line can be set in the ambiguity resolution rules. For example, if the ambiguity resolution rules are set to include 11 pixels in the sampling line, then 11 pixel grayscale values ​​can be obtained by sampling.

[0068] To establish a comparative standard for the detection of different bag images, the sampled gray values ​​are normalized to the [0,1] interval. The normalization process can be expressed by formula (1):

[0069] (1);

[0070] in, I min This is the average gray value at one end of the dark area of ​​the sampling line (such as the average gray value of the first two pixels obtained from sampling). I max This is the average gray value at one end of the bright area of ​​the sampling line (such as the average gray value of the last two pixels obtained from sampling). I norm (x i ) For pixels x i The corresponding normalized value.

[0071] Sampling I norm (x i ) These are discrete pixels, and a continuous blur function needs to be obtained through interpolation or curve fitting. A commonly used fitting model can be the error function (erf): since the blur of the imaging system (such as Gaussian blur) often conforms to a normal distribution, its integral is the error function; therefore, the fitting function can be set in the blur resolution rule as shown in formula (2):

[0072] (2);

[0073] in, x 0 The "center position" of the edge (and the midpoint of the grayscale transition, corresponding to) E(x 0 ) =0.5); σ is a parameter for the degree of blur (which can be obtained by performing normal distribution statistics on the gray values ​​of pixels in the sampling line). erf(t)The error function is defined as formula (3):

[0074] (3);

[0075] erf(t) No analysis is needed; it can be obtained through numerical calculation.

[0076] Based on the calculated fitting function E(x) Further differentiation yields the blur coefficient, which represents the degree of image blur. The blur coefficient is also the same as the aforementioned fitting function. E(x) The derivative of can be expressed by formula (4):

[0077] (4);

[0078] The ambiguity resolution rules allow setting an ambiguity detection interval. For example, if the ambiguity detection interval is 10, then a sampling line is set every 10 pixels along the same edge of the sealed area image; that is, the distance between two adjacent sampling lines (two adjacent sampling lines on the same edge are parallel) is 10 pixels. Based on the above method, multiple sampling lines can be drawn on the top, bottom, left, and right edges of the sealed area image, and the ambiguity coefficient corresponding to each sampling line can be obtained.

[0079] Furthermore, the brightness coefficient, blur coefficient, and transmission speed are detected according to the comprehensive quality detection set in the detection strategy to obtain the corresponding quality detection values. The transmission speed is used to reflect the speed at which the sealed bag moves along the transport direction; with a fixed camera exposure time, the higher the transmission speed, the higher the blur degree of the image in the sealed area. Specifically, the brightness coefficient values ​​of each pixel in the sampling line corresponding to each blur coefficient are obtained, and the average value of the brightness coefficient values ​​of multiple pixels contained in the same sampling line is calculated to obtain the average brightness coefficient. The average brightness coefficient, blur coefficient, and transmission speed of the same sampling line are detected according to the detection function set in the comprehensive quality detection rules. The detection function can be expressed by formula (5):

[0080] (5);

[0081] in, J The detection value corresponding to a calculated ambiguity coefficient (each ambiguity coefficient corresponds to a sampling line), S The mean of the brightness coefficients corresponding to the ambiguity coefficients. P Here, is the ambiguity coefficient, and e is the base of the natural logarithm. V r For transmission speed, V 0The basic speed parameter is used. The detection values ​​calculated for each ambiguity coefficient are obtained as the quality detection values ​​for the sealed area image.

[0082] S150. Verify whether the quality detection value matches the preset matching verification rules to obtain the corresponding verification result.

[0083] Furthermore, the quality inspection value is checked to see if it matches the pre-set matching verification rules, thereby obtaining the corresponding verification result. The matching verification rules can check whether there are defects in the sealing area. If there are defects in the sealing area, it is determined that there is a quality problem with the seal, and the verification result is unsuccessful. If there are no defects in the sealing area, it is determined that there is no quality problem with the seal, and the verification result is successful.

[0084] In one embodiment, step S150 includes the following steps: obtaining the detection difference value corresponding to each detection value in the quality detection value; determining whether the detection difference value is within the difference interval set by the matching verification rule; determining whether each detection value in the quality detection value is within the detection interval set by the matching verification rule; if each detection difference value is within the difference interval and each detection value is within the detection interval, a matching verification result is obtained; if a certain detection difference value is not within the difference interval or a certain detection value is not within the detection interval, a mismatched detection result is obtained.

[0085] Specifically, the mean of each quality inspection value can be obtained, and the absolute value of the difference between each inspection value and this mean can be calculated as the inspection difference value corresponding to each inspection value. Thus, an inspection difference value can be calculated for each inspection value. It is then determined whether each inspection difference value falls within the difference interval set by the matching verification rule; simultaneously, it is determined whether each inspection value in the quality inspection value falls within the detection interval set by the matching verification rule. If each inspection value falls within both the difference interval and the detection interval, a matching verification result is obtained; otherwise, a mismatch verification result is obtained.

[0086] S160. If the verification result is a match, the detection result of the current bag image is determined to be passed.

[0087] S170. If the matching judgment result or the verification result is not a match, the detection result of the current bag image is determined to be unsuccessful.

[0088] The detection result of the bag image can be determined by the obtained verification result and matching judgment result. If the verification result is a match, the detection result of the bag image is passed, that is, the seal of the bag image is flawless. If the verification result is a mismatch, or the matching judgment result is a mismatch, the detection result of the bag image is failed, that is, the seal of the bag image has flaws.

[0089] In one embodiment, the method further includes: generating a corresponding rotation control command based on the detection result and sending it to the rotary motor, so as to drive the paddle to move through the rotary motor and classify the sealed bag body corresponding to the detection result.

[0090] The system can generate rotation control commands based on the detection results and send them to the drive motor. If the detection result is "pass," a forward rotation command will be generated and sent to the rotation motor. The rotation motor drives the paddle to move, thereby adjusting the downstream conveying channel of the sealed bag corresponding to the detection result, thus achieving the classification and processing of the sealed bag. Figure 5 and Figure 6 As shown, the guide channel is the main channel on the upstream side, and a partition on the downstream side forms a dual channel. The sealed bags that have completed inspection upstream continue to be transported downstream. The upper downstream channel corresponds to sealed bags classified as having flawless seals, while the lower downstream channel corresponds to sealed bags classified as having flawed seals. The subsequent processing procedures for the two channels are different. If the inspection result is "pass," a forward rotation control command is generated to the rotary motor, which drives the front end of the lever to deflect downwards. As the rollers in the transmission assembly rotate, the sealed bag is conveyed to the upper channel, as shown... Figure 5 As shown; if the detection result is a failure, a reverse rotation control command is generated to the rotary motor, which drives the front end of the lever to deflect upwards. As the rollers in the transmission assembly rotate, the sealing bag is conveyed to the lower channel, as shown. Figure 6 As shown, this method can not only achieve intelligent sealing detection, but also intelligently classify the sealed bag body based on the sealing detection results.

[0091] In the sealing detection method of the liquid skin care product filling and sealing machine provided in this embodiment of the invention, the method includes: acquiring an initial image obtained by an image acquisition device and filtering it to obtain bag images corresponding to each sealing bag; extracting the corresponding sealing area image from the bag image according to a preset image cropping rule and determining whether the image size of the sealing area image matches the sealing parameters to obtain a matching judgment result; if the matching judgment result is a match, performing ambiguity detection on the sealing area image and the transmission speed obtained by the transmission detector according to a preset detection strategy to obtain a quality detection value; verifying whether the quality detection value matches the matching verification rule to obtain a verification result; and determining whether the detection result of the bag image passes based on the verification result. Through the above method, by acquiring an initial image and filtering bag images, performing image size matching judgment and quality detection value matching verification respectively, and obtaining a detection result indicating whether the bag image passes, accurate detection of whether the bag seal is qualified can be achieved, significantly improving the efficiency and accuracy of sealing detection of liquid skin care product bags.

[0092] This invention also provides a sealing detection device for a liquid skincare product filling and sealing machine. This sealing detection device can be configured in a detection terminal 10, which is communicatively connected to an image acquisition device 20 and a transmission detector 30 to transmit data. This sealing detection device is used to execute any embodiment of the aforementioned sealing detection method for a liquid skincare product filling and sealing machine. Specifically, please refer to... Figure 10 , Figure 10 This is a schematic block diagram of a sealing detection device for a liquid skin care product filling and sealing machine provided in an embodiment of the present invention.

[0093] like Figure 10 As shown, the sealing detection device 100 of the liquid skin care product filling and sealing machine includes an image filtering unit 110, an image cropping unit 120, a matching judgment result acquisition unit 130, a quality detection value acquisition unit 140, a verification result acquisition unit 150, a first judgment unit 160, and a second judgment unit 170.

[0094] The image filtering unit 110 is used to acquire the initial image acquired by the image acquisition device, and to filter the bag images corresponding to each sealed bag body from the initial image according to the preset image filtering template.

[0095] The image cropping unit 120 is used to crop the corresponding sealing area image from the bag image according to the preset image cropping rules.

[0096] The matching judgment result acquisition unit 130 is used to determine whether the image size of the sealing area image matches the preset sealing parameters, and obtain the corresponding matching judgment result.

[0097] The quality detection value acquisition unit 140 is used to perform ambiguity detection on the sealed area image and the transmission speed acquired by the transmission detector according to a preset detection strategy if the matching judgment result is a match, and obtain the corresponding quality detection value.

[0098] The verification result acquisition unit 150 is used to verify whether the quality detection value matches the preset matching verification rules and obtain the corresponding verification result.

[0099] The first determination unit 160 is used to determine that the detection result of the current bag image is passed if the verification result is a match.

[0100] The second determination unit 170 is used to determine that the detection result of the current bag image is not passed if the matching judgment result or the verification result is not a match.

[0101] The sealing detection device for a liquid skincare product filling and sealing machine provided in this embodiment of the invention applies the sealing detection method of the liquid skincare product filling and sealing machine described above. The method includes: acquiring an initial image obtained by an image acquisition device and filtering it to obtain bag images corresponding to each sealing bag; extracting the corresponding sealing area image from the bag image according to a preset image cropping rule and determining whether the image size of the sealing area image matches the sealing parameters to obtain a matching judgment result; if the matching judgment result is a match, performing ambiguity detection on the sealing area image and the transmission speed obtained by the transmission detector according to a preset detection strategy to obtain a quality detection value; verifying whether the quality detection value matches the matching verification rule to obtain a verification result; and determining whether the detection result of the bag image passes based on the verification result. Through the above method, by acquiring an initial image and filtering bag images, performing image size matching judgment and quality detection value matching verification respectively, a detection result of whether the bag image passes is obtained; accurate detection of whether the bag seal is qualified can be achieved, greatly improving the efficiency and accuracy of sealing detection of liquid skincare product bags.

[0102] This application also provides a sealing and testing device for a liquid skincare product filling and sealing machine, such as... Figure 3 and Figure 4 As shown, the sealing inspection equipment includes a machine base 1, an inspection terminal 10, a transmission component 101, a lighting lamp 21, an image acquisition device 20, a transmission detector 30, a rotary motor 40, a paddle 102, and a guide groove 103. The transmission component 101 is mounted on the machine base 1, and the guide groove 103 is mounted on the transmission component 101. The lighting lamp 21 and the image acquisition device 20 are positioned opposite each other on both sides of the transmission component 101. The transmission detector 30 is connected to a transmission shaft in the transmission component 101. The paddle 102 is positioned in the center of the guide groove 103. The output shaft of the rotary motor 40 is fixedly connected to a gear 104, and the lower end of the paddle 102 is slidably connected to a rack 105, which meshes with the gear 104. The inspection terminal 10 is used to perform the sealing inspection method of the liquid skin care product filling and sealing machine described above.

[0103] The conveying assembly 101 consists of multiple parallel rollers and a conveying motor. The conveying motor drives the parallel rollers to roll in the same direction, thereby transporting the sealed bag body on the parallel rollers downstream. The interrelationship between the rotary motor 40, gear 104, and rack 105 is as follows: Figure 7 and Figure 8As shown. The long axis of the rack 105 is parallel to the deflection direction of the paddle 102. The paddle 102 can be made of a flexible material. The rotary motor 40, gear 104, and rack 105 are all located below the parallel roller shaft. To achieve the deflection of the paddle 102's front end via the translation of the rack 105, a connecting post 106 can be fixedly mounted on the rack 105. One end of the connecting post 106 is perpendicularly connected to the rack 105, and the other end of the connecting post 106 has a circular protrusion 107. A long groove 108 is provided on the side of the paddle 102 opposite to the connecting post 106, and the circular protrusion 107 is embedded in the long groove 108. The specific structure is as follows. Figure 9 As shown. When the rack 105 drives the connecting post 106 to move longitudinally, the front end of the paddle 102 deflects with the connecting post 106; and the circular protrusion 107 slides in the elongated groove 108 to accommodate the offset of the contact point between the paddle 102 and the connecting post 106 caused by the bending during the deflection of the paddle 102, so that the rack 105 can drive the paddle 102 to deflect more smoothly.

[0104] The sealing detection device of the aforementioned liquid skincare product filling and sealing machine can be implemented in the form of a computer program, which can be used in, for example... Figure 11 The computer device shown runs on the computer. The computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor; when the computer device executes the computer program, it implements the sealing detection method for the liquid skincare product filling and sealing machine as described in the above embodiments.

[0105] Please see Figure 11 , Figure 11 This is a schematic block diagram of a computer device provided in an embodiment of the present invention. The computer device can be a detection terminal used to perform a sealing detection method for a liquid skincare product filling and sealing machine to detect the sealing quality of the sealed bag.

[0106] See Figure 11 The computer device 500 includes a processor 502, a memory, and a communication interface 505 connected via a system bus 501. The memory may include a storage medium 503 and internal memory 504.

[0107] The storage medium 503 may store an operating system 5031 and a computer program 5032. When the computer program 5032 is executed, it causes the processor 502 to execute a sealing detection method for a liquid skin care product filling and sealing machine. The storage medium 503 may be a volatile storage medium or a non-volatile storage medium.

[0108] The processor 502 provides computing and control capabilities to support the operation of the entire computer device 500.

[0109] The internal memory 504 provides an environment for the operation of the computer program 5032 in the storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute the sealing detection method of the liquid skin care product filling and sealing machine.

[0110] This communication interface 505 is used for network communication, such as providing data transmission. Those skilled in the art will understand that... Figure 11 The structure shown is merely a block diagram of a portion of the structure related to the present invention and does not constitute a limitation on the computer device 500 to which the present invention is applied. The specific computer device 500 may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0111] The processor 502 is used to run the computer program 5032 stored in the memory to implement the corresponding function in the sealing detection method of the liquid skin care product filling and sealing machine.

[0112] Those skilled in the art will understand that Figure 11 The embodiments of the computer device shown do not constitute a limitation on the specific configuration of the computer device. In other embodiments, the computer device may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. For example, in some embodiments, the computer device may include only memory and a processor. In such embodiments, the structure and function of the memory and processor are different from those shown. Figure 11 The embodiments shown are consistent and will not be described again here.

[0113] It should be understood that, in this embodiment of the invention, the processor 502 may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0114] In another embodiment of the invention, a computer-readable storage medium is provided. This computer-readable storage medium may be volatile or non-volatile. The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps included in the sealing detection method of the liquid skincare product filling and sealing machine described above.

[0115] Those skilled in the art will readily understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this invention.

[0116] In the embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Units with the same function may be grouped into one unit. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices, or units, or it may be an electrical, mechanical, or other form of connection.

[0117] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of the present invention, depending on actual needs.

[0118] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0119] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a computer-readable storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned computer-readable storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), magnetic disks, or optical disks.

[0120] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A sealing detection method for a liquid skincare product filling and sealing machine, characterized in that, The method is applied in a detection terminal, which is communicatively connected to an image acquisition device and a transmission detector to achieve data transmission. The method includes: Acquire the initial image acquired by the image acquisition device, and filter the bag images corresponding to each sealing bag body from the initial image according to the preset image filtering template; The corresponding sealing area image is extracted from the bag image according to the preset image cropping rules; Determine whether the image size of the sealed area image matches the preset sealing parameters, and obtain the corresponding matching judgment result; If the matching judgment result is a match, the image of the sealed area and the transmission speed acquired by the transmission detector are subjected to ambiguity detection according to the preset detection strategy to obtain the corresponding quality detection value. The quality detection value is checked to see if it matches the preset matching verification rules, and the corresponding verification result is obtained. If the verification result is a match, the detection result of the current bag image is determined to be passed; If the matching judgment result or the verification result is not a match, the detection result of the current bag image is determined to be unsuccessful. The step of extracting the corresponding sealing area image from the bag image according to preset image cropping rules includes: The bag image is cropped according to the cropping region in the image cropping rules to obtain the corresponding initial cropped image; The initial cropped image is subjected to boundary recognition based on the recognition parameters in the image cropping rules to obtain the corresponding sealing boundary. The initial cropped image is cropped according to the sealing boundary to obtain a sealing area image corresponding to the sealing boundary; The step of performing ambiguity detection on the sealed area image and the transmission speed acquired by the transmission detector according to a preset detection strategy to obtain the corresponding quality detection value includes: The brightness coefficients corresponding to the sealed area image and the reference image are obtained according to the brightness analysis rules in the detection strategy; the reference image is a local image in the initial cropped image that corresponds to the reference area set in the detection strategy. The ambiguity coefficient corresponding to the sealed area image is obtained according to the ambiguity resolution rule in the detection strategy; The brightness coefficient, the ambiguity coefficient, and the transmission speed are detected according to the comprehensive quality detection rules in the detection strategy to obtain the corresponding quality detection values; The step of obtaining the ambiguity coefficient corresponding to the sealed region image according to the ambiguity resolution rule in the detection strategy includes: converting the sealed region image to grayscale to obtain a corresponding grayscale image; obtaining the pixel grayscale value corresponding to the pixel points contained in the sampling line according to the sampling line set in the ambiguity resolution rule; normalizing the sampled pixel grayscale value to obtain the normalized value corresponding to the pixel grayscale value; configuring the fitting function set in the ambiguity resolution rule according to the parameter of ambiguity, wherein the parameter of ambiguity is obtained by performing normal distribution statistics on the normalized value; and taking the derivative of the fitting function to obtain the corresponding ambiguity coefficient. The brightness coefficient, the ambiguity coefficient, and the transmission speed are detected according to the comprehensive quality detection rules in the detection strategy to obtain the corresponding quality detection values. This includes: obtaining the brightness coefficient values ​​of each pixel in the sampling line corresponding to each ambiguity coefficient; calculating the average value of the brightness coefficient values ​​of multiple pixels contained in the same sampling line to obtain the average brightness coefficient; and detecting the average brightness coefficient, ambiguity coefficient, and transmission speed of the same sampling line according to the detection function in the comprehensive quality detection rules to obtain the corresponding detection values ​​as the quality detection values ​​of the sealed area image.

2. The sealing detection method for the liquid skincare product filling and sealing machine according to claim 1, characterized in that, The step of selecting bag images corresponding to each sealed bag body from the initial image according to a preset image filtering template includes: Determine whether the front edge of the upstream bag in the initial image reaches the starting position set in the image filtering template; If the front edge of the bag reaches the starting position, the initial image is acquired as the bag image corresponding to the bag and the bag is determined to be the downstream bag. If the front edge of the bag body has not reached the starting position, continue to acquire the next image as the initial image and return to execute the step of determining whether the front edge of the upstream bag body in the initial image has reached the starting position set in the image filtering template; Determine whether the rear edge of the downstream bag passes through the starting position in each of the subsequent initial images acquired; If the rear edge of the downstream bag in the subsequent initial image passes through the starting position, continue to acquire the next image as the initial image and return to execute the step of determining whether the front edge of the upstream bag in the initial image has reached the starting position set in the image filtering template; If the rear edge of the downstream bag does not pass through the starting position in the subsequent initial images, continue to acquire subsequent initial images and return to the step of determining whether the rear edge of the downstream bag passes through the starting position in each of the subsequent initial images.

3. The sealing detection method for the liquid skincare product filling and sealing machine according to claim 1, characterized in that, The step of determining whether the image size of the sealed area image matches the preset sealing parameters and obtaining the corresponding matching determination result includes: The horizontal length and sealing width of the sealed area image are obtained as the corresponding image size; The matching result is obtained by determining whether the image size matches the sealing parameters.

4. The sealing detection method for the liquid skincare product filling and sealing machine according to claim 1, characterized in that, The step of verifying whether the quality detection value matches the preset matching verification rules to obtain the corresponding verification result includes: Obtain the detection difference value corresponding to each detection value in the quality detection values; Determine whether the detected difference value is within the difference range set by the matching verification rule; Determine whether each of the quality detection values ​​is within the detection range set by the matching verification rule; If all detected difference values ​​are within the difference range and all detected values ​​are within the detection range, a matching verification result is obtained; If a certain detection difference value is not within the difference range or a certain detection value is not within the detection range, a mismatched detection result is obtained.

5. The sealing detection method for a liquid skincare product filling and sealing machine according to any one of claims 1-4, characterized in that, The detection terminal is also connected to a rotary motor for communication. After obtaining the detection result of the bag image, it further includes: Based on the detection results, a corresponding rotation control command is generated and sent to the rotary motor, so that the rotary motor drives the paddle to move and classify the sealed bag body corresponding to the detection results.

6. A sealing detection device for a liquid skincare product filling and sealing machine, characterized in that, The device is configured in a detection terminal, which is communicatively connected to an image acquisition device and a transmission detector to transmit data information. The sealing detection device of the liquid skin care product filling and sealing machine is used to perform the sealing detection method of the liquid skin care product filling and sealing machine as described in any one of claims 1-5. The device includes: The image filtering unit is used to acquire the initial image acquired by the image acquisition device, and to filter the bag images corresponding to each sealing bag body from the initial image according to the preset image filtering template; An image cropping unit is used to crop the corresponding sealing area image from the bag image according to a preset image cropping rule; The matching judgment result acquisition unit is used to determine whether the image size of the sealing area image matches the preset sealing parameters, and obtain the corresponding matching judgment result; The quality detection value acquisition unit is used to perform ambiguity detection on the sealed area image and the transmission speed acquired by the transmission detector according to a preset detection strategy if the matching judgment result is a match, and obtain the corresponding quality detection value. The verification result acquisition unit is used to verify whether the quality detection value matches the preset matching verification rules and obtain the corresponding verification result. The first determination unit is used to determine that the detection result of the current bag image is passed if the verification result is a match. The second determination unit is used to determine that the detection result of the current bag image is not passed if the matching judgment result or the verification result is not a match.

7. A sealing and testing device for a liquid skincare product filling and sealing machine, characterized in that, The sealing inspection equipment includes a machine base, an inspection terminal, a transmission component, a lighting lamp, an image acquisition device, a transmission detector, a rotary motor, a lever, and a guide groove; The transmission component is mounted on the machine base, the guide groove is mounted on the transmission component, and the lighting lamp and the image acquisition device are mounted opposite each other on both sides of the transmission component; the transmission detector is connected to a transmission shaft in the transmission component; the paddle is mounted in the center of the guide groove; the output shaft of the rotary motor is fixedly connected to a gear, the lower end of the paddle is slidably connected to a rack, and the rack meshes with the gear; The detection terminal includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; The processor, when executing a program stored in memory, implements the sealing detection method of the liquid skin care product filling and sealing machine as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the sealing detection method of the liquid skin care product filling and sealing machine as described in any one of claims 1 to 5.

Images