Quality detection device for pantoprazole sodium enteric capsule

By using different light angles to collect first and second types of images in the pantoprazole sodium enteric capsule quality detection device, and determining the image selection method based on the image difference reference value and the capsule influence reference value, the problem of low capsule detection efficiency is solved. , achieving more efficient capsule quality testing.

CN119064364APending Publication Date: 2024-12-03HUNAN MINGRUI PHARMACEUTICAL CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202410919834.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-10
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

In the prior art, capsule image acquisition is susceptible to the position and intensity of the light source, resulting in low capsule defect detection efficiency and inability to quickly and effectively screen, resulting in poor capsule quality detection efficiency.

Method used

A pantoprazole sodium enteric capsule quality detection device is designed, including an image acquisition module, a data analysis module and a control module. Class I and Class II images are collected through different light angles, and reference values ​​and capsules are affected according to the image difference reference values ​​and capsules. Value determines the image selection method to improve the accuracy and efficiency of image selection.

Benefits of technology

By collecting and selecting images divided into first and second categories, the efficiency of capsule quality detection is improved, the time for subsequent users to determine defects is reduced, and the detection accuracy is ensured while improving detection efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119064364A_ABST
    Figure CN119064364A_ABST
Patent Text Reader

Abstract

The invention relates to the field of capsule detection, in particular to a pantoprazole sodium enteric capsule quality detection device which comprises an image acquisition module used for respectively acquiring first-class images and second-class images of capsules at different illumination angles; the data analysis module is used for determining an image acquisition state according to the image difference reference value and the capsule influence reference value, and determining an image selection mode according to the image acquisition state; the control module is used for adjusting the shooting quantity when the stability coefficient of the image difference reference value is within the range of the stability coefficient needing to be regulated and controlled, and adjusting the single throughput when the influence difference value is within the range of the influence difference value needing to be regulated and controlled; the image selection module is used for carrying out image selection according to the stability coefficient or carrying out image selection according to the capsule interval; according to the invention, capsule images are effectively screened, and the efficiency of capsule quality detection is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the field of capsule detection, and in particular to a pantoprazole sodium enteric-coated capsule quality detection device. Background Art

[0002] Capsule inspection is one of the important links in the production of Pantoprazole Sodium Enteric-coated Capsules. As one of the existing drugs with the largest demand, Pantoprazole Sodium Enteric-coated Capsules have high inspection quality requirements. The current manual quality inspection has a lot of uncertainty and lacks detection accuracy. In addition, due to environmental reasons, workers have to inspect small objects under glaring light conditions for a long time, which is very easy to cause visual fatigue and lead to false detection. Therefore, technicians have proposed an automated detection technology that applies machine vision to capsule surface defect detection. However, in actual applications, the acquisition of capsule images is easily affected by the position and intensity of the light source, and it is impossible to quickly and effectively screen the acquired capsule images, resulting in poor efficiency of capsule defect detection. Therefore, how to achieve fast and effective capsule surface image acquisition and screening is a problem that technicians in this field urgently need to solve.

[0003] Chinese patent application publication number CN111047573A discloses a capsule defect detection method, which includes the following steps: a camera receives an instruction to start taking pictures and collect images of capsules; color measurement is performed on the collected images containing capsules to obtain color information of the capsule images; color extraction is performed on the images containing color information, and the pixel part of the specified color range is extracted and binarized to obtain an 8-bit binary image; morphological processing is performed on the 8-bit binary image to extract the shape features of the capsule image; Blob analysis is used to detect, locate and analyze the shape features in the morphologically processed 8-bit binary image area to determine defective capsules or good capsules; it can be seen that the capsule defect detection method has the following problems: it is impossible to screen the collected images containing capsules, so each image needs to be analyzed, resulting in a long image analysis time loss in actual application, which in turn leads to poor capsule detection efficiency. Summary of the invention

[0004] To this end, the present invention provides a pantoprazole sodium enteric-coated capsule quality detection device to overcome the problem in the prior art that the collected capsule images cannot be effectively screened, resulting in poor capsule quality detection efficiency in practical applications.

[0005] To achieve the above object, the present invention provides a pantoprazole sodium enteric-coated capsule quality detection device, comprising:

[0006] An image acquisition module, used to respectively acquire the first type of image and the second type of image of the capsule under different illumination angles;

[0007] a data analysis module connected to the image acquisition module, for determining an image acquisition state according to an image difference reference value and a capsule influence reference value, and determining an image selection mode according to the image acquisition state;

[0008] A control module connected to the image acquisition module and the data analysis module, for adjusting the number of shots when the stability coefficient of the image difference reference value is within the stability coefficient range to be adjusted, and for adjusting the single pass amount when the influence difference is within the influence difference range to be adjusted;

[0009] An image selection module is connected to the image acquisition module and the data analysis module, and is used to select images according to the stability coefficient or the capsule interval.

[0010] Furthermore, the image acquisition module includes:

[0011] A light-proof box, which is a box with a cube structure and an empty bottom;

[0012] A high-precision camera assembly is arranged at the top of the light-proof box to collect images of the capsule;

[0013] A plurality of illumination components, including a first illumination component disposed adjacent to the high-precision camera component and an annular light source disposed on the inner wall of the light-shielding box, wherein the central axis of the annular light source passes through the installation position of the high-precision camera component;

[0014] A conveying component, which is arranged at the bottom of the light-proof box and is used to convey capsules;

[0015] The isolation assembly comprises a column arranged on one side of the transmission assembly and an isolation rod located above the transmission assembly and slidably connected to the column, and is used to achieve the passage and isolation of capsules by changing the distance between the isolation rod and the transmission assembly.

[0016] Furthermore, the image acquisition module is provided with a first shooting mode and a second shooting mode, and the positions of the illumination components turned on are different in different shooting modes;

[0017] The first shooting mode and the second shooting mode are used cyclically;

[0018] The images acquired in the first shooting mode are recorded as type one images, and the images acquired in the second shooting mode are recorded as type two images.

[0019] Furthermore, the data analysis module determines an image selection method according to the image acquisition state, including selecting images according to a stability coefficient, or selecting images according to a capsule interval.

[0020] Furthermore, the data analysis module is provided with different preset image acquisition states, including that the image difference reference value is greater than the preset image difference reference value and the capsule influence reference value is less than or equal to the preset capsule influence reference value, or that the image difference reference value is less than or equal to the preset image difference reference value and the capsule influence reference value is less than or equal to the preset capsule influence reference value.

[0021] Furthermore, the data analysis module obtains the comparison area in the second type of image corresponding to the position of each capsule in the first type of image and detects the bright spot difference;

[0022] The image difference reference value is positively correlated with the bright spot difference value.

[0023] Furthermore, the control module detects the stability coefficient corresponding to the image difference reference value, and increases and adjusts the number of shots when the stability coefficient of the image difference reference value is within the range of the stability coefficient to be adjusted;

[0024] The increase value of the shooting quantity is negatively correlated with the stability coefficient.

[0025] Further, the control module detects the influence difference corresponding to the influence reference value, and when the influence difference is within the influence difference range to be regulated, reduces the single pass amount;

[0026] The reduction value of the single pass volume is positively correlated with the impact difference;

[0027] The impact difference is determined based on the capsule impact reference value and the preset capsule impact reference value.

[0028] Furthermore, when the image selection module selects images according to the stability coefficient, if the stability coefficient is less than a preset stability coefficient, the image selection module determines to select two second-category images with the smallest number of bright spots and the largest number of bright spots and the corresponding first-category images as valid images;

[0029] If the stability coefficient is greater than or equal to the preset stability coefficient, the image selection module determines to select a number of valid images according to the number of bright spots.

[0030] Furthermore, the image selection module selects images according to the capsule interval, and selects a number of images in the order of interval influence distance from large to small and records them as valid images.

[0031] Compared with the prior art, the beneficial effect of the present invention lies in that the image acquisition module in the technical solution of the present invention is provided with a first shooting mode and a second shooting mode, and the positions of the lighting components turned on in different shooting modes are different. The reflective characteristics of the capsule are used to divide the image into one type of image and two types of image, and then the image selection method is determined according to the image acquisition state, so that the image selection method is more in line with the actual working scene, and the image difference reference value between the one type of image and the second type of image is used to reflect the probability of the existence of the current capsule defect, so that the subsequent image selection method is determined more accurately, thereby improving the efficiency of the capsule quality detection of the present invention.

[0032] Furthermore, the present invention acquires multiple first-category images and second-category images, and then selects valid images. On the premise of ensuring that the number of acquired images can meet the defect detection accuracy, several valid images with the best defect characterization effect are effectively selected, thereby reducing the time for subsequent user defect judgment.

[0033] Furthermore, the control module in the present invention detects the stability coefficient corresponding to the image difference reference value, and increases the number of shots when the stability coefficient of the image difference reference value is within the range of the stability coefficient that needs to be adjusted. The stability coefficient of the image difference reference value reflects the probability that defects may exist in the capsule, so that the number of shots can meet the effective data analysis requirements, thereby improving the efficiency of capsule quality detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 This is a module connection diagram of a quality inspection device for pantoprazole sodium enteric-coated capsules of the present invention;

[0035] Figure 2 It is a structural schematic diagram of the image acquisition module of the present invention;

[0036] Figure 3 The present invention is a flow chart of determining an image selection method according to an image acquisition state. DETAILED DESCRIPTION

[0037] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; 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 present invention.

[0038] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0039] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the components or elements must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be understood as a limitation on the present invention.

[0040] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" 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 a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0041] See also Figure 1 As shown, it is a module connection diagram of a pantoprazole sodium enteric-coated capsule quality detection device of the present invention. The present invention provides a pantoprazole sodium enteric-coated capsule quality detection device, comprising:

[0042] An image acquisition module, used to respectively acquire the first type of image and the second type of image of the capsule under different illumination angles;

[0043] a data analysis module connected to the image acquisition module, for determining an image acquisition state according to an image difference reference value and a capsule influence reference value, and determining an image selection mode according to the image acquisition state;

[0044] A control module connected to the image acquisition module and the data analysis module, for adjusting the number of shots when the stability coefficient of the image difference reference value is within the stability coefficient range to be adjusted, and for adjusting the single pass amount when the influence difference is within the influence difference range to be adjusted;

[0045] An image selection module is connected to the image acquisition module and the data analysis module, and is used to select images according to the stability coefficient or the capsule interval.

[0046] The application scenario of the present invention is the quality inspection of pantoprazole sodium enteric-coated capsules, especially the quality inspection of surface depressions of pantoprazole sodium enteric-coated capsules. The detection device can be connected to a production line, and the production line transmits the produced capsules to the detection device for inspection through any existing transmission method. The detection device can also be used alone, and the user places the produced capsules on the transmission component of the detection device.

[0047] See also Figure 2As shown, it is a structural schematic diagram of the image acquisition module of the present invention, and the image acquisition module includes:

[0048] A light-proof box 1, which is a box with a cube structure and an empty bottom;

[0049] A high-precision camera assembly (not shown), which is arranged at the top of the light-proof box and is used to capture images of the capsule;

[0050] Several illumination components, including a first illumination component 2 arranged adjacent to the high-precision camera component and an annular light source 3 arranged on the inner wall of the light-shielding box, wherein the central axis of the annular light source 3 passes through the installation position of the high-precision camera component;

[0051] A conveying component 4, which is disposed at the bottom of the light-proof box 1 and is used to convey capsules;

[0052] An isolation assembly, comprising a column (not shown) disposed on one side of the conveying assembly and an isolation rod located above the conveying assembly and slidably connected to the column, for achieving the passage and isolation of capsules by changing the distance between the isolation rod and the conveying assembly;

[0053] The first illumination component 2 is a bar-shaped light source;

[0054] The isolation rod includes a first isolation rod body 5 and a second isolation rod body 6. The first isolation rod body 5 and the second isolation rod body 6 can be connected to a column respectively, or connected to the same column through a connecting structure. This is a structure that is easy to implement for those skilled in the art and there is no need to elaborate on it here. During operation, the first isolation rod body 5 and the second isolation rod body 6 fall, and the first isolation rod body 5 and the second isolation rod body 6 keep the capsule to be detected under the light-proof box. The surface of the second isolation rod body 6 is a light-absorbing material, preferably a black fiber cloth.

[0055] See also Figures 1 to 3 As shown, the image acquisition module is provided with a first shooting mode and a second shooting mode, and the positions of the illumination components turned on in different shooting modes are different;

[0056] The first shooting mode and the second shooting mode are used cyclically;

[0057] The images acquired in the first shooting mode are recorded as type one images, and the images acquired in the second shooting mode are recorded as type two images.

[0058] Among them, in the first shooting mode, the annular light source is turned on and the first illumination component is turned off, and the illumination direction of the first illumination component is perpendicular to the transmission direction of the transmission component. In the second shooting mode, the first illumination component is turned on and the annular light source is turned off.

[0059] Specifically, the data analysis module determines the image selection method according to the image acquisition state, including selecting images according to the stability coefficient, or selecting images according to the capsule interval.

[0060] Specifically, the data analysis module is provided with different preset image acquisition states, including a first preset image acquisition state and a second preset image acquisition state;

[0061] The first preset image acquisition state is that the image difference reference value is greater than the preset image difference reference value and the capsule influence reference value is less than or equal to the preset capsule influence reference value;

[0062] The second preset image acquisition state is that the image difference reference value is less than or equal to the preset image difference reference value and the capsule influence reference value is less than or equal to the preset capsule influence reference value;

[0063] If the image acquisition state is in the first preset image acquisition state, the image selection method is to select the image according to the stability coefficient;

[0064] If the image acquisition state is in the second preset image acquisition state, the image selection method is to select images according to the capsule interval.

[0065] Specifically, the data analysis module obtains the comparison area corresponding to the position of each capsule in the first type of image in the second type of image and detects the bright spot difference;

[0066] The image difference reference value is positively correlated with the bright spot difference value.

[0067] Among them, the method for confirming the comparison area is to select the capsule position for the first type of image through image processing and computer vision technology, and record the selected area corresponding to each capsule position in the first type of image as the comparison area, and binarize the second type of image. The pixel value of each pixel block in the processed second type of image is 0 or 255. The area corresponding to the comparison area position in the first type of image in the processed second type of image is extracted, and the number H of continuous areas with a pixel value of 255 is detected. The continuous area is an area where all the pixel blocks in the area have a pixel value of 255. The bright spot difference is |H-Hmax|, Hmax is the number of comparison areas. It can be understood that the second In the shooting mode, the capsule will reflect light due to the material, thus presenting a continuous long strip of bright spots. However, the capsule with a concave type defect on the surface will present multiple bright spots or no bright spots. Therefore, the image difference reference value reflects the probability that the capsule in the image may have defects, thereby making the subsequent image selection more targeted. The capsule influence reference value is confirmed by detecting the interval influence distance Li of each comparison area in a type of image. The capsule influence reference value is the minimum value among Li, i=1,2,3,...,Hmax. For the i-th comparison area, its interval influence distance is the minimum distance between the i-th comparison area and the nearest comparison area.

[0068] The preset image difference reference value and the preset capsule influence reference value can be set by the user according to the actual working scenario. The greater the user's demand for capsule defect recognition efficiency, the greater the value of the preset image difference reference value, and the smaller the value of the preset capsule influence reference value. A preset image difference reference value and a preset capsule influence reference value are provided. The preset image difference reference value is 30% of Hmax. The preset capsule influence reference value can be obtained by the user through quantitative experiments to detect the position recognition accuracy of the capsule image under different capsule influence reference values. The minimum capsule influence reference value corresponding to the position recognition accuracy that meets the user's needs is recorded as the preset capsule influence reference value.

[0069] Specifically, the control module detects the stability coefficient corresponding to the image difference reference value, and increases and adjusts the number of shots when the stability coefficient of the image difference reference value is within the range of the stability coefficient to be adjusted;

[0070] The increase value of the shooting quantity is negatively correlated with the stability coefficient.

[0071] The working process of the image acquisition module is to cyclically open the first shooting mode and the second shooting mode, and obtain one type one image and one type two image in one image acquisition. The number of image acquisitions is set by the user. The greater the user's demand for defect recognition accuracy, the greater the number of image acquisitions. A value of the number of image acquisitions is provided, and the number of image acquisitions is 3. The calculation formula of the stability coefficient S is:

[0072]

[0073] Among them, Sc is the image difference reference value corresponding to the c-th image acquisition, S0 is the average value of all image difference reference values, cmax is the number of image acquisitions, c=1, 2, 3, ..., cmax, the values ​​within the range of the stability coefficient to be adjusted are all greater than the preset stability coefficient, the value of the preset stability coefficient can be set by the user in the actual working scenario, and a preset stability coefficient value is provided, which is 20% of S0.

[0074] Specifically, the control module detects the influence difference corresponding to the influence reference value, and when the influence difference is within the influence difference range to be regulated, reduces the single pass amount;

[0075] The reduction value of the single pass volume is positively correlated with the impact difference;

[0076] The impact difference is determined based on the capsule impact reference value and the preset capsule impact reference value.

[0077] Preferably, the conveying method in the present invention uses a robotic arm to convey the produced capsules to the detection device. This is a prior art that has been mastered by those skilled in the art and will not be elaborated here. The single throughput is the number of capsules conveyed by the robotic arm at a single time, and the impact difference is the value obtained by subtracting the preset capsule impact reference value from the capsule impact reference value. The values ​​within the impact difference range need to be controlled to be greater than 0.

[0078] Specifically, the image selection module selects images according to the stability coefficient. If the stability coefficient is less than the preset stability coefficient, the image selection module determines to select the two second-category images with the smallest number of bright spots and the largest number of bright spots and the corresponding first-category images as valid images.

[0079] If the stability coefficient is greater than or equal to the preset stability coefficient, the image selection module determines to select a number of valid images according to the number of bright spots.

[0080] The image selection module determines and selects the two first-class images with the smallest and largest number of bright spots as valid images, and records the second-class images with different bright spot positions from the current valid image as valid images, and also records the first-class images corresponding to the second-class images with different bright spot positions from the current valid image as valid images.

[0081] Specifically, the image selection module selects images according to the capsule interval, and selects several first-class images and corresponding second-class images in the order of interval influence distance from large to small as valid images. The number of first-class images selected is set by the user. The larger the number, the greater the defect detection accuracy.

[0082] The image selection module transmits the valid images to the user for final defect determination.

[0083] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0084] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A quality inspection device for pantoprazole sodium enteric-coated capsules, characterized in that: include: An image acquisition module, used to respectively acquire the first type of image and the second type of image of the capsule under different illumination angles; a data analysis module connected to the image acquisition module, for determining an image acquisition state according to an image difference reference value and a capsule influence reference value, and determining an image selection mode according to the image acquisition state; A control module connected to the image acquisition module and the data analysis module, for adjusting the number of shots when the stability coefficient of the image difference reference value is within the stability coefficient range to be adjusted, and for adjusting the single pass amount when the influence difference is within the influence difference range to be adjusted; An image selection module is connected to the image acquisition module and the data analysis module, and is used to select images according to the stability coefficient or the capsule interval.

2. The pantoprazole sodium enteric-coated capsule quality detection device according to claim 1, characterized in that: The image acquisition module includes: A light-proof box, which is a box with a cube structure and an empty bottom; A high-precision camera assembly is arranged at the top of the light-proof box to collect images of the capsule; A plurality of illumination components, including a first illumination component disposed adjacent to the high-precision camera component and an annular light source disposed on the inner wall of the light-shielding box, wherein the central axis of the annular light source passes through the installation position of the high-precision camera component; A conveying component, which is arranged at the bottom of the light-proof box and is used to convey capsules; The isolation assembly comprises a column arranged on one side of the transmission assembly and an isolation rod located above the transmission assembly and slidably connected to the column, and is used to achieve the passage and isolation of capsules by changing the distance between the isolation rod and the transmission assembly.

3. The pantoprazole sodium enteric-coated capsule quality detection device according to claim 2, characterized in that: The image acquisition module is provided with a first shooting mode and a second shooting mode, and the positions of the illumination components turned on are different in different shooting modes; The first shooting mode and the second shooting mode are used cyclically; The images acquired in the first shooting mode are recorded as type one images, and the images acquired in the second shooting mode are recorded as type two images.

4. The pantoprazole sodium enteric-coated capsule quality detection device according to claim 3, characterized in that: The data analysis module determines an image selection method according to the image acquisition state, including selecting images according to a stability coefficient, or selecting images according to a capsule interval.

5. The pantoprazole sodium enteric-coated capsule quality detection device according to claim 4, characterized in that: The data analysis module is provided with different preset image acquisition states, including that the image difference reference value is greater than the preset image difference reference value and the capsule influence reference value is less than or equal to the preset capsule influence reference value, or that the image difference reference value is less than or equal to the preset image difference reference value and the capsule influence reference value is less than or equal to the preset capsule influence reference value.

6. The pantoprazole sodium enteric-coated capsule quality detection device according to claim 5, characterized in that: The data analysis module obtains the comparison area corresponding to the position of each capsule in the first type of image in the second type of image and detects the bright spot difference; The image difference reference value is positively correlated with the bright spot difference value.

7. The pantoprazole sodium enteric-coated capsule quality detection device according to claim 6, characterized in that: The control module detects the stability coefficient corresponding to the image difference reference value, and increases and adjusts the number of shots when the stability coefficient of the image difference reference value is within the range of the stability coefficient to be adjusted; The increase value of the shooting quantity is negatively correlated with the stability coefficient.

8. The pantoprazole sodium enteric-coated capsule quality detection device according to claim 7, characterized in that: The control module detects the influence difference corresponding to the influence reference value, and reduces and adjusts the single pass amount when the influence difference is within the influence difference range to be regulated; The reduction value of the single pass volume is positively correlated with the impact difference; The impact difference is determined based on the capsule impact reference value and the preset capsule impact reference value.

9. The pantoprazole sodium enteric-coated capsule quality detection device according to claim 8, characterized in that: The image selection module selects images according to the stability coefficient. If the stability coefficient is less than the preset stability coefficient, the image selection module determines to select the two second-category images with the smallest number of bright spots and the largest number of bright spots and the corresponding first-category images as valid images; If the stability coefficient is greater than or equal to the preset stability coefficient, the image selection module determines to select a number of valid images according to the number of bright spots.

10. The pantoprazole sodium enteric-coated capsule quality detection device according to claim 9, characterized in that: The image selection module selects images according to the capsule interval, and selects several images in the order of interval influence distance from large to small and records them as valid images.

Citation Information

Cited By

  • Automatic welding position identification method for hot melting gasket

    CN120619666A