Perfusator quality inspection method, device and equipment and storage medium
By acquiring and processing images inside the perfusion device, combined with visual inspection and emergency braking components, the problems of error and high cost of traditional inspection methods are solved, achieving high-accuracy quality inspection and ensuring the safety of the blood perfusion device before it leaves the factory.
Patent Information
- Application Number
- CN202510664553.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-22
- Publication Date
- 2025-10-28
AI Technical Summary
Existing technologies are susceptible to interference from internal liquids and resins when testing blood perfusion devices, leading to errors in test results. Furthermore, traditional testing methods are costly and cannot prevent malfunctions in advance, posing risks to treatment safety.
By acquiring images of the inside of the irrigation device, performing preprocessing and feature extraction, and using a visual inspection device to acquire images of the irrigation device in its initial and rotating states, combined with emergency braking and motion components, foreign objects inside are ejected. Image correction and feature comparison are then performed to improve detection accuracy.
This enables highly accurate quality inspection of the perfusion device before it leaves the factory, reducing false positives, ensuring treatment safety, and lowering testing costs.
Smart Images
Figure CN120852270A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of irrigation device technology, and in particular to a quality inspection method, apparatus, equipment and storage medium for irrigation devices. Background Technology
[0002] A hemoperfusion device is a medical device for blood purification. The performance of the hemoperfusion device has a crucial impact on the safety of hemoperfusion therapy; therefore, testing the hemoperfusion device is extremely important. Currently, before leaving the factory, hemoperfusion devices are generally tested for malfunctions or defects using technologies such as microwave testing, ultrasound testing, X-ray testing, and CT scans. However, the testing results may be affected by interference from internal liquids (such as water) and resin within the hemoperfusion device, leading to errors. Summary of the Invention
[0003] This application provides a method, apparatus, equipment, and storage medium for quality inspection of irrigation devices, aiming to improve the accuracy of irrigation device quality inspection.
[0004] To achieve the above objectives, this application provides a quality inspection method for an irrigation device, the quality inspection method for the irrigation device comprising:
[0005] Acquire images of the inside of the perfusion apparatus;
[0006] The image is preprocessed;
[0007] Feature extraction is performed on the preprocessed image;
[0008] The extracted features are compared with standard features to obtain the quality inspection results of the irrigation device.
[0009] In addition, to achieve the above objectives, this application also provides a quality inspection device for an irrigation device, which includes a memory and a processor;
[0010] The memory is used to store computer programs;
[0011] The processor is configured to execute the computer program and, in executing the computer program, implement the steps of the perfusion device quality inspection method as described above.
[0012] In addition, to achieve the above objectives, this application also provides a quality inspection device, which includes a quality inspection apparatus for the irrigation device as described above.
[0013] In addition, to achieve the above objectives, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described perfusion device quality inspection method.
[0014] This application discloses a quality inspection method, apparatus, equipment, and storage medium for an irrigation device. By acquiring an image of the inside of the irrigation device, preprocessing the image, extracting features from the preprocessed image, and comparing the extracted features with standard features, the quality inspection results of the irrigation device are obtained, thereby improving the accuracy of the quality inspection of the irrigation device. Attached Figure Description
[0015] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0016] Figure 1 This is a schematic flowchart illustrating the steps of a quality inspection method for an irrigation device provided in an embodiment of this application;
[0017] Figure 2 This is a schematic flowchart illustrating the steps for acquiring an image inside an irrigation device, as provided in an embodiment of this application.
[0018] Figure 3 This is a schematic diagram of multiple cameras in a visual inspection component provided in an embodiment of this application;
[0019] Figure 4 This is a schematic diagram of an irrigation device that oscillates radially at a low amplitude and high frequency, according to an embodiment of this application.
[0020] Figure 5 This is a schematic diagram of a method for controlling an irrigation device to rotate at high speed in the same direction, as provided in an embodiment of this application.
[0021] Figure 6 This is a schematic diagram of the liquid and resin area inside an irrigation device provided in an embodiment of this application;
[0022] Figure 7 This is a schematic flowchart illustrating the steps of preprocessing the image provided in an embodiment of this application;
[0023] Figure 8 This is a schematic flowchart illustrating the steps of feature extraction from a preprocessed image provided in an embodiment of this application;
[0024] Figure 9 This is a schematic flowchart illustrating the steps of comparing extracted features with standard features to obtain the quality inspection results of the irrigation device, as provided in an embodiment of this application.
[0025] Figure 10 This is a flowchart of a feature comparison process provided in an embodiment of this application;
[0026] Figure 11 This is a schematic block diagram of a quality inspection device for an irrigation device provided in an embodiment of this application. Detailed Implementation
[0027] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0028] The flowchart shown in the attached diagram is for illustrative purposes only and does not necessarily include all content and operations / steps, nor does it necessarily have to be performed in the order described. For example, some operations / steps can be broken down, combined, or partially merged, so the actual execution order may change depending on the actual situation.
[0029] It should 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 scope of the application. 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.
[0030] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
[0031] A hemoperfusion device is a blood purification medical device. During treatment, blood is drawn from the body through extracorporeal circulation tubing, flows through the hemoperfusion device, is purified by an adsorbent inside, and then returned to the body. The performance of the hemoperfusion device has a crucial impact on the safety of hemoperfusion treatment; therefore, its testing is extremely important.
[0032] Traditional techniques typically involve monitoring blood perfusion parameters during hemoperfusion therapy to determine if the hemoperfusion device itself is malfunctioning. This method, which detects malfunctions during treatment, is a post-factory inspection and cannot prevent future problems, easily posing treatment risks to patients. The safest approach is to perform testing during the hemoperfusion device's manufacturing process. While traditional techniques also detect problems or defects during manufacturing, these methods, such as microwave, ultrasound, X-ray, and CT scans, are costly and cannot eliminate interference from internal fluids (like water) or resin within the hemoperfusion device, potentially leading to false positives.
[0033] To address the aforementioned issues, embodiments of this application provide a method, apparatus, device, and storage medium for quality inspection of irrigation devices, thereby improving the accuracy of irrigation device quality inspection.
[0034] Please see Figure 1 , Figure 1 This is a schematic flowchart of a quality inspection method for an irrigation device provided in one embodiment of this application. This method can be applied to a quality inspection device for irrigation devices or to quality inspection equipment; the application scenario of this method is not limited in this application.
[0035] like Figure 1 As shown, the quality inspection method for the irrigation device specifically includes steps S101 to S104.
[0036] S101. Obtain an image of the inside of the perfusion device.
[0037] The perfusion device includes, but is not limited to, a blood perfusion device, and is not specifically limited to in this application. For example, an image of the inside of the perfusion device can be obtained by taking a picture using an imaging device (such as a camera, webcam, etc.). During the imaging process, attention should be paid to the clarity of the image to avoid image ghosting, as image ghosting can cause visual misjudgment as a defect in the perfusion device, ultimately leading to false diagnosis.
[0038] For example, multiple images of the inside of the irrigation device can be captured by an imaging device, and the irrigation device can be inspected based on these multiple images, which can improve the accuracy of the quality inspection.
[0039] In some embodiments, as Figure 2 As shown, step S101 may include sub-step S1011 and sub-step S1012.
[0040] S1011. Obtain a first image of the perfusion device in its initial state;
[0041] S1012. Control the rotation of the irrigation device and acquire a second image of the irrigation device when the rotation is completed.
[0042] For example, the static state of the irrigation device at the start of quality inspection is taken as the initial state. An image of the irrigation device in the initial state is first captured by an imaging device. For ease of distinction and description, it will be referred to as the first image below.
[0043] After obtaining the first image, the perfusion device is controlled to rotate. During the rotation, centrifugal force causes debris, impurities, and other foreign objects carried in the resin to be thrown from the central area of the tank to the outer edge near the inner wall of the tank. After the perfusion device finishes rotating, an image of the perfusion device at the end of its rotation is captured by an imaging device. For ease of distinction and description, this image will be referred to as the second image below.
[0044] For example, an image of the interior of an irrigation device is acquired using a visual inspection device (hereinafter referred to as the inspection device). The inspection device includes at least a motion component, an emergency braking component, and a visual inspection component, wherein:
[0045] The motion component, possessing radial and axial rotational degrees of freedom, fixes the irrigation device to the motion component. The irrigation device can rotate at high speed in the axial direction and oscillate at low amplitude and high frequency in the radial direction.
[0046] The emergency braking assembly can bring the high-speed rotating irrigation device to an emergency stop and ensure that the irrigation device stops exactly in its initial position when it stops.
[0047] The visual inspection component includes multiple cameras positioned around the perfusion apparatus, for example, at least one camera each in the front, back, top, bottom, left, and right directions. For instance, the cameras are preferably high-speed color cameras with a resolution of 20 megapixels or higher, a frame rate of 120fps or higher, and a focal length capable of covering the visible area of the perfusion apparatus column. For example, such as... Figure 3 As shown, a high-speed color camera is installed at each of the four positions: left, right, top, and bottom of the irrigation device.
[0048] For example, acquiring the first image of the perfusion device in its initial state includes: obtaining the first image by capturing it using the visual detection component;
[0049] The step of controlling the rotation of the irrigation device and acquiring a second image of the irrigation device at the end of rotation includes: controlling the irrigation device to rotate axially via the motion component; controlling the irrigation device to stop rotating and stop at the initial position before rotation via the emergency braking component; and acquiring the second image via the visual detection component.
[0050] The process of acquiring images of the inside of the irrigation device using a detection device is as follows:
[0051] 1) Start the camera of the visual inspection component to take a picture and obtain the first image.
[0052] 2) The perfusion device is controlled to oscillate radially by a motion component, for example, such as... Figure 4 As shown, the irrigation device is controlled to tilt and swing up and down in a low-amplitude (e.g., 10-30 degrees on one side) and high-frequency (e.g., 300 back and forth times per minute) radial direction, with the movement duration controlled within a certain period (e.g., 2-3 seconds). The purpose is to shake the resin at both ends of the irrigation device to the middle area of the irrigation device.
[0053] 3) The perfusion device is controlled to rotate at high speed around its central axis via a motion component (e.g., a rotation speed greater than or equal to 3500 rpm, preferably within the range of 3500-5000 rpm). For example, such as... Figure 5 As shown, the perfusion device is controlled to rotate at high speed in the same direction (e.g., clockwise) for a certain duration (e.g., 2-5 seconds). The purpose is to use centrifugal force to throw the fragments, impurities and other foreign objects carried in the resin from the central area of the tank to the outer edge near the inner wall of the tank.
[0054] 4) Release the emergency brake assembly to stop the rotation of the perfusion device and control it to stop in the initial position. The purpose is to maintain the consistency of the perfusion device position before and after rotation, so as to facilitate subsequent image comparison.
[0055] 5) Activate the camera of the vision inspection component to capture a second image. After the perfusion unit finishes rotating and the resin settles, the liquid (clarified liquid) and resin area inside the perfusion unit are as follows: Figure 6 As shown, the camera can capture foreign objects in the liquid and those adhering to the surface of the resin area. For example, the camera captures images at intervals less than or equal to a certain duration (e.g., 250 milliseconds, preferably 50-250 milliseconds), and the capture duration is within a certain range (e.g., 3-5 seconds). Special attention must be paid to image sharpness during the capture process to avoid motion blur, as motion blur can cause visual misjudgment as a defect, ultimately leading to false detection.
[0056] By using a detection device to acquire images of the inside of the perfusion apparatus, the stability of the detection quality level can be ensured.
[0057] S102. Preprocess the image.
[0058] For example, after obtaining the first image and the second image, the first image and the second image are preprocessed. The preprocessing includes, but is not limited to, identifying the regions where features are to be extracted and recording their numbers, cutting out each region to generate independent slice images, and performing image correction on each slice image.
[0059] In some embodiments, such as Figure 7As shown, step S102 includes sub-steps S1021 to S1023.
[0060] S1021. Compare the first image with the second image to determine at least one target region where there is a difference;
[0061] S1022. Cut out each target region to generate a slice image;
[0062] S1023. Perform image correction processing on each of the slice images.
[0063] By comparing the first and second images, the regions corresponding to the differences in the state before and after the irrigation device are identified and designated as target regions. Each target region is assigned a number Q according to its corresponding physical coordinates (e.g., XY axis coordinates). xy Each target area is cut out to generate an independent slice image, for example, slice images with dimensions of 10*10, 20*20, or 50*50 pixels. Each slice image is numbered with coordinate Q. xy Name the image and store relevant information such as the shooting time, camera position, and perfusion device number in the detailed information section.
[0064] Next, image correction processing is performed on each slice to restore the true state. The correction processing includes at least one or more of the following: exposure correction, to eliminate non-uniform brightness or darkness variations in the image, which are generally caused by uneven lighting, camera optical system or sensor characteristics; geometric correction, to eliminate distortion problems such as compression, stretching, twisting and offset in the image; and color correction, to eliminate color cast, color difference or color balance problems in the image.
[0065] S103. Extract features from the preprocessed image.
[0066] For example, feature extraction is performed on each slice image after image correction processing. The extracted features include, but are not limited to, features such as color, roundness, and diameter.
[0067] In some embodiments, as Figure 8 The step S103 may include sub-steps S1031 and S1032.
[0068] S1031. Based on the preprocessed image, extract the target contour;
[0069] S1032. Identify features of the target contour, the features including at least one of color, roundness, and diameter.
[0070] For example, the target contour can be extracted from each slice image, such as by using an edge detection algorithm or a contour detection algorithm to obtain a set of contour points, and then determining the corresponding target contour based on the obtained set of contour points.
[0071] Then, the features of each target contour are identified separately and in parallel, such as the color, roundness, and diameter of the target contour.
[0072] To determine the color of the target contour, the RGB (Red, Green, Blue) color standard can be used to define the color parameters in the image. RGB is a color model that represents color as a mixture of three basic components: Red (R), Green (G), and Blue (B). This model uses three numbers (typically between 0 and 255) to describe the color, each representing a different intensity of the three basic colors that determine the final color. By reading the RGB value of each pixel in the slice image, the color of the target contour can be determined.
[0073] To determine the circularity of the target contour, the slice image is binarized to obtain a black and white image. The area of the target contour is calculated by counting the pixels enclosed by the contour, and the perimeter is calculated by counting the number of pixels on the contour. Then, based on the area and perimeter, the circularity of the target contour is calculated. The closer the circularity of the target contour is to 1, the closer the target contour is to a circle.
[0074] For example, the roundness of the target contour can be calculated using the following formula (1):
[0075] e=(4π*s) / (c*c) (1)
[0076] Where e represents the circularity of the target contour, s represents the area of the target contour, and c represents the perimeter of the target contour.
[0077] The diameter of the target contour can be calculated using the following formula (2):
[0078] d=c / π (2)
[0079] Where d represents the diameter of the target contour and c represents the perimeter of the target contour.
[0080] S104. Compare the extracted features with the standard features to obtain the quality inspection results of the irrigation device.
[0081] For example, a standard feature database is established, which includes standard features corresponding to various different objects. These standard features serve as criteria for determining the type of target object. For instance, by performing feature recognition on a large number of resin images, the standard features corresponding to resin are summarized as follows: the color is brown, the roundness is in the range of 0.7-1, and the diameter is in the range of 0.3-2 mm. These standard features serve as the criteria for determining whether the target object is resin.
[0082] By comparing the extracted features with standard features in a standard feature database, the quality inspection results of the irrigation device are obtained. The quality inspection results include, but are not limited to, whether the irrigation device has defects or not.
[0083] In some embodiments, such as Figure 9 The step S104 may include sub-steps S1041 and S1042.
[0084] S1041. Compare the extracted features with the standard features to determine the target object type corresponding to the extracted features;
[0085] S1042. Based on the target object type, obtain the quality inspection result.
[0086] After obtaining the extracted features, they are compared with standard features in a standard feature database to determine the target object type corresponding to the extracted features. For example, the extracted features are compared with the standard features corresponding to resin in the standard feature database, such as... Figure 10 As shown, determine whether the extracted roundness feature is within the range of 0.7-1; if it is not within the range of 0.7-1, it is marked as a defect; if it is within the range of 0.7-1, continue to determine whether the extracted color feature is brown; if it is not brown, it is marked as an air bubble, that is, the target object type is determined to be an air bubble; if it is brown, continue to determine whether the extracted diameter feature is within the range of 0.3-2 mm; if it is not within the range of 0.3-2 mm, it is marked as a defect; if it is within the range of 0.3-2 mm, it is marked as resin, that is, the target object type is determined to be resin.
[0087] For example, features identified during quality inspection can be automatically incorporated into a standard feature database, with continuous iteration and updates to the evaluation criteria. For instance, if inspection reveals that some resins are black, the evaluation criteria for the resin can be automatically revised based on the inspection results, changing the color feature in the corresponding standard features from brown to either brown or black. The evaluation criteria for roundness and diameter will also be continuously iterated and optimized using the same methods, thereby continuously improving inspection accuracy and meeting the ever-increasing quality requirements for irrigation devices.
[0088] In some embodiments, after comparing the extracted features with standard features to obtain the quality inspection result of the irrigation device, the process includes: uploading the quality inspection result and the image inside the irrigation device to a server, and generating a unique identifier corresponding to the irrigation device.
[0089] After quality inspection, the inspection results and corresponding images are uploaded to the server, and a unique identifier is assigned to the outer surface of each irrigation device through printing, pasting, or laser marking. This unique identifier includes, but is not limited to, QR codes and strings. The unique identifier is linked to the irrigation device's production information, which includes, but is not limited to, product brand, series, production address, production line, production batch, and production date. Furthermore, the unique identifier stores the irrigation device's quality inspection results (whether there are defects) and defect images. Scanning the code immediately retrieves this information, facilitating quality tracking and processing, and providing basic data for quality improvement in the production process. Moreover, it meets the requirements of continuous automated production of irrigation devices and allows for adjustment of inspection accuracy according to the quality standards of the irrigation device itself.
[0090] In the above embodiments, by acquiring an image of the inside of the irrigation device, preprocessing the image, extracting features from the preprocessed image, and comparing the extracted features with standard features, the quality inspection results of the irrigation device are obtained, thereby improving the accuracy of the irrigation device quality inspection.
[0091] Please see Figure 11 , Figure 11 This is a schematic block diagram of a quality inspection device for an irrigation device provided in an embodiment of this application. The quality inspection device for the irrigation device can be configured in a quality inspection equipment to perform the aforementioned quality inspection method for the irrigation device.
[0092] like Figure 11 As shown, the quality inspection device 200 of the irrigation device may include a processor 210 and a memory 220, wherein the processor 210 and the memory 220 are connected by a bus, such as an I2C (Inter-integrated Circuit) bus.
[0093] Specifically, the processor 210 can be a microcontroller unit (MCU), a central processing unit (CPU), or a digital signal processor (DSP), etc.
[0094] Specifically, the memory 220 can be a Flash chip, a read-only memory (ROM) disk, an optical disk, a USB flash drive, or a portable hard drive, etc. The memory 220 stores various computer programs for the processor 210 to execute.
[0095] The processor 210 is configured to run a computer program stored in the memory, and to perform the following steps when executing the computer program:
[0096] Acquire images of the inside of the perfusion apparatus;
[0097] The image is preprocessed;
[0098] Feature extraction is performed on the preprocessed image;
[0099] The extracted features are compared with standard features to obtain the quality inspection results of the irrigation device.
[0100] In some embodiments, when implementing the acquisition of images inside the perfusion apparatus, the processor 210 is configured to:
[0101] Acquire a first image of the perfusion device in its initial state;
[0102] The irrigation device is controlled to rotate, and a second image of the irrigation device at the end of its rotation is acquired.
[0103] In some embodiments, when performing the preprocessing of the image, the processor 210 is configured to:
[0104] By comparing the first image with the second image, at least one target region with differences is identified;
[0105] Each target region is cut out to generate a slice image;
[0106] Image correction processing is performed on each of the slice images.
[0107] In some embodiments, the perfusion device is fixed to a motion component of a detection device, the detection device further comprising an emergency braking component and a visual detection component. When the processor 210 implements the control of the perfusion device's rotation and acquires a second image of the perfusion device at the end of its rotation, it is configured to:
[0108] The perfusion device is controlled to rotate axially by the motion component;
[0109] The emergency braking assembly controls the perfusion device to stop rotating and remain at its initial position before rotation.
[0110] The second image is obtained by capturing images using the visual detection component.
[0111] In some embodiments, when performing feature extraction on the preprocessed image, the processor 210 is configured to:
[0112] Based on the preprocessed image, target contour extraction is performed;
[0113] Identify features of the target contour, the features including at least one of color, roundness, and diameter.
[0114] In some embodiments, when the processor 210 compares the extracted features with standard features to obtain the quality inspection result of the perfusion device, it is configured to:
[0115] The extracted features are compared with the standard features to determine the target object type corresponding to the extracted features;
[0116] The quality inspection results are obtained based on the type of the target object.
[0117] In some embodiments, after the processor 210 compares the extracted features with standard features to obtain the quality inspection result of the perfusion device, it is configured to:
[0118] The quality inspection results and the image inside the irrigation device are uploaded to the server, and a unique identifier corresponding to the irrigation device is generated.
[0119] The quality inspection device 200 for the irrigation device can perform the quality inspection method for the irrigation device provided in the embodiments of this application. Therefore, it can achieve the beneficial effects that the quality inspection method for the irrigation device provided in the embodiments of this application can achieve. For details, please refer to the previous embodiments, which will not be repeated here.
[0120] This application also provides a quality inspection device in its embodiments, which includes a quality inspection apparatus for an irrigation device. This quality inspection apparatus for the irrigation device can be... Figure 11 The quality inspection device 200 for the irrigation device shown is illustrated. Therefore, the quality inspection equipment can achieve the beneficial effects of the irrigation device quality inspection method provided in the embodiments of this application, as detailed in the preceding embodiments, and will not be repeated here.
[0121] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the perfusion device quality inspection method described above.
[0122] The computer-readable storage medium can be an internal storage unit of the quality inspection device or equipment of the irrigation device described in the foregoing embodiments, such as the hard disk or memory of the quality inspection device or equipment of the irrigation device. The computer-readable storage medium can also be an external storage device of the quality inspection device or equipment of the irrigation device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD card), flash card, etc., equipped on the quality inspection device or equipment of the irrigation device.
[0123] Since the computer program stored in the storage medium can execute any of the quality inspection methods for the irrigation device provided in the embodiments of this application, the beneficial effects that the quality inspection methods for the irrigation device provided in the embodiments of this application can achieve can be realized. For details, please refer to the previous embodiments, which will not be repeated here.
[0124] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.
[0125] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the scope of the technology disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application.
Claims
1. A quality inspection method for an irrigation device, characterized in that, The quality inspection method for the irrigation device includes: Acquire images of the inside of the perfusion apparatus; The image is preprocessed; Feature extraction is performed on the preprocessed image; The extracted features are compared with standard features to obtain the quality inspection results of the irrigation device.
2. The quality inspection method for the irrigation device as described in claim 1, characterized in that, The acquisition of images inside the perfusion device includes: Acquire a first image of the perfusion device in its initial state; The irrigation device is controlled to rotate, and a second image of the irrigation device at the end of its rotation is acquired.
3. The quality inspection method for the irrigation device as described in claim 2, characterized in that, The preprocessing of the image includes: By comparing the first image with the second image, at least one target region with differences is identified; Each target region is cut out to generate a slice image; Image correction processing is performed on each of the slice images.
4. The quality inspection method for the irrigation device as described in claim 2, characterized in that, The irrigation device is fixed to the motion component of the detection device, which also includes an emergency braking component and a visual detection component. Controlling the rotation of the irrigation device and acquiring a second image of the irrigation device at the end of its rotation includes: The perfusion device is controlled to rotate axially by the motion component; The emergency braking assembly controls the perfusion device to stop rotating and remain at its initial position before rotation. The second image is obtained by capturing images using the visual detection component.
5. The quality inspection method for the irrigation device as described in claim 1, characterized in that, The feature extraction of the preprocessed image includes: Based on the preprocessed image, target contour extraction is performed; Identify features of the target contour, the features including at least one of color, roundness, and diameter.
6. The quality inspection method for the irrigation device as described in claim 1, characterized in that, The step of comparing the extracted features with standard features to obtain the quality inspection result of the irrigation device includes: The extracted features are compared with the standard features to determine the target object type corresponding to the extracted features; The quality inspection results are obtained based on the type of the target object.
7. The quality inspection method for the irrigation device as described in any one of claims 1 to 6, characterized in that, After comparing the extracted features with standard features to obtain the quality inspection results of the irrigation device, the process includes: The quality inspection results and the image inside the irrigation device are uploaded to the server, and a unique identifier corresponding to the irrigation device is generated.
8. A quality inspection device for an irrigation device, characterized in that, The quality control device for the irrigation device includes a memory and a processor; The memory is used to store computer programs; The processor is configured to execute the computer program and, in executing the computer program, implement the steps of the perfusion device quality inspection method as described in any one of claims 1 to 7.
9. A quality inspection device, characterized in that, The quality inspection equipment includes the quality inspection device for the irrigation device as described in claim 8.
10. 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 steps of the perfusion device quality inspection method as described in any one of claims 1 to 7.