A machine vision-based defect detection method, device and electronic equipment

Abstract

This application provides a defect detection method, apparatus, and electronic device based on machine vision. In this embodiment, defect detection of the demolded gloves is performed using first and second glove images acquired by an image acquisition device. This achieves automatic inspection of glove production quality through machine vision, improving inspection efficiency. Simultaneously, whenever the sensing component detects a hand mold, it sends a sensing signal to the first and second image acquisition devices for image acquisition, avoiding missed detections. Defect detection of the demolded gloves is achieved based on glove images acquired from different directions, realizing comprehensive defect detection. By associating the defect detection results of the demolded gloves with the grippers set on the demolding machine, early warnings are issued for the grippers based on the associated defect detection results, preventing batch glove quality problems caused by gripper malfunctions.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to a defect detection method, apparatus and electronic device based on machine vision. Background Technology

[0002] In product manufacturing applications, taking glove production as an example, after the gloves are formed, they are processed in various processes along the assembly line on a hand mold, and finally the finished product is removed.

[0003] Currently, in order to ensure the production quality of gloves, defects (such as oil stains, damage, etc.) are often checked manually by visual inspection. This manual inspection method is time-consuming and labor-intensive, and it is also common to miss some defects. Summary of the Invention

[0004] In view of this, embodiments of this application provide a defect detection method, apparatus, and electronic device based on machine vision, so as to realize automatic detection of glove production quality through machine vision, improve detection efficiency, and avoid missed detection.

[0005] According to a first aspect of the embodiments of this application, a defect detection method based on machine vision is provided, the method comprising:

[0006] During the transfer of the hand mold and the release glove, when the deployed sensing components detect the hand mold, they send sensing signals to the deployed first image acquisition device and the deployed second image acquisition device, respectively. The release glove refers to a glove that is not fully fitted onto the hand mold.

[0007] When the first image acquisition device receives the sensing signal, it acquires a first glove image of the demolding glove; when the second image acquisition device receives the sensing signal, it acquires a second glove image of the demolding glove; the first image acquisition device and the second image acquisition device are deployed in different positions; the first glove image is an end face image of the demolding glove, which is obtained by the first image acquisition device being deployed on the demolding glove and capturing the front of the glove as the fingers point; the second glove image is a surface image of the demolding glove, which is an image captured by the second image acquisition device of the surface of the demolding glove.

[0008] After receiving the first glove image and the second glove image, the industrial control computer performs defect detection on the demolding glove based on machine vision and in combination with the first glove image and the second glove image. The result of the defect detection on the demolding glove is associated with the gripper set on the demolding machine, so as to give a warning to the gripper based on the defect detection results associated with the gripper. The demolding machine is currently used to fix the wrist of the demolding glove.

[0009] According to a second aspect of the embodiments of this application, a defect detection device based on machine vision is provided, the device comprising:

[0010] The sensing module is used to send sensing signals to the first image acquisition device and the second image acquisition device respectively when the deployed sensing component detects the hand mold during the transfer of the hand mold and the demolding glove. The demolding glove refers to a glove that is not completely covered by the hand mold.

[0011] An image acquisition module is used for the first image acquisition device to acquire a first glove image of the demolding glove when it receives the sensing signal; and for the second image acquisition device to acquire a second glove image of the demolding glove when it receives the sensing signal. The first image acquisition device and the second image acquisition device are deployed in different locations. The first glove image is an end face image of the demolding glove, obtained by the first image acquisition device being deployed on the demolding glove and capturing the image from the front of the fingers pointing to it. The second glove image is a surface image of the demolding glove, captured by the second image acquisition device on the surface of the demolding glove.

[0012] The defect detection module is used by the industrial control computer to perform defect detection on the demolding glove based on machine vision and in combination with the first glove image and the second glove image after receiving the first glove image and the second glove image. The defect detection result of the demolding glove is associated with the gripper set on the demolding machine, so as to give a warning to the gripper based on the defect detection results associated with the gripper. The demolding machine is currently used to fix the wrist of the demolding glove.

[0013] According to a third aspect of the embodiments of this application, an electronic device is provided, the electronic device comprising: a processor and a memory; wherein, the memory is configured to store machine-executable instructions; and the processor is configured to read and execute the machine-executable instructions stored in the memory to implement the method as described in the first aspect.

[0014] The technical solutions provided in this application embodiment may have the following beneficial effects:

[0015] As can be seen from the above technical solutions, in this embodiment of the application, the first glove image and the second glove image acquired by the image acquisition device are used to detect defects in the demolded glove, thereby realizing automatic detection of glove production quality through machine vision, improving detection efficiency. At the same time, whenever the sensing component detects a hand mold, it sends a sensing signal to the first image acquisition device and the second image acquisition device to realize image acquisition of the target hand mold, avoiding missed detection.

[0016] Furthermore, by using a first image acquisition device and a second image acquisition device to acquire images of the demolding glove from different directions, and by using the glove images acquired from different directions to perform defect detection on the demolding glove, comprehensive defect detection of the demolding glove is achieved.

[0017] Furthermore, by correlating the defect detection results of the demolded gloves with the grippers set on the demolding machine, the grippers can be given an early warning based on the defect detection results associated with each gripper, thus avoiding batch glove quality problems caused by gripper failure. Attached Figure Description

[0018] Figure 1 This is a network example diagram of the defect detection system provided in the application embodiment.

[0019] Figure 2 This is a flowchart of the method provided in the embodiments of this application.

[0020] Figure 3 This is an example image of the second glove provided in an embodiment of this application.

[0021] Figure 4 This is an example image of the first glove provided in an embodiment of this application.

[0022] Figure 5 This is an example diagram of the first defect detection result provided in the embodiments of this application.

[0023] Figure 6 This is an example diagram showing the distance from a designated position of a finger to the demolding machine, provided in an embodiment of this application.

[0024] Figure 7 This is a block diagram of the apparatus provided in the embodiments of this application.

[0025] Figure 8 This is a block diagram of the electronic device provided in the embodiments of this application. Detailed Implementation

[0026] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0027] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0028] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0029] The embodiments described in this specification will now be described in detail.

[0030] like Figure 1 As shown, Figure 1 This is a network example diagram of a defect detection system according to an embodiment of this application. In this embodiment, the defect detection system includes at least: an image acquisition device, a light source disposed around the image acquisition device, and a transmission device (…). Figure 1 Taking a transmission device as an example (like a sliding track), sensing components, and an industrial control computer, etc., wherein the sensing components and the industrial control computer are... Figure 1 Not shown in the image.

[0031] The image acquisition device mentioned above can be an industrial camera or a regular camera; this application embodiment does not specifically limit it.

[0032] In this embodiment, the number of the above-mentioned image acquisition devices can be set to one. Of course, in order to perform defect detection on the release gloves in all directions, the number of the above-mentioned image acquisition devices can also be set to multiple. This embodiment of the application does not specifically limit the number of devices.

[0033] Here, when the number of image acquisition devices is greater than one, each image acquisition device has a different shooting direction for the demolding glove. For example, when there are two image acquisition devices (hereinafter referred to as the first image acquisition device and the second image acquisition device), the first image acquisition device acquires the end face image of the demolding glove. The end face image is obtained by the first image acquisition device being deployed on the demolding glove in front of the fingers pointing to it. The second image acquisition device acquires the surface image of the demolding glove. The surface image is obtained by the second image acquisition device from the palm direction or the back of the hand direction of the demolding glove. Here, the second image acquisition device is deployed at a position perpendicular to the palm direction of the demolding glove, or at a position at a certain angle (e.g., 50°) to the palm direction of the demolding glove. This application embodiment is not specifically limited, as long as it is ensured that the second image acquisition device can acquire the surface image of the demolding glove.

[0034] When there are three image acquisition devices (e.g., one first image acquisition device and two second image acquisition devices), the first image acquisition device acquires an end face image of the demolding glove. This end face image is obtained by positioning the first image acquisition device on the demolding glove in front of the fingers. The second image acquisition devices acquire surface images of the demolding glove. These surface images are acquired by the second image acquisition devices from both the palm and back of the hand directions. Specifically, one second image acquisition device acquires the image from the palm direction, and the other acquires it from the back of the hand direction. Here, the second image acquisition devices are positioned perpendicular to the palm direction of the demolding glove, or at a certain angle (e.g., 50°) to the palm direction. This embodiment of the application does not specifically limit the position, as long as it ensures that the second image acquisition device can acquire the surface image of the demolding glove.

[0035] For example, when the number of image acquisition devices is 2, such as Figure 1 As shown, one of the image acquisition devices acquires images from the back of the release glove. Figure 1 Image acquisition can be performed either from the top camera in the middle or from the palm of the demolding glove. Figure 1 The bottom camera is located in the center, and another image acquisition device is set on the end face of the release glove. Figure 1 The end-face camera in the middle acquires images from the end face.

[0036] For example, when the number of image acquisition devices is 3, such as Figure 1 As shown, an image acquisition device acquires images from the back of the release glove. Figure 1 The top camera in the middle, an image acquisition device acquires images from the palm direction of the release glove. Figure 1The bottom camera in the middle, an image acquisition device is set on the end face of the release glove ( Figure 1 The end-face camera in the middle acquires images from the end face.

[0037] In this embodiment, the light source can be a surface light source. The light source can be kept on all the time, or it can be turned on when the corresponding image acquisition device takes a picture. This embodiment of the application is not limited to this.

[0038] For example, in this embodiment, the transmission device can be a sliding track, a conveyor belt, etc., and this application embodiment is not specifically limited to this. This application embodiment only uses the transmission device as an example. Figure 1 The sliding track shown is used as an example for description.

[0039] In this embodiment, during the defect detection process of the demolded gloves, each hand mold is transferred on a sliding track. A sensing component is provided on the sliding track. When the sensing component senses that a hand mold has been transferred, it sends a sensing signal to the industrial control computer or image acquisition device. Here, the sensing component can be a sensor switch.

[0040] based on Figure 1 The network topology shown below will be used in conjunction with the network topology described below. Figure 2 The method provided in the embodiments of this application is described as follows:

[0041] See Figure 2 , Figure 2 This is a flowchart illustrating a method provided in an embodiment of this application. The method is applied to the aforementioned industrial control computer, such as... Figure 2 As shown, the process may include the following steps:

[0042] S210: During the transfer of the hand mold and the demolding glove, when the deployed sensing component detects the hand mold, it sends sensing signals to the deployed first image acquisition device and the deployed second image acquisition device, respectively.

[0043] For example, in this embodiment, the sensing component is deployed on a sliding track, and the sensing signal is triggered when the hand mold is transmitted to the sensing component on the sliding track. When the hand mold is transmitted to the sensing component, the sensing component is triggered to send a sensing signal.

[0044] As another embodiment of this application, during the transmission of the hand mold and the demolding glove, when the hand mold is transmitted to the sensing component, the sensing component can send the sensing signal to the industrial control computer, which then divides the sensing signal into two sets of point signals and sends them to the first image acquisition device and the second image acquisition device respectively, triggering the first image acquisition device and the second image acquisition device to simultaneously acquire images of the demolding glove.

[0045] In this embodiment, a release glove refers to a glove that is not fully fitted onto the hand mold, such as... Figure 3As shown, after the glove demolding process is completed, there is an overlap between the demolded glove and the hand mold.

[0046] S220: When the first image acquisition device receives the sensing signal, it acquires an image of the first glove for the demolding glove; when the second image acquisition device receives the sensing signal, it acquires an image of the second glove for the demolding glove.

[0047] For example, in this embodiment, the first image acquisition device and the second image acquisition device are deployed in different locations. The first glove image is an end face image of the demolding glove, which is obtained by the first image acquisition device being deployed on the demolding glove in front of the fingers pointing. The second glove image is a surface image of the demolding glove, which is an image acquired by the second image acquisition device for the surface of the demolding glove. Here, the surface of the demolding glove can be the surface where the palm of the demolding glove is located, or it can be the surface where the back of the demolding glove is located. This embodiment of the application does not specifically limit the scope.

[0048] For example, in this embodiment, during the transmission of the hand mold and the demolded glove, when the first image acquisition device and the second image acquisition device receive the sensing signal sent by the sensing component, the first image acquisition device and the second image acquisition device simultaneously acquire images of the demolded glove to obtain the first glove image and the second glove image.

[0049] Here, both the first glove image and the second glove image can be RGB images or black and white images; this application embodiment does not specifically limit them.

[0050] For example, such as Figure 3 As shown, Figure 3 An example image of a second glove, such as Figure 4 As shown, Figure 4 This is an example image of the first glove.

[0051] S230: After receiving the first glove image and the second glove image, the industrial control computer performs defect detection on the demolding glove based on machine vision and in combination with the first glove image and the second glove image. The result of the defect detection on the demolding glove is associated with the gripper set on the demolding machine. The gripper is given a warning based on the defect detection results associated with the gripper. The demolding machine is currently used to fix the wrist of the demolding glove.

[0052] For example, in this embodiment, after the industrial control computer receives the first glove image and the second glove image, in this step S230, there are many methods for performing defect detection on the demolded glove based on machine vision and combining the first glove image and the second glove image. For example, defect detection on the demolded glove based on a neural network model, defect detection on the demolded glove based on conventional machine vision methods, etc. This application embodiment does not specifically limit the methods.

[0053] The following describes defect detection for release gloves based on a neural network model:

[0054] As an optional implementation of this application, step S230 above, which involves defect detection of the demolded glove on the hand mold based on machine vision and in combination with the first glove image and the second glove image, includes:

[0055] First, the pre-trained detection model is used to identify the first defect detection result of the demolded glove from the first glove image, and the detection model is used to identify the second defect detection result of the demolded glove from the second glove image.

[0056] For example, in this embodiment, the detection model is pre-trained. The training process of the detection model is described below. Specifically, the process may include:

[0057] (1) Building a network model

[0058] Specifically, in the embodiments of this application, the detection model is mainly used for feature extraction and classification. Its model structure is similar to that of the model structure used for feature extraction and classification in related technologies, and will not be described in detail here.

[0059] (2) Obtain training samples

[0060] Based on the above detection model, glove image samples containing various defects can be obtained. Then, the types of defects in the obtained glove image samples can be manually labeled and tagged.

[0061] (3) Train the network model using the obtained training samples to obtain the trained detection model.

[0062] Specifically, the network parameters in the network model can be set to specified values ​​first, and then the network model can be trained using training samples with manually labeled defect types to obtain a trained detection model.

[0063] Specifically, the process can include two stages: forward propagation and backward propagation. Forward propagation involves inputting a training sample, performing forward propagation on the training sample to extract data features, and calculating the loss function. Backward propagation uses the loss function to propagate backward from the last layer of the network model, while simultaneously using gradient descent to modify the network parameters of the network model so that the loss function converges, resulting in a trained detection model.

[0064] In this embodiment, after obtaining the above-mentioned detection model, the collected first glove image and second glove image are respectively input into the detection model, and the detection model processes the first glove image and second glove image respectively, and outputs the first defect detection result and the second defect detection result.

[0065] Figure 5 This is a specific example of the first or second defect detection result; the white part indicated by the arrow is the detected defect.

[0066] Secondly, based on the results of the first and second defect detections, the defect detection results of the release gloves are determined.

[0067] For example, in this embodiment, the first defect detection result may include: oil stains, damage, scratches, etc., and this embodiment of the application is not specifically limited.

[0068] In this embodiment, the second trap detection result may also include: oil stains, damage, scratches, etc., and this embodiment of the application is not specifically limited.

[0069] For example, in this embodiment, there are many ways to determine the defect detection result of the release glove based on the first defect detection result and the second defect detection result, and this embodiment of the application is not specifically limited.

[0070] As one implementation method, the defect detection result of the demolding glove can be determined based on the first defect detection result and the second defect detection result by taking the union of the first defect detection result and the second defect detection result as the defect detection result of the demolding glove.

[0071] As another implementation, in order to meet the needs of different users, only a certain defect can be focused on, for example, only the damaged gloves. Based on this, the defect detection result of the demolding gloves can be determined according to the first defect detection result and the second defect detection result: the set of the specified defects in the first defect detection result and the second defect detection result can be taken as the defect detection result of the demolding gloves. Here, the specified defect can be, for example, damage. This application embodiment does not specifically limit the specified defect.

[0072] This application embodiment uses a neural network model to perform defect detection on images of the first glove and the second glove, achieving end-to-end defect detection and improving defect detection efficiency.

[0073] For example, in this embodiment, there are many ways to issue a warning to the gripper based on the defect detection results associated with the gripper. For example, a warning can be issued by text information (e.g., displayed on the monitor of an industrial control computer) or by sound information. This application embodiment is not specifically limited to these methods.

[0074] In this embodiment, the specific method for issuing an early warning for the gripper based on the detection results of each defect associated with the gripper can be found in the example description of the following embodiment, which will not be repeated here.

[0075] This concludes the process. Figure 2 The process is shown below.

[0076] pass Figure 2 As can be seen from the process, in this embodiment of the application, the first glove image and the second glove image acquired by the image acquisition device are used to detect defects in the demolded gloves, thereby realizing automatic detection of glove production quality through machine vision, improving detection efficiency. At the same time, since the first image acquisition device and the second image acquisition device only need to acquire the glove image when they receive the sensing signal sent by the sensing component, and then perform defect detection on the demolded gloves based on the acquired glove image, the situation of missed detection is avoided.

[0077] Furthermore, by using a first image acquisition device and a second image acquisition device to acquire images of the demolding glove from different directions, and by using the glove images acquired from different directions to perform defect detection on the demolding glove, comprehensive defect detection of the demolding glove is achieved.

[0078] Furthermore, by correlating the defect detection results of the demolded gloves with the grippers set on the demolding machine, the grippers can be given an early warning based on the defect detection results associated with each gripper, thus avoiding batch glove quality problems caused by gripper failure.

[0079] As an optional implementation of this application, when the result of defect detection of the release gloves meets the specified early warning conditions, the machine vision-based defect detection method further includes:

[0080] The first warning message is issued to indicate that the release gloves are substandard.

[0081] For example, in this embodiment, there can be many types of specified warning conditions, and this application embodiment does not specifically limit them.

[0082] As an example, the specified warning condition can be that the number of defects in the result of defect detection of the release glove is greater than or equal to a specified number (e.g., 3).

[0083] As another embodiment, the specified warning condition can also be that the number of each type of defect in the result of defect detection of the release glove is greater than or equal to its corresponding specified number, for example, the number of oil stains is greater than 2, the number of damages is greater than 1, etc.

[0084] In this embodiment, the first warning information can be a text warning information displayed on a display screen, where the display screen is the display screen of the industrial control computer operated by the operator. The first warning information can also be an audio warning information, so that the operator can promptly detect the problematic gloves and handle them in a timely manner. This application embodiment does not specifically limit the first warning information, and it can be determined according to the actual situation.

[0085] As an optional implementation of this application, the machine vision-based defect detection method further includes:

[0086] First, the claw markings were identified from the second glove image.

[0087] For example, in this embodiment, the identifier of the gripper can be a numerical code of the gripper, such as... Figure 3 The "15" shown can also be the English name of the gripper, such as "A". This application embodiment does not specifically limit this.

[0088] In this embodiment, the identification of the gripper markings from the second glove image can be achieved using an OCR recognition algorithm or a code reading algorithm; however, this embodiment is not specifically limited to this method.

[0089] The OCR recognition algorithms or code reading algorithms mentioned above are all conventional recognition algorithms, and will not be elaborated on here.

[0090] Secondly, the defect detection results of the release glove are associated with the markings on the gripper. As an optional implementation of this application, the defect detection results of the release glove include at least: damage detection results, and a warning is issued for the gripper based on the defect detection results associated with it, including:

[0091] First, the damage detection results associated with the grippers are statistically analyzed at preset time intervals.

[0092] For example, in this embodiment, the preset time period can be any time period, such as 30 minutes, and this embodiment of the application is not specifically limited.

[0093] In this embodiment, the gripper will demold multiple gloves within the preset time period. Therefore, the number of damage detection results within the preset time period is obtained by counting the defect detection results of all demolded gloves associated with the gripper.

[0094] Secondly, when the statistical number of damage detection results exceeds a specified value, a second warning message is issued, which indicates a gripper malfunction.

[0095] For example, in this embodiment, the specified value can be any value, such as 10, and this embodiment of the application is not specifically limited.

[0096] In this embodiment, the second warning information can be a text warning information displayed on a display screen, which is the display screen of the industrial control computer operated by the operator. The second warning information can also be an audio warning information, so that the operator can promptly detect the problematic gloves and deal with them in a timely manner. This embodiment of the application does not specifically limit the second warning information, and it can be determined according to the actual situation.

[0097] In this embodiment of the application, when the statistical number of damage detection results exceeds a specified value, an early warning message is issued to avoid batch problems with demolding gloves due to gripper failure.

[0098] As an optional implementation of this application, the machine vision-based defect detection method further includes:

[0099] First, based on the second glove image, determine the distance from each designated position in the second glove image to the demolding machine in the second glove image; the demolding machine is currently used to fix the wrist of the demolding glove.

[0100] For example, in this embodiment, the distance from each specified position in the second glove image to the demolding machine in the second glove image can be determined by processing the second glove image using a specified machine vision algorithm. Here, the specified machine vision algorithm includes at least: Blob analysis algorithm, 2D caliper measurement algorithm, straight line measurement algorithm, etc. This application embodiment does not specifically limit the above-mentioned specified machine vision algorithm, which can be determined according to the actual situation.

[0101] For example, in this embodiment, each designated location includes at least: the position where each finger of the release glove is placed on the hand mold, such as... Figure 6 As shown, Figure 6 The left side is a hand mold. Figure 6 On the right is the demolding machine. The cylindrical area on each finger is the overlapping area between the demolding glove and that finger. The leftmost part of the cylindrical area is the position of each finger on the demolding glove on the hand mold. The distance from the designated position of each finger to the demolding machine can be the distance from the leftmost part of the cylindrical area to the center line of the demolding machine.

[0102] Secondly, when the distance from any designated position to the demolding machine does not meet the designated distance condition, a third warning message is issued, which indicates a malfunction in the clamps of the demolding machine.

[0103] For example, in this embodiment, the specified distance condition can be that the distance from a specified position of each finger to the demolding machine is less than its corresponding set distance. Of course, the specified distance condition can also be other conditions, and this embodiment of the application does not specifically limit it.

[0104] In this embodiment, a set distance is set for each finger. For example, for the thumb, the corresponding set distance can be 5cm. This embodiment of the application is not specifically limited.

[0105] This application embodiment, by measuring the dimensional stretching of the demolded gloves, can provide a certain early warning for the grippers of the demolding machine, thus avoiding batch defects.

[0106] Corresponding to the embodiments of the foregoing methods, this specification also provides embodiments of the apparatus and the terminal to which it is applied.

[0107] like Figure 7 As shown, Figure 7 This is a block diagram of a machine vision-based defect detection device provided in an embodiment of this application. The device includes:

[0108] The sensing module is used to send sensing signals to the first and second image acquisition devices respectively when the deployed sensing components detect the hand mold during the transfer of the hand mold and the release glove. The release glove refers to the glove that is not completely covered by the hand mold.

[0109] An image acquisition module is used for a first image acquisition device to acquire an image of a demolding glove when it receives a sensing signal; and a second image acquisition device to acquire an image of a demolding glove when it receives a sensing signal. The first and second image acquisition devices are deployed at different locations. The first glove image is an end face image of the demolding glove, which is obtained by the first image acquisition device being deployed on the demolding glove in front of the fingers pointing. The second glove image is a surface image of the demolding glove, which is an image acquired by the second image acquisition device of the surface of the demolding glove.

[0110] The defect detection module is used by the industrial control equipment to perform defect detection on the demolding glove based on machine vision and in combination with the first glove image and the second glove image after receiving the first glove image and the second glove image. The defect detection result of the demolding glove is associated with the gripper set on the demolding machine, so as to give a warning to the gripper based on the defect detection results associated with the gripper. The demolding machine is currently used to fix the wrist of the demolding glove.

[0111] As an optional implementation of this application, when the result of defect detection on the release gloves meets the specified early warning conditions, the machine vision-based defect detection device further includes:

[0112] The first early warning module is used to issue the first early warning information, which indicates that the demolding gloves are unqualified.

[0113] As an optional implementation of this application, the machine vision-based defect detection device further includes:

[0114] The recognition module is used to identify the gripper markings from the second glove image;

[0115] The second early warning module is used to associate the results of defect detection on the release gloves with the markings on the grippers.

[0116] As an optional implementation of this application, the result of defect detection of the release gloves includes at least: damage detection result, and the second early warning module is specifically used for:

[0117] The damage detection results associated with the grippers are statistically analyzed at preset time intervals;

[0118] When the statistical number of damage detection results exceeds a specified value, a second warning message is issued, which indicates a gripper malfunction.

[0119] As an optional implementation of this application, the machine vision-based defect detection device further includes:

[0120] The distance determination module is used to determine the distance from each specified position in the second glove image to the demolding machine in the second glove image based on the second glove image; each specified position includes at least the position of each finger on the demolding glove on the hand mold;

[0121] The third early warning module is used to issue a third early warning message when the distance from any specified position to the demolding machine does not meet the specified distance condition. The third early warning message indicates that the clamp of the demolding machine is malfunctioning.

[0122] This concludes the process. Figure 7 Description of the block diagram shown.

[0123] The specific implementation process of the functions and roles of each unit in the above device can be found in the implementation process of the corresponding steps in the above method, and will not be repeated here.

[0124] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of the solution in this specification according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0125] Correspondingly, embodiments of this application also provide Figure 7 The hardware structure diagram of the device shown is as follows: Figure 8 As shown, the electronic device can be a device implementing the above-described method. Figure 8 As shown, the hardware architecture includes a processor and memory.

[0126] The memory is used to store machine-executable instructions;

[0127] The processor is configured to read and execute machine-executable instructions stored in the memory to implement the corresponding machine vision-based defect detection method embodiment shown above.

[0128] As one embodiment, the memory can be any electronic, magnetic, optical, or other physical storage device that can contain or store information such as executable instructions, data, etc. For example, the memory can be volatile memory, non-volatile memory, or similar storage media. Specifically, the memory can be RAM (Random Access Memory), flash memory, storage drives (such as hard disk drives), solid-state drives, any type of storage disk (such as optical discs, DVDs, etc.), or similar storage media, or combinations thereof.

[0129] This concludes the process. Figure 8 Description of the electronic device shown.

[0130] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0131] Other embodiments of this specification will readily occur to those skilled in the art upon consideration of the specification and practice of the invention claimed herein. This specification is intended to cover any variations, uses, or adaptations that follow the general principles of this specification and include common knowledge or customary techniques in the art not claimed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this specification are indicated by the following claims.

[0132] It should be understood that this specification is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this specification is limited only by the appended claims.

[0133] The above description is merely a preferred embodiment of this specification and is not intended to limit this specification. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this specification should be included within the scope of protection of this specification.

Claims

1. A defect detection method based on machine vision, characterized in that, The method includes: During the transfer of the hand mold and the release glove, when the deployed sensing components detect the hand mold, they send sensing signals to the deployed first image acquisition device and the deployed second image acquisition device, respectively. The release glove refers to a glove that is not fully fitted onto the hand mold. When the first image acquisition device receives the sensing signal, it acquires a first glove image of the demolding glove; when the second image acquisition device receives the sensing signal, it acquires a second glove image of the demolding glove; the first image acquisition device and the second image acquisition device are deployed in different positions; the first glove image is an end face image of the demolding glove, which is obtained by the first image acquisition device being deployed on the demolding glove and capturing the front of the glove as the fingers point; the second glove image is a surface image of the demolding glove, which is an image captured by the second image acquisition device of the surface of the demolding glove. After receiving the first glove image and the second glove image, the industrial control computer performs defect detection on the demolding glove based on machine vision and in combination with the first glove image and the second glove image. The result of the defect detection on the demolding glove is associated with the gripper set on the demolding machine. Based on the defect detection results associated with the gripper, the gripper is given an early warning. The demolding machine is currently used to fix the wrist of the demolding glove. Specifically, based on the second glove image, the distance from each designated position in the second glove image to the demolding machine in the second glove image is determined; each designated position includes at least the position of each finger on the demolding glove on the hand mold; when the distance from any designated position to the demolding machine does not meet the designated distance condition, a third warning message is issued, the third warning message indicating a gripper malfunction of the demolding machine.

2. The method according to claim 1, characterized in that, When the result of defect detection on the release glove meets the specified early warning conditions, the method further includes: A first warning message is issued, which indicates that the release gloves are defective.

3. The method according to claim 1, characterized in that, The result of defect detection on the demolding glove is correlated with the grippers on the demolding machine, including: Identify the gripper markings from the second glove image; The results of defect detection on the release glove are associated with the identification of the gripper.

4. The method according to claim 3, characterized in that, The defect detection results of the release glove include at least: damage detection results. The warning given to the gripper based on the defect detection results associated with the gripper includes: The damage detection results associated with the grippers are statistically analyzed at preset time intervals; When the statistical number of damage detection results exceeds a specified value, a second warning message is issued, which indicates a gripper malfunction.

5. A defect detection device based on machine vision, characterized in that, The device includes: The sensing module is used to send sensing signals to the first image acquisition device and the second image acquisition device respectively when the deployed sensing component detects the hand mold during the transfer of the hand mold and the demolding glove. The demolding glove refers to a glove that is not completely covered by the hand mold. An image acquisition module is used for the first image acquisition device to acquire a first glove image of the demolding glove when it receives the sensing signal; and for the second image acquisition device to acquire a second glove image of the demolding glove when it receives the sensing signal. The first image acquisition device and the second image acquisition device are deployed in different locations. The first glove image is an end face image of the demolding glove, obtained by the first image acquisition device being deployed on the demolding glove and capturing the image from the front of the fingers pointing to it. The second glove image is a surface image of the demolding glove, captured by the second image acquisition device on the surface of the demolding glove. The defect detection module is used by the industrial control computer to perform defect detection on the demolding glove based on machine vision and in combination with the first glove image and the second glove image after receiving the first glove image and the second glove image. The defect detection result of the demolding glove is associated with the gripper set on the demolding machine, so as to give a warning to the gripper based on the defect detection results associated with the gripper. The demolding machine is currently used to fix the wrist of the demolding glove. The device further includes: a distance determination module, used to determine the distance from each specified position in the second glove image to the demolding machine in the second glove image based on the second glove image; each specified position includes at least the position of each finger on the demolding glove on the hand mold; and a third early warning module, used to issue a third early warning message when the distance from any specified position to the demolding machine does not meet the specified distance condition, the third early warning message indicating a gripper malfunction of the demolding machine.

6. The apparatus according to claim 5, characterized in that, When the result of defect detection on the release glove meets the specified early warning conditions, the device further includes: The first early warning module is used to issue a first early warning message, which indicates that the demolding gloves are defective.

7. The apparatus according to claim 5, characterized in that, The device further includes: The recognition module is used to identify the gripper markings from the second glove image; The second early warning module is used to associate the result of defect detection of the release glove with the identification of the gripper.

8. The apparatus according to claim 7, characterized in that, The defect detection results of the release gloves include at least: damage detection results, and the second early warning module is specifically used for: The damage detection results associated with the grippers are statistically analyzed at preset time intervals; When the statistical number of damage detection results exceeds a specified value, a second warning message is issued, which indicates a gripper malfunction.

9. An electronic device, characterized in that, Electronic devices include: processors and memory; The memory is used to store machine-executable instructions; The processor is configured to read and execute machine-executable instructions stored in the memory to implement the method as described in any one of claims 1 to 4.

Images