Ceramic Tube Sorting Method and Device Based on Image Recognition

Abstract

The present application provides a sorting method and device for ceramic tubes based on image recognition, which relates to the field of computer technology. Among them, the method includes: placing the ceramic tubes to be sorted on a sorting turntable and stably placing them at a fixed angle. As the sorting turntable rotates, a set of ceramic tube images of the ceramic tubes is acquired, where the set of ceramic tube images includes a front-end image, a rear-end image, and a length image; calling a pre-trained image recognition model, inputting the set of ceramic tube images into the image recognition model for recognition, and obtaining corresponding recognition results, where the recognition results include good products and defective products; when the sorting turntable conveys to the blanking area, controlling different air valves to open based on the recognition results, and sending the ceramic tubes to a predetermined area for classified collection. The present application solves the problem of low accuracy in sorting ceramic tubes in the related art.

Description

Technical Field

[0001] This application relates to the field of computer technology. Specifically, this application relates to a method and device for sorting ceramic tubes based on image recognition. Background Art

[0002] Electronic ceramic tubes generally refer to ceramic components used in electronic devices. These components can be insulators or ceramic parts with specific electrical properties. Electronic ceramic tubes have a wide range of applications in the electronics industry, such as being used as insulators, high-frequency circuit components, sensor components, etc. During the process of sorting ceramic tubes, it is necessary to ensure that these components have good electrical and mechanical properties.

[0003] Traditional sorting of ceramic tubes mainly relies on manual visual inspection. This method has many limitations, including but not limited to: since manual inspection is required one by one, the sorting speed is slow and it is difficult to meet the needs of large-scale production. In addition, due to the different experience and technical levels of different inspectors, the sorting standards are inconsistent and the consistency is poor.

[0004] As can be seen from the above, how to improve the sorting efficiency of ceramic tubes based on image recognition still needs to be solved. Summary of the Invention

[0005] This application provides a method, device, electronic device, and storage medium for sorting ceramic tubes based on image recognition, which can solve the problem of low accuracy in sorting ceramic tubes in related technologies. The technical solutions are as follows:

[0006] According to one aspect of this application, a method for sorting ceramic tubes based on image recognition includes: placing the ceramic tubes to be sorted on a sorting turntable and stabilizing them at a fixed angle. As the sorting turntable rotates, a set of ceramic tube images of the ceramic tubes is obtained, where the set of ceramic tube images includes a front-end image, a rear-end image, and a length image; calling a pre-trained image recognition model, inputting the set of ceramic tube images into the image recognition model for recognition, and obtaining corresponding recognition results, where the recognition results include good products and defective products; when the sorting turntable is transported to the blanking area, based on the recognition results, different air valves are controlled to open, and the ceramic tubes are sent to a predetermined area for classification and collection.

[0007] In an exemplary embodiment,

[0008] In an exemplary embodiment, during the process of obtaining the set of ceramic tube images of the ceramic tubes, the method further includes: controlling a dual light source emitting visible light and near-infrared spectrum to irradiate the ceramic tubes to be sorted; obtaining a dual-spectrum image of the ceramic tubes; where the image recognition model includes a deep learning hierarchical detection algorithm based on Transformer.

[0009] In an exemplary embodiment, in the process of inputting the set of ceramic tube images into the image recognition model for recognition to obtain corresponding recognition results, the method further includes: inputting all of the front-end image, back-end image, and length image corresponding to the dual-spectrum image into the image recognition model for recognition; or, inputting the front-end image, back-end image, and length image corresponding to the dual-spectrum image into the image recognition model one by one for recognition to obtain a front-end recognition result corresponding to the front-end image and a back-end recognition result corresponding to the back-end image; if there is a defective product in the front-end recognition result or the back-end recognition result and the defective ceramic tube is determined, stop the subsequent recognition of the defective ceramic tube and send the defective ceramic tube to a predetermined area for classification and collection.

[0010] In an exemplary embodiment, the method further includes: after identifying a defective ceramic tube, determining a corresponding defective position based on the defective ceramic tube, where the defective position includes the front end of the ceramic tube, the back end of the ceramic tube, and the length of the ceramic tube; obtaining the defective frequency corresponding to each of the defective positions, sorting the three defective frequencies; determining the vulnerable position of the ceramic tube based on the maximum defective frequency, and switching the recognition order of the vulnerable position of the ceramic tube to priority recognition.

[0011] In an exemplary embodiment, the dual-spectrum image includes a visible light image and a near-infrared light image, and the method further includes: simultaneously or alternately emitting visible light and near-infrared light to irradiate the ceramic tube to be sorted to obtain corresponding visible light images and near-infrared light images; extracting corresponding visible light features based on the visible light images, extracting corresponding near-infrared light features based on the near-infrared light images, and fusing the visible light features and the near-infrared light features to obtain corresponding fusion features; inputting the fusion features into the image recognition model for recognition.

[0012] In an exemplary embodiment, in the process of fusing the visible light features and the near-infrared light features to obtain corresponding fusion features, the method further includes: obtaining visible light image I vis and near-infrared light image I NIR , preprocessing visible light image I vis and visible light image I NIR to obtain processed I′ vis and I′ NIR ; performing feature extraction on both I′ vis and I′ NIR to obtain corresponding visible light feature F vis and near-infrared light feature F NIR ; retrieving weight data, where the weight of visible light is α, the weight of near-infrared light is β, and α + β = 1, and calculating fusion feature F fused , and F fused= α × F vis + β × F NIR 。

[0013] In an exemplary embodiment, the method further includes: controlling a front sensor to obtain the reflection intensity on the surface of the ceramic tube; determining whether the reflection intensity matches a preset light intensity range, and if not, adjusting the light intensity.

[0014] According to one aspect of the present application, a ceramic tube sorting device based on image recognition includes: a ceramic tube image set acquisition module, which places the ceramic tubes to be sorted on a sorting turntable and stably places them at a fixed angle. As the sorting turntable rotates, it is used to acquire a set of ceramic tube images, where the set of ceramic tube images includes a front-end image, a rear-end image, and a length image; an identification result acquisition module, which retrieves a pre-trained image recognition model and inputs the set of ceramic tube images into the image recognition model for identification, and is used to obtain corresponding identification results, where the identification results include good products and defective products; a classification and collection module, which controls different air valves to open based on the identification results when the sorting turntable is transported to the blanking area, and is used to send the ceramic tubes to a predetermined area for classification and collection.

[0015] According to one aspect of the present application, an electronic device includes at least one processor and at least one memory, where computer-readable instructions are stored on the memory; the computer-readable instructions are executed by one or more of the processors, enabling the electronic device to implement the above-mentioned ceramic tube sorting method based on image recognition.

[0016] According to one aspect of the present application, a storage medium stores computer-readable instructions thereon, and the computer-readable instructions are executed by one or more processors to implement the above-mentioned ceramic tube sorting method based on image recognition.

[0017] According to one aspect of the present application, a computer program product includes computer-readable instructions, the computer-readable instructions are stored in a storage medium, and one or more processors of an electronic device read the computer-readable instructions from the storage medium, load and execute the computer-readable instructions, enabling the electronic device to implement the above-mentioned ceramic tube sorting method based on image recognition.

[0018] The beneficial effects brought by the technical solution provided by the present application are:

[0019] During the rotation of the sorting turntable, images of the ceramic tubes are acquired from different angles (front end, rear end, and length direction), so that the appearance quality of the ceramic tubes can be comprehensively inspected. Then, the image recognition model can quickly process a large number of images in a short time, thus realizing a high-speed sorting process. When the sorting turntable moves to the discharging area, the system controls the corresponding air valves to open according to the recognition results, and accurately sends the ceramic tubes to the preset collection area. On the one hand, due to the high degree of automation of the whole process, continuous and uninterrupted production can be achieved, reducing the waiting time and the time of manual intervention. In this way, errors in manual operations can be avoided, and the accuracy and efficiency of sorting can be improved. On the other hand, by promptly identifying defective products and separating them, resource waste in subsequent processing steps is reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments of the present application. Obviously, the drawings in the following description are only some embodiments of the present application. For those skilled in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0021] Figure 1 is a schematic diagram of the implementation environment related to the present application;

[0022] Figure 2 is a flowchart of a method for sorting ceramic tubes based on image recognition shown according to an exemplary embodiment;

[0023] Figure 3 is a flowchart of S103 to S105 in a method for sorting ceramic tubes based on image recognition shown according to an exemplary embodiment;

[0024] Figure 4 is a flowchart of S106 to S108 in a method for sorting ceramic tubes based on image recognition shown according to an exemplary embodiment;

[0025] Figure 5 is a block diagram of the structure of a device for sorting ceramic tubes based on image recognition shown according to an exemplary embodiment.. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] The following will describe in detail the embodiments of the present application. The examples of the embodiments are shown in the drawings, where the same or similar reference numerals represent the same or similar elements or elements with the same or similar functions from beginning to end. The embodiments described below by referring to the drawings are exemplary and are only used to explain the present application, and cannot be construed as a limitation of the present application.

[0027] Those skilled in the art can understand that, unless specifically stated otherwise, the singular forms "a", "an", "the" and "said" used herein may also include the plural forms. It should be further understood that the term "including" used in the specification of the present disclosure means the presence of the described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or their groups. It should be understood that when we say that an element is "connected" or "coupled" to another element, it can be directly connected or coupled to other elements, or there may also be intermediate elements. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any unit and all combinations of one or more related listed items.

[0028] The ceramic tube sorting method based on image recognition provided by the present application can effectively improve the accuracy of ceramic tube sorting. Correspondingly, the ceramic tube sorting method based on image recognition is applicable to a ceramic tube sorting device based on image recognition, and the ceramic tube sorting device based on image recognition can be deployed on an electronic device.

[0029] To make the objectives, technical solutions and advantages of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the accompanying drawings.

[0030] Figure 1 It is a schematic diagram of the implementation environment involved in a ceramic tube sorting method based on image recognition. The implementation environment includes an acquisition end and a service end.

[0031] Please refer to Figure 2 , the embodiments of the present application provide a ceramic tube sorting method based on image recognition. This method is applicable to an electronic device, and the electronic device can be Figure 1 the server in the shown implementation environment.

[0032] In the following method embodiments, for the convenience of description, the execution subject of each step of the method is taken as an example of an electronic device for illustration, but this is not a specific limitation thereto.

[0033] As Figure 2 shown, the method may include the following steps:

[0034] S100, place the ceramic tube to be sorted on the sorting turntable and make it stably placed at a fixed angle. As the sorting turntable rotates, obtain the ceramic tube image set of the ceramic tube.

[0035] It should be noted here that the ceramic tubes to be sorted can be first placed on a vibrating bowl feeder for feeding, so that the ceramic tubes can be placed on the sorting turntable at a fixed angle, and the placement position and angle of the ceramic tubes on the sorting turntable are fixed, ensuring that the images captured each time are obtained under consistent conditions, which helps to improve the quality and consistency of the images.

[0036] Among them, the set of ceramic tube images includes front-end images, rear-end images and length images; during the rotation of the sorting turntable, images of the ceramic tubes are obtained from different angles (front-end, rear-end and length directions), so that the appearance quality of the ceramic tubes can be comprehensively inspected.

[0037] S110, retrieve the pre-trained image recognition model, input the set of ceramic tube images into the image recognition model for recognition, and obtain the corresponding recognition results.

[0038] Among them, the recognition results include good products and defective products. In addition, the image recognition model applied here is pre-trained. The specific training process is as follows: collect a large number of ceramic tube images as the training set. These images should include various types of good products and defective products, and for each image, its category (good product or defective product) needs to be marked, and the specific defect position or type may also need to be marked. Then remove duplicate, blurred or non-compliant images to ensure the quality of the data set. It is necessary to adjust the image size, unify the color space, etc. to make the images consistent. The diversity and richness of the data set can also be increased through transformations such as rotation, scaling, and flipping to help the model generalize better; select a suitable deep learning framework according to the task requirements, such as a convolutional neural network, to divide the data set into a training set, a validation set and a test set. The training set is used to train the model, the validation set is used to adjust the hyperparameters, and the test set is used to evaluate the performance of the final model. Use the data in the training set for iterative training, adjust the weights and biases through the backpropagation algorithm, minimize the loss function, and use the validation set to monitor the performance during the training process. If problems such as overfitting are found, adjust the model structure or regularization parameters, and make necessary adjustments according to the evaluation results, such as adjusting the learning rate, adding more training data or modifying the model architecture. Finally, save the trained model as the image recognition model for easy deployment, and deploy the model to the actual sorting system for real-time image recognition and sorting tasks.

[0039] S120, when the sorting turntable is conveyed to the discharging area, control different air valves to open based on the recognition results, and send the ceramic tubes to the predetermined area for classified collection.

[0040] Among them, when the sorting turntable moves to the discharging area, the system controls the corresponding air valves to open according to the recognition results, and accurately sends the ceramic tubes to the preset collection area. This can avoid errors in manual operations and improve the accuracy of sorting.

[0041] It should be noted here that when the sorting turntable moves to the blanking area, after passing through the blanking areas corresponding to the good products and the defective products, if the ceramic tubes to be sorted on the sorting turntable are not blown off, at this time, another air blowing valve on the system control device is opened to collect the residual ceramic tubes on the sorting turntable, avoiding repeated detection and at the same time avoiding affecting the sorting of subsequent ceramic tubes on the sorting turntable.

[0042] In order to further improve the detection of ceramic tubes to be sorted, during the process of obtaining the set of ceramic tube images of the ceramic tubes, the method further includes:

[0043] S101, controlling dual illumination of visible light and near-infrared spectrum to be directed at the ceramic tubes to be sorted.

[0044] It should be noted here that visible light can provide conventional visual information on the surface of the ceramic tube, facilitating the capture of features such as surface color and shape; while the near-infrared spectrum can reveal some internal characteristics of the material, such as internal structure and compositional differences, which is particularly useful for detecting some subtle defects under the surface.

[0045] S102, obtaining the dual-spectrum images of the ceramic tubes.

[0046] Among them, by combining the image information of visible light and near-infrared spectrum, a more comprehensive characterization of the ceramic tube can be obtained, which helps to improve the accuracy and reliability of detection; the near-infrared spectrum image can detect some internal or subsurface defects that cannot be found only by visible light, such as microcracks and pores, so the dual-spectrum image can reduce the influence of environmental light changes on the image quality and improve the consistency and stability of the image.

[0047] Among them, in the embodiments of the present application, the image recognition model includes a deep learning hierarchical detection algorithm based on Transformer. Transformer is a powerful deep learning architecture, especially suitable for processing sequence data. In image recognition tasks, it can be used to process local and global context information in image patches or feature maps, and the model based on Transformer can effectively capture details and patterns in the image, especially for complex defect detection tasks, and can provide more accurate recognition results.

[0048] By adopting dual illumination and a deep learning hierarchical detection algorithm based on Transformer, not only can more information on the surface and inside of the ceramic tube be obtained, but also the good products and defective products can be more accurately identified and classified.

[0049] After obtaining the dual-spectrum images, as Figure 3 shown, the method further includes:

[0050] S103. Input all the front-end image, back-end image, and length image corresponding to the dual-spectrum image into the image recognition model for recognition.

[0051] Among them, by inputting all the images (front-end image, back-end image, and length image) into the image recognition model for recognition simultaneously, the image recognition model can comprehensively consider the information from multiple perspectives, thus making a more accurate judgment. It can also reduce the number of model calls and improve the overall processing speed.

[0052] S104. Or, input the front-end image, back-end image, and length image corresponding to the dual-spectrum image into the image recognition model one by one for recognition, and obtain the front-end recognition result corresponding to the front-end image and the back-end recognition result corresponding to the back-end image.

[0053] S105. If there are defective products in the front-end recognition result or the back-end recognition result, and the defective ceramic tube is determined, stop the subsequent recognition of the defective ceramic tube, and send the defective ceramic tube to a predetermined area for classification and collection.

[0054] Input the front-end image, back-end image, and length image into the image recognition model for recognition one by one respectively. If defective products are found in the front-end or back-end recognition result, immediately stop the subsequent recognition steps for this ceramic tube and directly classify it as a defective product. Once a certain ceramic tube is determined to be a defective product, it can be processed immediately without additional recognition steps, thus saving computing resources and time.

[0055] By using the information of the dual-spectrum image and adjusting the corresponding recognition strategy, the efficiency and accuracy of the ceramic tube sorting process are improved, and at the same time, unnecessary consumption of computing resources is reduced.

[0056] In addition, it should be noted that during the recognition process, the front-end image, back-end image, and length image are recognized respectively. And in the above-mentioned strategy of recognizing one by one, in order to further improve the recognition efficiency, as Figure 4 shown, the following steps are also carried out:

[0057] S106. After recognizing a defective ceramic tube, determine the corresponding defective position based on the defective ceramic tube.

[0058] Among them, the defective position includes the front end of the ceramic tube, the back end of the ceramic tube, and the length of the ceramic tube. By determining the defective position, it is possible to more accurately understand which parts are prone to problems.

[0059] S107. Obtain the defective frequency corresponding to each defective position, and sort the three defective frequencies.

[0060] S108. Determine the vulnerable position of the ceramic tube based on the maximum defective frequency, and switch the recognition order of the vulnerable position of the ceramic tube to give priority to recognition.

[0061] Among them, sort the defect frequencies of the three defective positions. According to the sorting results, find the position with the highest defect frequency, that is, the vulnerable position, and adjust the recognition order of the vulnerable position to the position to be recognized preferentially. By preferentially recognizing the vulnerable position, defective products can be found faster, thereby reducing unnecessary subsequent recognition steps and improving the sorting efficiency.

[0062] In addition, in the embodiment of the present application, in the process of recognizing the dual-spectrum image, it is necessary to simultaneously or alternately emit visible light and emit near-infrared light to irradiate the ceramic tube to be sorted, and then obtain the corresponding visible light image I vis and near-infrared light image I NIR , preprocess the visible light image I vis and visible light image I NIR to obtain the processed I′ vis and I′ NIR , then perform feature extraction on both I′ vis and I′ NIR to obtain the corresponding visible light feature F vis and near-infrared light feature F NIR .

[0063] It should be noted here that for the visible light feature F vis and near-infrared light feature F NIR , corresponding weight data are preset in the system, and the weight data can be modified. Then, the weight data are retrieved, where the weight of visible light is α, the weight of near-infrared light is β, and α + β = 1, and the fused feature F fused is calculated, and F fused = α × F vis + β × F NIR . Finally, input the obtained fused feature F fused into the image recognition model for recognition, and the corresponding recognition result can be obtained.

[0064] By fusing the features of visible light and near-infrared light, the internal and external characteristics of the ceramic tube can be comprehensively analyzed from multiple angles, improving the recognition accuracy. The adjustable nature of the weight data enables the image recognition model to be personalized according to different types of ceramic tubes or specific requirements, expanding the applicable range of the image recognition model. Moreover, the use of the fused feature reduces the computational amount required for separately processing each spectral image and speeds up the recognition speed.

[0065] Finally, during the process of irradiating the ceramic tube to be sorted, the light intensity can be adjusted, which specifically includes the following steps: controlling the front sensor to obtain the reflection intensity on the surface of the ceramic tube, and then judging whether the reflection intensity matches the preset light intensity range. If it does not match, adjust the light intensity.

[0066] By controlling the front sensor to obtain the reflected light intensity on the surface of the ceramic tube and adjusting the light intensity according to whether the reflected light intensity matches a pre-set light intensity range, the quality of image acquisition can be ensured, the accuracy and reliability of image recognition can be improved, and thus the performance and efficiency of the entire sorting system can be enhanced. This method is particularly applicable to automated production lines and can significantly improve the accuracy and speed of ceramic tube sorting.

[0067] The following are the device embodiments of this application, which can be used to execute the ceramic tube sorting method based on image recognition involved in this application. For details not disclosed in the device embodiments of this application, please refer to the method embodiments of the ceramic tube sorting method based on image recognition involved in this application.

[0068] Please refer to Figure 5 , in the embodiments of this application, a ceramic tube sorting device based on image recognition is provided, including but not limited to:

[0069] A ceramic tube image set acquisition module 200, which places the ceramic tubes to be sorted on the sorting turntable and makes them stably placed at a fixed angle. As the sorting turntable rotates, it is used to acquire the ceramic tube image set of the ceramic tubes, where the ceramic tube image set includes a front-end image, a rear-end image, and a length image;

[0070] An identification result acquisition module 210, which retrieves a pre-trained image recognition model and inputs the ceramic tube image set into the image recognition model for recognition to obtain the corresponding recognition results, where the recognition results include good products and defective products;

[0071] A classification and collection module 220, which controls different air valves to open based on the recognition results when the sorting turntable is conveyed to the discharging area, and is used to send the ceramic tubes to a predetermined area for classification and collection.

[0072] In an exemplary embodiment, the device further includes but not limited to:

[0073] A light control module, which is used to control dual illumination of visible light and near-infrared spectrum to be emitted towards the ceramic tubes to be sorted;

[0074] A dual-spectrum image acquisition module, which is used to acquire the dual-spectrum images of the ceramic tubes;

[0075] Among them, the image recognition model includes a deep learning hierarchical detection algorithm based on Transformer.

[0076] In an exemplary embodiment, the device further includes but not limited to:

[0077] An image recognition module, which is used to input all the front-end image, rear-end image, and length image corresponding to the dual-spectrum image into the image recognition model for recognition;

[0078] An individual recognition module, or, for individually inputting the front-end image, back-end image, and length image corresponding to the dual-spectrum image into an image recognition model for recognition, to obtain the front-end recognition result corresponding to the front-end image and the back-end recognition result corresponding to the back-end image;

[0079] If there are defective products in the front-end recognition result or the back-end recognition result, and the defective ceramic tube is determined, the subsequent recognition of the defective ceramic tube is stopped, and the defective ceramic tube is sent to a predetermined area for classification and collection.

[0080] In an exemplary embodiment, the device further includes but is not limited to:

[0081] A defective position determination module, after identifying a defective ceramic tube, for determining the corresponding defective position based on the defective ceramic tube, where the defective position includes the front end of the ceramic tube, the back end of the ceramic tube, and the length of the ceramic tube;

[0082] A sorting module, for obtaining the defective frequencies corresponding to each defective position, and for sorting the three defective frequencies;

[0083] An identification order switching module, for determining the vulnerable position of the ceramic tube based on the maximum defective frequency, and for switching the identification order of the vulnerable position of the ceramic tube to prior identification.

[0084] In an exemplary embodiment, the device further includes but is not limited to:

[0085] An image acquisition module, for simultaneously or alternately emitting visible light and near-infrared light to irradiate the ceramic tube to be sorted, and for obtaining the corresponding visible light image and near-infrared light image;

[0086] A fusion module, for extracting the corresponding visible light features based on the visible light image and extracting the corresponding near-infrared light features based on the near-infrared light image, and for fusing the visible light features and the near-infrared light features to obtain the corresponding fusion features;

[0087] A feature recognition module, for inputting the fusion features into an image recognition model for recognition.

[0088] In an exemplary embodiment, the device further includes but is not limited to:

[0089] Obtain the visible light image I vis and the near-infrared light image I NIR , preprocess the visible light image I vis and the visible light image I NIR to obtain the processed I′ vis and I′ NIR ;

[0090] For I′ vis and I′ NIRFeature extraction is performed on all of them to obtain the corresponding visible light feature F vis and the near-infrared light feature F NIR ;

[0091] Retrieve the weight data, where the weight of visible light is α and the weight of near-infrared light is β, and α + β = 1, and calculate the fusion feature F fused and F fused = α × F vis + β × F NIR .

[0092] In an exemplary embodiment, the device further includes but is not limited to:

[0093] A specular reflection intensity acquisition module that controls a front sensor to acquire the specular reflection intensity on the surface of the ceramic tube;

[0094] A judgment module for judging whether the specular reflection intensity matches a preset light intensity range, and if not, adjusting the light intensity.

[0095] It should be noted that when the above-mentioned ceramic tube sorting device based on image recognition performs ceramic tube sorting based on image recognition, only the above-mentioned division of each functional module is used as an example. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the ceramic tube sorting device based on image recognition will be divided into different functional modules to complete all or part of the functions described above.

[0096] In addition, the above-mentioned ceramic tube sorting device based on image recognition provided by the above embodiment and the embodiment of the ceramic tube sorting method based on image recognition belong to the same concept. The specific ways in which each module performs operations have been described in detail in the method embodiment and will not be repeated here.

[0097] According to one aspect of the present application, an electronic device includes at least one processor and at least one memory, wherein computer-readable instructions are stored on the memory; the computer-readable instructions are executed by one or more processors, so that the electronic device implements the above-mentioned ceramic tube sorting method based on image recognition.

[0098] In addition, a storage medium is provided in an embodiment of the present application. Computer-readable instructions are stored on the storage medium, and the computer-readable instructions are executed by one or more processors to implement the above-mentioned ceramic tube sorting method based on image recognition.

[0099] In an embodiment of the present application, a computer program product is provided. The computer program product includes computer-readable instructions stored in a storage medium. One or more processors of an electronic device read the computer-readable instructions from the storage medium, load and execute the computer-readable instructions, so that the electronic device implements the above-mentioned ceramic tube sorting method based on image recognition.

[0100] In summary, during the rotation of the sorting turntable, images of the ceramic tubes are acquired from different angles (front end, rear end, and length direction), so that the appearance quality of the ceramic tubes can be comprehensively inspected. Then, the image recognition model can quickly process a large number of images in a short time, thereby realizing a high-speed sorting process. When the sorting turntable moves to the blanking area, the system controls the corresponding air valve to open according to the recognition result, and accurately sends the ceramic tubes to the preset collection area. On the one hand, since the whole process is highly automated, continuous and uninterrupted production can be achieved, reducing the waiting time and the time of manual intervention. In this way, errors in manual operations can be avoided, and the accuracy and efficiency of sorting can be improved. On the other hand, by promptly identifying defective products and separating them, resource waste in subsequent processing steps is reduced.

[0101] It should be understood that although the steps in the flowchart of the accompanying drawings are shown in sequence according to the arrows, these steps do not necessarily have to be executed in the order indicated by the arrows. Unless otherwise clearly stated in this article, there is no strict order restriction for the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages. These sub-steps or stages do not necessarily have to be executed at the same time, but can be executed at different times, and their execution order does not necessarily have to be sequential, but can be executed alternately or alternately with at least a part of other steps or sub-steps or stages of other steps.

[0102] The above are only some embodiments of the present application. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present application, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present application.

Claims

1. A ceramic tube sorting method based on image recognition, characterized in that: include: The ceramic tubes to be sorted are placed on a sorting turntable and stably placed at a fixed angle. As the sorting turntable rotates, a ceramic tube image set of the ceramic tubes is obtained. In the process of obtaining the ceramic tube image set of the ceramic tubes, the method further includes: controlling the emission of dual light of visible light and near-infrared spectrum to illuminate the ceramic tubes to be sorted; obtaining a dual-spectrum image of the ceramic tubes, the dual-spectrum image including a visible light image and a near-infrared light image; wherein the ceramic tube image set includes a front end image, a rear end image and a length image; Retrieve a pre-trained image recognition model, and input the ceramic tube image set into the image recognition model for recognition; in the process of acquiring dual-spectrum images and performing recognition, the method further comprises: simultaneously or alternately emitting visible light and emitting near-infrared light to illuminate the ceramic tubes to be sorted, and acquiring corresponding visible light images and near-infrared light images; extracting corresponding visible light features based on the visible light image, and extracting corresponding near-infrared light features based on the near-infrared light image, and fusing the visible light features with the near-infrared light features to obtain corresponding fused features; inputting the fused features into the image recognition model for recognition; and acquiring corresponding recognition results, wherein the recognition results include good products and defective products, and the image recognition model includes a deep learning hierarchical detection algorithm based on Transformer; When the sorting turntable is transported to the unloading area, different air valves are controlled to open based on the recognition result, and the ceramic tubes are transported to the predetermined area for classification and collection.

2. The method according to claim 1, characterized in that In the process of inputting the ceramic tube image set into the image recognition model for recognition and obtaining the corresponding recognition result, the method further includes: Inputting the front-end image, the rear-end image and the length image corresponding to the dual-spectrum image into the image recognition model for recognition; Or, the front-end image, the rear-end image and the length image corresponding to the dual-spectrum image are input into the image recognition model one by one for recognition, and the front-end recognition result corresponding to the front-end image and the rear-end recognition result corresponding to the rear-end image are obtained; If there are defective products in the front-end recognition results or the back-end recognition results, and the defective ceramic tubes are determined to be defective, the subsequent identification of the defective ceramic tubes will be stopped, and the defective ceramic tubes will be sent to the predetermined area for classification and collection.

3. The method according to claim 2, characterized in that The method further comprises: After identifying a defective ceramic tube, determining a corresponding defective position based on the defective ceramic tube, wherein the defective position includes a front end of the ceramic tube, a rear end of the ceramic tube, and a length of the ceramic tube; Obtain the defect frequency corresponding to each defect position, and sort the three defect frequencies; The vulnerable position of the ceramic tube is determined based on the maximum defect frequency, and the identification order of the vulnerable position of the ceramic tube is switched to priority identification.

4. The method according to claim 1, characterized in that In the process of fusing the visible light feature with the near infrared light feature to obtain a corresponding fused feature, the method further includes: Acquire visible light images and near-infrared images , for visible light images and visible light images Perform preprocessing and obtain the processed and ; right and Feature extraction is performed to obtain the corresponding visible light features Near-infrared light characteristics ; Retrieve weight data, where the weight of visible light is , the near infrared light weight is ,and , and calculate the fusion features ,and .

5. The method according to claim 1, characterized in that The method further comprises: Control the front sensor to obtain the reflection intensity of the ceramic tube surface; Determine whether the reflected light intensity matches the preset light intensity range. If not, adjust the light intensity.

6. A sorting device for performing the ceramic tube sorting method based on image recognition as described in any one of claims 1 to 5, characterized in that: include: The ceramic tube image set acquisition module places the ceramic tube to be sorted on the sorting turntable and stably places it at a fixed angle. As the sorting turntable rotates, the ceramic tube image set of the ceramic tube is acquired, wherein the ceramic tube image set includes a front end image, a rear end image and a length image; A recognition result acquisition module, which calls a pre-trained image recognition model, inputs the ceramic tube image set into the image recognition model for recognition, and is used to obtain corresponding recognition results, wherein the recognition results include good products and defective products; The classification and collection module controls different air valves to open based on the recognition result when the sorting turntable is transported to the unloading area, so as to transport the ceramic tubes to the predetermined area for classification and collection.

7. An electronic device, characterized in that: include: at least one processor and at least one memory, wherein: The memory has computer-readable instructions stored thereon; The computer-readable instructions are executed by one or more of the processors, so that the electronic device implements the ceramic tube sorting method based on image recognition as described in any one of claims 1 to 5.

8. A storage medium having computer-readable instructions stored thereon, characterized in that: The computer-readable instructions are executed by one or more processors to implement the ceramic tube sorting method based on image recognition as described in any one of claims 1 to 5.

Images