Automatic detection and classification system for thermos cup surface defects based on image recognition

Abstract

The present invention relates to the technical field of thermos cup surface detection technology, and discloses an automatic detection and classification system for thermos cup surface defects based on image recognition. The system includes a scratch recognition module, which uses an image acquisition device to take high-resolution images of the surface of the thermos cup after production, and combines with a laser scanning device to identify the number, length, and depth data of scratches on the thermos cup surface; and a defect classification module, which is used to obtain a repair difficulty index based on the number, depth, and length of scratches on the thermos cup surface, and compare the repair difficulty index with a repair difficulty threshold. The present invention automatically detects scratches through image recognition, reducing manual intervention and being suitable for efficient quality control in mass production environments. The system can accurately measure the number, length, and depth of scratches, providing reliable data support for assessing the severity of scratches and the difficulty of repair.

Description

Technical Field

[0001] The present invention relates to the technical field of thermos cup surface detection, and in particular to an automatic detection and classification system for thermos cup surface defects based on image recognition. Background Art

[0002] Scratches are one of the most common surface defects on thermos bottles, especially those made of metal or coated materials. Scratches can occur even in the smallest detail during the manufacturing and packaging process. Therefore, identifying and controlling scratches is a crucial step in quality control.

[0003] During the factory production process, a small number of scratches on the surface of thermos cups in a batch of production orders will be repaired. For minor scratches, the surface of the stainless steel thermos cup can be restored by lightly polishing it. For deeper scratches, abrasive paste is needed to fill and smooth the scratches. However, how to identify and identify the scratches on each thermos cup and classify them into different treatment methods still requires quality inspectors to judge and classify them. This makes the detection of scratch defects on the surface of the thermos cup take a long time, inefficient, and may lead to misjudgments and omissions.

[0004] To this end, the present invention provides an automatic detection and classification system for surface defects of thermos cups based on image recognition. Summary of the Invention

[0005] In response to the problems existing in the above-mentioned prior art, the purpose of the present invention is to provide an automatic detection and classification system for surface defects of thermos cups based on image recognition, so as to detect and classify scratches on the surface of thermos cups using machine vision through image recognition technology, and help managers decide on appropriate treatment methods based on the classification results.

[0006] To achieve the above objectives, the present invention provides the following technical solution: an automatic detection and classification system for surface defects of thermos cups based on image recognition, comprising:

[0007] A scratch recognition module is used to use an image acquisition device to take high-resolution images of the surface of the thermos cup after production, and in combination with a laser scanning device to identify the number, length, and depth of scratches on the surface of the thermos cup;

[0008] A defect classification module is used to determine a repair difficulty index based on the number, depth, and length of scratches on the surface of the thermos cup, compare the repair difficulty index with a repair difficulty threshold, and classify the thermos cup as having a minor scratch defect or a severe scratch defect based on the comparison result;

[0009] a defect definition module, which is used to divide the thermos cup classified as having a severe scratch defect into corresponding areas based on the collected image data, specifically dividing the thermos cup into a cup body area and a cup lid area, and at the same time dividing the cup body area and the cup lid area into two parts, specifically dividing the cup body area into a cup body front area and a cup body back area, and dividing the cup lid area into a cup lid front area and a cup lid back area;

[0010] And according to the number of areas occupied by the scratches on the thermos cup, the thermos cup classified as having serious scratch defects will be classified as easy to repair or difficult to repair. Specifically, the number of areas occupied by the scratches on the thermos cup is compared with the easy to repair threshold. If the number of areas occupied by the scratches on the thermos cup is less than or equal to the easy to repair threshold, the thermos cup will be classified as easy to repair; if the number of areas occupied by the scratches on the thermos cup is greater than the easy to repair threshold, the thermos cup will be classified as difficult to repair.

[0011] The result feedback module is used to compare the number of thermos cups classified as difficult to repair with the repair quantity threshold, and make a final judgment feedback based on the comparison result.

[0012] In some embodiments, a repair quantity threshold is set. After the thermos cup is classified as having a slight scratch defect or a severe scratch defect, the number of thermos cups classified as having a severe scratch defect in this production order is compared with the repair quantity threshold to determine whether to repair the defective thermos cup.

[0013] In some embodiments, when the number of thermos cups classified as having severe scratch defects is less than the repair quantity threshold, it indicates that the number of thermos cups with severe scratches on the surface in this production batch is relatively small, and therefore a judgment is made to repair the defective thermos cups; and when the number of thermos cups classified as having severe scratch defects is greater than or equal to the repair quantity threshold, a first judgment is made not to repair the defective thermos cups.

[0014] In some embodiments, a specific method for obtaining the repair difficulty index is: obtaining the number, length, and depth data of scratches on the surface of the thermos cup, and taking the maximum depth of the scratches as the depth data, and calculating the repair difficulty index D as follows:

[0015]

[0016] Among them, N represents the number of scratches on the thermos, Li represents the length of the i-th scratch, Si represents the maximum depth of the i-th scratch, and a, b and c are weight coefficients used to adjust the impact of each factor on the overall repair difficulty.

[0017] In some embodiments, the specific method of judging feedback is: when the number of thermos cups that are difficult to repair is less than the repair quantity threshold, a judgment is made to repair the defective thermos cups; and when the number of thermos cups that are difficult to repair is greater than or equal to the repair quantity threshold, a judgment is made not to repair the defective thermos cups, and the defective thermos cups are re-produced or retrieved from inventory according to the number of defective thermos cups.

[0018] In some embodiments, after the scratch recognition module identifies the number of thermos cups with scratch defects on the surface, the total number of thermos cups required to be produced in the current production batch is obtained. When the number of thermos cups identified with scratches on the surface exceeds the scratch defect threshold, the system directly feeds back the result that the production line needs to be checked, and re-produces or retrieves the same number of thermos cups with scratch defects from the inventory to obtain the total number of thermos cups required by the order; when the number of thermos cups identified with scratches on the surface does not exceed the scratch defect threshold, the next step of the defect classification module is executed.

[0019] In some embodiments, the specific method for obtaining the data on the number, length, and depth of scratches on the surface of the thermos cup is:

[0020] An image acquisition device is used to capture high-resolution images of the surface of the thermos cup after production, and an edge detection algorithm is used to identify the boundaries of scratches on the surface of the thermos cup in the image. After extracting the contours of all scratches on the surface of the thermos cup, the total number of scratches is obtained, and the length of each scratch is measured using the image coordinate system. At the same time, a laser beam is emitted by a laser scanning device to measure the distance to the surface of the thermos cup. By comparing the height difference between the scratch area and the surrounding normal surface, the maximum depth of each scratch is measured.

[0021] The present invention further provides a computer-readable storage medium storing a computer program, which is executed by a processor to implement the above-mentioned automatic detection and classification system for surface defects of thermos cups based on image recognition.

[0022] Compared with the prior art, the technical solution provided by the present invention has the following beneficial effects:

[0023] First, the present invention automatically detects scratches through image recognition, reducing manual intervention and the risk of false detection and missed detection. It is suitable for efficient quality control in mass production environments. The system can accurately measure the number, length and depth of scratches, providing reliable data support for assessing the severity of scratches and the difficulty of repair.

[0024] Secondly, after the present invention classifies the severity of scratches on the surface of the thermos cup for the first time, it allows the scratch classification to be dynamically adjusted according to the concentration of scratches on the surface area of ​​the thermos cup, so that the system can formulate repair and processing strategies more flexibly and accurately.

[0025] Third, through the refined detection and classification process, the detailed data collected by the present invention can be used to analyze and optimize the production process, identify and reduce the root causes of scratch defects, and improve the quality stability of future production. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 This is a module diagram of the automatic detection and classification system for vacuum flask surface defects based on image recognition according to the present invention;

[0027] Figure 2 The figure is a schematic diagram of the working principle of the automatic detection and classification system for thermos cup surface defects based on image recognition of the present invention. DETAILED DESCRIPTION

[0028] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0029] It is to be understood that the term "one" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element may be one, while in another embodiment, the number of the elements may be multiple, and the term "one" should not be understood as a limitation on the quantity.

[0030] See also Figure 1-Figure 2 , the present invention provides an automatic detection and classification system for surface defects of thermos cups based on image recognition, the system includes a scratch recognition module, a defect classification module, a defect definition module and a result feedback module;

[0031] The scratch recognition module is used to use an image acquisition device to take high-resolution images of the surface of the thermos cup after production, ensuring that the entire surface of the thermos cup can be clearly seen. It also uses an edge detection algorithm to identify the boundaries of scratches on the surface of the thermos cup in the image. After extracting the outlines of all scratches on the surface of the thermos cup, the total number of scratches is determined, and the length of each scratch is measured using the image coordinate system. At the same time, a laser beam is emitted from a laser scanning device to measure the distance of the thermos cup surface. By comparing the height difference between the scratch area and the surrounding normal surface, the maximum depth of each scratch can be measured. The laser scanning data is combined with the image data, and the image data can be processed in real time to quickly screen and identify scratches and determine the areas that require detailed analysis. The laser scanning can only perform depth scanning on key areas, providing accurate depth information for these areas, supplementing the three-dimensional data that the image cannot provide. The combination of the two can achieve a more comprehensive scratch analysis, ensuring both speed and accuracy, thereby identifying the number, length, and depth of scratches on the surface of the thermos cup.

[0032] At the same time, after identifying the number of thermos cups with scratch defects on the surface, the total number of thermos cups required to be produced in the current production batch is obtained. When the number of thermos cups with scratch defects on the surface is identified to exceed the scratch defect threshold, it indicates that the raw materials or semi-finished products were not properly handled during the production process of this batch of orders, or the machinery and equipment used were improperly maintained and adjusted. The production line should be checked, and the same number of thermos cups with scratch defects should be reproduced or transferred from the inventory to obtain the total number of thermos cups required by the order. For example, set the total number of thermos cups required to be produced in the current production batch to 100, and the scratch defect threshold is 10. When the number of thermos cups with scratch defects on the surface is 11, the same number of thermos cups with scratch defects should be reproduced or transferred from the inventory. When the number of thermos cups with scratch defects on the surface does not exceed the scratch defect threshold, the next step of the defect classification module is executed.

[0033] The defect classification module includes setting a repair difficulty threshold and a repair quantity threshold. The repair quantity threshold is half of the scratch defect threshold. When the number of thermos cups with scratches on the surface is identified to be less than the scratch defect threshold, a repair difficulty index is obtained based on the number, depth and length of scratches on the surface of the thermos cup, and the repair difficulty index is compared with the repair difficulty threshold. Based on the comparison result, the thermos cup is classified as a minor scratch defect or a severe scratch defect. Then, the number of thermos cups classified as severe scratch defects in this production order is compared with the repair quantity threshold to determine whether to repair the defective thermos cup.

[0034] Specifically, when the number of thermos cups classified as having severe scratch defects is less than the repair quantity threshold, it means that the number of thermos cups with severe scratches on the surface in this production batch is small, and the corresponding defect repair time is less, so a judgment can be made to repair the defective thermos cups; and when the number of thermos cups classified as having severe scratch defects is greater than or equal to the repair quantity threshold, it means that at least half of the thermos cups in this production batch have severe surface scratches, and the repair process requires more energy and time of the staff. Comprehensive repair of the thermos cups with scratch defects may cause delayed delivery of the entire batch of orders, so the first judgment can be made not to repair the defective thermos cups.

[0035] For example, let's assume the total number of thermos cups to be produced in the current production batch is 100, the scratch defect threshold is 10, and the repair quantity threshold is 5. If the image acquisition device captures scratch defects on the surface of 11 produced thermos cups, the scratch defect threshold has been exceeded. The production line should be inspected and the defective thermos cups should be re-produced or retrieved from inventory.

[0036] If the image acquisition device captures scratches on the surfaces of nine thermos cups produced, these nine thermos cups are classified as either minor scratches or severe scratches. Assume that four thermos cups are classified as minor scratches and five are classified as severe scratches. Since the number of thermos cups classified as severe scratches equals the repair threshold, the initial decision is to not repair the defective thermos cups, and the next step is executed.

[0037] The defect definition module is used to divide the thermos cup classified as having severe scratch defects into corresponding areas based on the collected image data after first determining that the defective thermos cup will not be repaired. For example, the thermos cup can be divided into a cup body area and a cup lid area, and the cup body area and the cup lid area can each be divided into two areas. Specifically, the cup body area is divided into a cup front area and a cup back area, and the cup lid area is divided into a cup front area and a cup back area, for a total of four areas. After the areas are divided, the image data is used to check whether the scratches appear in the corresponding areas. The thermos cup classified as having severe scratch defects can be classified as an easy-to-repair thermos cup or a difficult-to-repair thermos cup based on the amount of area occupied by the scratches.

[0038] The specific reason for dividing the areas is that when polishing and repairing scratches on the surface of a thermos bottle, even if there are multiple scratches to repair in the same area, the same repair tools and materials can be used in a centralized manner. There is no need to frequently adjust the position of the thermos bottle or replace the repair tools, so that repairs in more concentrated areas can reduce the difficulty of repair and the time required.

[0039] The specific method for classifying a thermos cup with a serious scratch defect as an easy-to-repair thermos cup or a difficult-to-repair thermos cup is as follows: the number of areas of the thermos cup occupied by the scratch is compared with the easy-to-repair threshold. If the number of areas of the thermos cup occupied by the scratch is less than or equal to the easy-to-repair threshold, the thermos cup is classified as an easy-to-repair thermos cup; if the number of areas of the thermos cup occupied by the scratch is greater than the easy-to-repair threshold, the thermos cup is classified as a difficult-to-repair thermos cup. For example, if the thermos cup is divided into 4 areas and the easy-to-repair threshold is 2, when the scratch only occupies 1 area of ​​the thermos cup, the thermos cup is classified as an easy-to-repair thermos cup, and when the scratch occupies 3 areas of the thermos cup, the thermos cup is classified as a difficult-to-repair thermos cup.

[0040] The result feedback module is used to compare the number of thermos cups classified as difficult to repair with the repair quantity threshold, and make a final judgment feedback based on the comparison result. Specifically, the number of thermos cups classified as difficult to repair is compared with the repair quantity threshold. When the number of thermos cups difficult to repair is less than the repair quantity threshold, it means that most of the scratches on the surface of the thermos cups in this production batch are easy to repair, and a judgment is made to repair the defective thermos cups; and when the number of thermos cups difficult to repair is greater than or equal to the repair quantity threshold, it means that there are many thermos cups in this production batch with scratches on the surface that are difficult to repair. In order to avoid time-consuming repairs and causing delayed delivery of the entire batch of orders, a judgment is made not to repair the defective thermos cups, and they are re-produced or transferred from inventory based on the number of defective thermos cups.

[0041] The specific method for obtaining the repair difficulty index is:

[0042] Obtain the number, length, and depth of scratches on the surface of the thermos cup. The depth data is the maximum depth of the scratches. The calculation method for the repair difficulty index D is as follows:

[0043]

[0044] Among them, N represents the number of scratches on the thermos, Li represents the length of the i-th scratch, Si represents the maximum depth of the i-th scratch, and a, b and c are weight coefficients used to adjust the impact of each factor on the overall repair difficulty.

[0045] As a preferred embodiment, it is possible to assume that there are two scratches on the surface of the thermos cup, with lengths of 20 mm and 25 mm, respectively, and maximum depths of 0.1 mm and 0.2 mm, respectively. Setting a=1, b=0.1, and c=5, then D=1×2+0.1×(20+25)+5×(0.1+0.2), yielding a repair difficulty index of 8 for the thermos cup. Setting the repair difficulty threshold to 10, since the thermos cup's repair difficulty index is less than the repair difficulty threshold, the system classifies the thermos cup as having minor scratches.

[0046] In general, the present invention aims to design an automatic detection and classification system for surface defects of thermos cups based on image recognition, in order to address the current problems of insufficient efficiency in the detection and classification of scratch defects on the surface of thermos cups, and the lack of means to take corresponding measures according to the difficulty of defect repair. The present invention obtains the specific number, length and depth data of scratches on the surface of the thermos cup through image acquisition equipment, and judges whether the scratch defects of the thermos cup are easy to repair based on these data. When it is judged for the first time that it is not easy to repair, the thermos cup in the image data is further divided into regions, and each region represents an area where scratch repair can be concentrated. When the scratches that need to be repaired are concentrated in some areas, the thermos cups classified as serious scratch defects can be dynamically reclassified as easy-to-repair thermos cups, and the system can once again provide feedback on the judgment result of whether the thermos cup needs to be repaired, so that after the thermos cup is produced, it can be repaired based on the severity of the actual scratch defects. The system can quickly feedback reasonable response measures according to the situation. Compared with traditional manual inspection that is time-consuming and easily affected by human factors, this system greatly improves the inspection speed and efficiency through automated image recognition and inspection, making quality control in mass production more efficient. The system can accurately obtain the number, length and depth data of scratches, providing objective data support for subsequent repair decisions. Through this data, the severity of defects and the difficulty of repair can be more accurately assessed. The system can also dynamically adjust the classification of scratches, allowing severe scratches to be reclassified as easily repaired scratches based on the concentration of the area. This flexibility enables the production line to make better further decisions.

[0047] In the embodiments disclosed herein, the processes described above with reference to the flowcharts can be implemented as computer software programs. The embodiments disclosed herein include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for executing the method illustrated in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication component, or alternatively, from removable media. When the computer program is executed by a central processing unit, the functions defined in the methods of this application are performed. It should be noted that the computer-readable medium referred to herein can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. Computer-readable storage media can be, for example, but are not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination thereof. More specific examples of computer-readable storage media can include, but are not limited to, an electrical connection having one or more wire segments, a portable computer disk, a hard disk, random access memory, read-only memory, erasable programmable read-only memory, optical fiber, a portable compact disk read-only memory, an optical storage device, a magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. Furthermore, in this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, electrical, optical, RF, or any suitable combination thereof.

[0048] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, as well as the combination of the boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.

[0049] Those skilled in the art should understand that the above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered by the scope of protection of the present application.

Claims

1. The automatic detection and classification system for vacuum cup surface defects based on image recognition is characterized by: include: A scratch recognition module is used to use an image acquisition device to take high-resolution images of the surface of the thermos cup after production, and in combination with a laser scanning device to identify the number, length, and depth of scratches on the surface of the thermos cup; A defect classification module is used to determine a repair difficulty index based on the number, depth, and length of scratches on the surface of the thermos cup, compare the repair difficulty index with a repair difficulty threshold, and classify the thermos cup as having a minor scratch defect or a severe scratch defect based on the comparison result; a defect definition module, which is used to divide the thermos cup classified as having a severe scratch defect into corresponding areas based on the collected image data, specifically dividing the thermos cup into a cup body area and a cup lid area, and at the same time dividing the cup body area and the cup lid area into two parts, specifically dividing the cup body area into a cup body front area and a cup body back area, and dividing the cup lid area into a cup lid front area and a cup lid back area; The thermos cups classified as having serious scratch defects are classified as easily repairable or difficult to repair based on the amount of area occupied by the scratches. Specifically, the amount of area occupied by the scratches is compared with the easy-to-repair threshold. If the amount of area occupied by the scratches is less than or equal to the easy-to-repair threshold, the thermos cup is classified as easily repairable. If the area of ​​the thermos cup occupied by the scratches is greater than the easy-to-repair threshold, the thermos cup is classified as a difficult-to-repair thermos cup; The result feedback module is used to compare the number of thermos cups classified as difficult to repair with the repair quantity threshold, and make a final judgment feedback based on the comparison result.

2. The automatic detection and classification system for vacuum cup surface defects based on image recognition according to claim 1 is characterized in that: Set a repair quantity threshold. After classifying the thermos cup as having a minor scratch defect or a severe scratch defect, compare the number of thermos cups classified as having a severe scratch defect in this production order with the repair quantity threshold to determine whether to repair the defective thermos cup.

3. The automatic detection and classification system for vacuum cup surface defects based on image recognition according to claim 2 is characterized in that: When the number of thermos cups classified as having severe scratch defects is less than the repair quantity threshold, it means that the number of thermos cups with severe scratches on the surface in this production batch is small, so a judgment is made to repair the defective thermos cups; and when the number of thermos cups classified as having severe scratch defects is greater than or equal to the repair quantity threshold, the first judgment is made not to repair the defective thermos cups.

4. The automatic detection and classification system for vacuum cup surface defects based on image recognition according to claim 1 is characterized in that: The specific method for obtaining the repair difficulty index is to obtain the number, length, and depth data of the scratches on the surface of the thermos cup, and the depth data is the maximum depth of the scratches. The calculation method for obtaining the repair difficulty index D is as follows: Among them, N represents the number of scratches on the thermos, Li represents the length of the i-th scratch, Si represents the maximum depth of the i-th scratch, and a, b and c are weight coefficients used to adjust the impact of each factor on the overall repair difficulty.

5. The automatic detection and classification system for vacuum cup surface defects based on image recognition according to claim 1 is characterized in that: The specific method of judging feedback is: when the number of thermos cups that are difficult to repair is less than the repair quantity threshold, a judgment is made to repair the defective thermos cups; and when the number of thermos cups that are difficult to repair is greater than or equal to the repair quantity threshold, a judgment is made not to repair the defective thermos cups, and they are re-produced or transferred from inventory according to the number of defective thermos cups.

6. The automatic detection and classification system for vacuum cup surface defects based on image recognition according to claim 1 is characterized in that: After the scratch recognition module identifies the number of thermos cups with surface scratches, the total number of thermos cups required for the current production batch is obtained. If the number of thermos cups with surface scratches exceeds the scratch defect threshold, the system directly feedbacks the result that the production line needs to be checked, and re-produces or transfers the same number of thermos cups with scratch defects from inventory to obtain the total number of thermos cups required for the order. When the number of thermos cups with scratches on the surface is identified to be less than the scratch defect threshold, the next step of the defect classification module is executed.

7. The automatic detection and classification system for vacuum cup surface defects based on image recognition according to claim 1 is characterized in that: The specific method for obtaining the scratch quantity, length and depth data on the surface of the thermos cup is: An image acquisition device is used to capture high-resolution images of the surface of the thermos cup after production, and an edge detection algorithm is used to identify the boundaries of scratches on the surface of the thermos cup in the image. After extracting the contours of all scratches on the surface of the thermos cup, the total number of scratches is obtained, and the length of each scratch is measured using the image coordinate system. At the same time, a laser beam is emitted by a laser scanning device to measure the distance to the surface of the thermos cup. By comparing the height difference between the scratch area and the surrounding normal surface, the maximum depth of each scratch is measured.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the automatic detection and classification system for surface defects of thermos cups based on image recognition as described in any one of claims 1 to 7.

Images