Deep learning-based detection result display method and device, and storage medium

Abstract

The invention relates to the technical field of computer vision, and provides a detection result display method based on deep learning, and the method comprises the steps: loading an original image of a target detection product; patterning the defect ratio of the target detection product on the original image of the target detection product; in response to a first input operation of a user on the original image of the target detection product, visually displaying the defect data of the target detection product; in response to a second input operation of the user on the target detection product, screening the target detection product; the screened target detection products are listed according to the one-to-one correspondence mode of the product names and the detection results and then displayed. According to the technical scheme, the detection result can be visually displayed, and effective decision support is provided for a user.

Description

Technical Field

[0001] The present invention relates to the field of computer vision technology, and in particular to a method, device and storage medium for displaying detection results based on deep learning. Background Art

[0002] In industrial production, defect detection is an important part of ensuring product quality. Traditional manual inspection methods are not only inefficient, but also easily affected by human factors, resulting in frequent false detections and missed detections. With the rise of deep learning technology, AI-based defect detection systems have gradually become the focus of industrial attention. However, existing deep learning defect detection systems often focus on defect identification and classification, and are still insufficient for accurate display of defect locations and proportion analysis, making it difficult to meet the needs of fast and accurate detection on production lines. Summary of the invention

[0003] The present application provides a method, device and storage medium for displaying detection results based on deep learning, which can intuitively display the detection results and provide users with effective decision support.

[0004] On the one hand, the present application provides a method for displaying detection results based on deep learning, the method comprising:

[0005] Load the original image of the target detection product;

[0006] Graphically representing the defect ratio of the target detection product on the original image;

[0007] In response to a first input operation of a user on an original image of the target detection product, visually displaying defect data of the target detection product;

[0008] In response to a second input operation of the user on the target detection product, screening the target detection product;

[0009] The screened target detection products are listed and displayed in a one-to-one correspondence between product names and detection results.

[0010] On the other hand, the present application provides a device for displaying detection results based on deep learning, the device comprising:

[0011] Loading module, used to load the original image of the target detection product;

[0012] A first display module is used to graphically display the defect ratio of the target detection product on the original image;

[0013] A second display module, configured to visually display defect data of the target detection product in response to a first input operation of a user on an original image of the target detection product;

[0014] A screening module, configured to screen the target detection products in response to a second input operation of the user on the target detection products;

[0015] The third display module is used to list and display the screened target detection products in a one-to-one correspondence between product names and detection results.

[0016] In a third aspect, the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the technical solution of the method for displaying detection results based on deep learning as described above when executing the computer program.

[0017] In a fourth aspect, the present application provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of the technical solution of the method for displaying detection results based on deep learning as described above.

[0018] From the technical solution provided by the present application, it can be seen that, on the one hand, the defect ratio of the target detection product on the original image is graphically displayed, and the distribution and quantity ratio of various defects are displayed in an intuitive way, which helps users better understand the product quality status and formulate targeted improvement measures accordingly, providing strong data support and decision-making basis for the management; on the other hand, by responding to the user's first input operation on the original image of the target detection product, the defect data of the target detection product is visualized, and the user can accurately locate the problem link in the product design and production process, thereby optimizing resource allocation in a targeted manner and reducing unnecessary waste; on the third aspect, in response to the user's second input operation on the target detection product, the target detection product is screened, so that through in-depth analysis of the screened sample data, the user can dig out potential problems and trends, and provide a scientific basis for decisions such as product optimization and process improvement. In summary, the technical solution of the present application can intuitively display the detection results and provide users with effective decision-making support. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 is a flowchart of a method for displaying detection results based on deep learning provided in an embodiment of the present application;

[0021] Figure 2 It is a schematic diagram provided in an embodiment of the present application for graphically displaying defects of a target detection product on an original image according to dimensions such as type and severity;

[0022] Figure 3 It is a structural schematic diagram of a device for displaying detection results based on deep learning provided in an embodiment of the present application;

[0023] Figure 4 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0025] In this specification, adjectives such as first and second may be used only to distinguish one element or action from another element or action, without necessarily requiring or implying any actual such relationship or order. Where circumstances permit, reference to an element or component or step (etc.) should not be interpreted as being limited to only one of the elements, components, or steps, but may be one or more of the elements, components, or steps, etc.

[0026] In this specification, for the convenience of description, the sizes of various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0027] In industrial production, defect detection is an important part of ensuring product quality. Traditional manual inspection methods are not only inefficient, but also easily affected by human factors, resulting in frequent false detections and missed detections. With the rise of deep learning technology, AI-based defect detection systems have gradually become the focus of industrial attention. However, existing deep learning defect detection systems often focus on defect identification and classification, and are still insufficient for accurate display of defect locations and proportion analysis, making it difficult to meet the needs of fast and accurate detection on production lines.

[0028] In view of the above problems in the prior art, this application proposes a method for displaying detection results based on deep learning, the flow chart of which is shown in the attached figure. Figure 1 As shown, it mainly includes steps S101 to S105, which are described in detail as follows:

[0029] Step S101: Loading the original image of the target detection product.

[0030] In the embodiment of the present application, the target detection product is a product that needs to be detected for defects, and the original image of the target detection product can be loaded into the main interface of the system for display. Since the system supports high-definition display, the original image details of the target detection product loaded into the main interface of the system are clearly visible.

[0031] Step S102: Graphically represent the defect ratio of the target detection product on the original image.

[0032] The system first collects and processes the defect data of all detected target detection products, including key information such as defect type and quantity. Based on the processed data, the system automatically generates a defect ratio graph. Specifically, the defect ratio of the target detection product on the original image can be graphically displayed by introducing a graphical display method, such as a pie chart, a bar chart, or a line chart, etc., to graphically display the defects of the target detection product on the original image according to dimensions such as type and severity. Through the graphical interface, users (for example, project managers and developers, etc.) can observe the proportion and change trend of various defects at a glance, so as to better formulate repair plans and improvement measures. Figure 2 It is a schematic diagram that introduces a pie chart to graphically display the defects of the target detection product on the original image according to the type, severity and other dimensions. For example, each sector area in the pie chart represents a defect type, and the size of the sector represents the proportion of defects of this type.

[0033] Step S103: In response to a first input operation of the user on the original image of the target detection product, the defect data of the target detection product is visually displayed.

[0034] As an embodiment of the present application, in response to a user's first input operation on the original image of the target detection product, visually displaying the defect data of the target detection product can be: in response to the user dragging or zooming the original image of the target detection product, displaying the defect data of different areas of the target detection product. Specifically, when the user drags the original image of the target detection product through a mouse or touch screen to view different areas, or zooms the original image of the target detection product through a scroll wheel or a pinch gesture, the system displays the defect data of different areas of the target detection product so that the user can more accurately locate and analyze defects.

[0035] As another embodiment of the present application, in response to the user's first input operation on the original image of the target detection product, the defect data of the target detection product can also be visualized by: detecting the index input by the user; and displaying the defect data of the part corresponding to the index on the original image of the target detection product to the user. Specifically, the system configures the image index and the corresponding image part (for example, an index of 1 represents the front of the product image). When the user inputs the index corresponding to a part of the target detection product (for example, the front, side, bottom, etc.) that needs to be selected to view, the system displays the defect data of the part corresponding to the index on the original image of the target detection product to the user. It should be noted that the user can quickly switch between the parts of the original image of the target detection product using the keyboard arrow keys, which is convenient for comprehensive analysis of the defects of the target detection product.

[0036] As another embodiment of the present application, in response to the user's first input operation on the original image of the target detection product, the defect data of the target detection product can also be visualized: detecting the user's click on the area where there are defects on the original image of the target detection product; in response to the user's click on the area where there are defects on the original image of the target detection product, the relevant information of the defects on the clicked area is displayed to the user. Specifically, when the user clicks on the defective area in the original image of the target detection product, the system will pop up a detailed information window of the defect in the area on the interface, including the defect name, center coordinates (X, Y), length, width, area, circumscribed rectangle and other parameters. This information helps users quickly understand the specific situation and severity of the defects of the target detection product.

[0037] Step S104: In response to the user's second input operation on the target detection product, the target detection products are screened.

[0038] As an embodiment of the present application, in response to the user's second input operation on the target detection product, the target detection product can be screened by: detecting the query condition input by the user; in response to the query condition input by the user, the target detection product and its test result that meet the query condition are screened and returned. In the above embodiment, the query condition includes a time period, a test result or a test time, and the query condition includes a time period, a test result or a test time. Specifically, the user can select a specific time period input to query the test data of all products detected in the time period; the system supports the selection of date ranges and time queries accurate to seconds. For another example, the user can filter the test data of the product according to the test results (for example, qualified, unqualified, pending review, etc.); the system provides a drop-down list for the user to select the corresponding test result option. For another example, if the user wants to know which products are detected at which test time, the user can enter the test time, that is, the specific time when the product is detected by the system to filter the target detection product and its test results and other data, which helps the user understand the detection of products in different time periods. The system returns the target detection products and their test results that meet these query conditions to the user.

[0039] As another embodiment of the present application, in response to the user's second input operation on the target detection product, the target detection products can also be screened by: detecting the product name input by the user; performing fuzzy matching on the product name input by the user; if the fuzzy matching is successful, returning the successfully matched target detection product name and its detection result. Specifically, the user can enter a keyword or fuzzy string of the product name in the search box, and the system will automatically filter out the product name containing the keyword and its detection results and display them in a list, that is, by constructing an SQL query statement containing a LIKE operator in the back end, passing the search term entered by the user (possibly with leading and trailing wildcards %) as a parameter to the query, and returning the matching data set to the front end for display, while using parameterized queries to prevent SQL injection attacks, and considering index optimization to improve query performance.

[0040] Step S105: List and display the screened target detection products in a one-to-one correspondence between product names and detection results.

[0041] After the screening is completed, the screened target detection products are listed and displayed in a one-to-one correspondence between product name and detection result. At this time, the user can view the detailed information of the product (including image, defect information, etc.) by clicking the product name in the list. At the same time, the system supports sorting and exporting the query results to meet the different needs of users.

[0042] From the above attached Figure 1From the example of the display method of the detection results based on deep learning, it can be seen that, on the one hand, the defect ratio of the target detection product on the original image is graphically displayed, and the distribution and quantity ratio of various defects are displayed in an intuitive way, which helps users better understand the product quality status and formulate targeted improvement measures accordingly, providing strong data support and decision-making basis for the management; on the other hand, by responding to the user's first input operation on the original image of the target detection product, the defect data of the target detection product is visualized, and the user can accurately locate the problem link in the product design and production process, thereby optimizing resource allocation in a targeted manner and reducing unnecessary waste; on the third aspect, in response to the user's second input operation on the target detection product, the target detection product is screened, so that through in-depth analysis of the screened sample data, the user can dig out potential problems and trends, and provide a scientific basis for decisions such as product optimization and process improvement. In summary, the technical solution of the present application can intuitively display the detection results and provide users with effective decision-making support.

[0043] Please see attached Figure 3 , is a display device for detection results based on deep learning provided in an embodiment of the present application, the device may include a loading module 301, a first display module 302, a second display module 303, a screening module 304 and a third display module 305, which are described in detail as follows:

[0044] A loading module 301 is used to load the original image of the target detection product;

[0045] The first display module 302 is used to graphically display the defect ratio of the target detection product on the original image of the target detection product;

[0046] The second display module 303 is used to visually display the defect data of the target detection product in response to the user's first input operation on the original image of the target detection product;

[0047] A screening module 304, configured to screen the target detection products in response to a second input operation of the user on the target detection products;

[0048] The third display module 305 is used to list and display the screened target detection products in a one-to-one correspondence between product names and detection results.

[0049] From the above attached Figure 3It can be seen from the display device of the detection results based on deep learning that, on the one hand, the defect ratio of the target detection product on the original image is graphically displayed, and the distribution and quantity ratio of various defects are displayed in an intuitive way, which helps users better understand the product quality status and formulate targeted improvement measures accordingly, providing strong data support and decision-making basis for the management; on the other hand, by responding to the user's first input operation on the original image of the target detection product, the defect data of the target detection product is visualized, and the user can accurately locate the problem link in the product design and production process, thereby optimizing resource allocation in a targeted manner and reducing unnecessary waste; on the third aspect, in response to the user's second input operation on the target detection product, the target detection product is screened, so that through in-depth analysis of the screened sample data, the user can dig out potential problems and trends, and provide a scientific basis for decisions such as product optimization and process improvement. In summary, the technical solution of the present application can intuitively display the detection results and provide users with effective decision-making support.

[0050] Figure 4 Schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 4 As shown, the electronic device 4 of this embodiment mainly includes: a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40, such as a program for a method for displaying detection results based on deep learning. When the processor 40 executes the computer program 42, the steps in the above-mentioned method for displaying detection results based on deep learning are implemented, such as Figure 1 Alternatively, when the processor 40 executes the computer program 42, the functions of each module / unit in the above-mentioned device embodiments are realized, for example Figure 3 The functions of the loading module 301 , the first display module 302 , the second display module 303 , the screening module 304 and the third display module 305 are shown.

[0051] Exemplarily, the computer program 42 of the method for displaying the detection results based on deep learning mainly includes: loading the original image of the target detection product; graphically displaying the defect ratio of the target detection product on the original image of the target detection product; visually displaying the defect data of the target detection product in response to the user's first input operation on the original image of the target detection product; screening the target detection product in response to the user's second input operation on the target detection product; and displaying the screened target detection products in a list in a one-to-one correspondence between the product name and the detection result. The computer program 42 can be divided into one or more modules / units, one or more modules / units are stored in the memory 41, and are executed by the processor 40 to complete the present application. One or more modules / units can be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program 42 in the electronic device 4. For example, the computer program 42 can be divided into the functions of a loading module 301, a first display module 302, a second display module 303, a screening module 304 and a third display module 305 (modules in the virtual device), and the specific functions of each module are as follows: a loading module 301 is used to load the original image of the target detection product; the first display module 302 is used to graph the defect ratio of the target detection product on the original image of the target detection product; the second display module 303 is used to visualize the defect data of the target detection product in response to the user's first input operation on the original image of the target detection product; the screening module 304 is used to screen the target detection products in response to the user's second input operation on the target detection product; the third display module 305 is used to list and display the screened target detection products in a one-to-one correspondence between the product name and the detection result.

[0052] The electronic device 4 may include but is not limited to a processor 40 and a memory 41. Those skilled in the art will appreciate that Figure 4 It is only an example of the electronic device 4 and does not constitute a limitation of the electronic device 4. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0053] The processor 40 may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0054] The memory 41 may be an internal storage unit of the electronic device 4, such as a hard disk or memory of the electronic device 4. The memory 41 may also be an external storage device of the electronic device 4, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 4. Further, the memory 41 may also include both an internal storage unit and an external storage device of the electronic device 4. The memory 41 is used to store computer programs and other programs and data required by the electronic device. The memory 41 may also be used to temporarily store data that has been output or is to be output.

[0055] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned device can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0056] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0057] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0058] In the embodiments provided in the present application, it should be understood that the disclosed devices / equipment and methods can be implemented in other ways. For example, the device / equipment embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0059] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0060] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0061] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program of the method for displaying the detection results based on deep learning can be stored in a storage medium. When the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented, that is, loading the original image of the target detection product; graphically displaying the defect ratio of the target detection product on the original image of the target detection product; in response to the user's first input operation on the original image of the target detection product, visually displaying the defect data of the target detection product; in response to the user's second input operation on the target detection product, screening the target detection product; and displaying the screened target detection products in a one-to-one correspondence between the product name and the detection result. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. Storage media may include: any entity or device capable of carrying computer program code, recording media, USB flash drives, mobile hard disks, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content contained in the storage medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, storage media do not include electric carrier signals and telecommunication signals.

[0062] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application is described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some of the technical features therein by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application. The specific implementation methods described above further describe the purpose, technical solutions and beneficial effects of the present application in detail. It should be understood that the above description is only the specific implementation method of the present application, and is not used to limit the protection scope of the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present invention.

Claims

1. A method for displaying detection results based on deep learning, characterized in that: The method comprises: Load the original image of the target detection product; Graphically representing the defect ratio of the target detection product on the original image; In response to a first input operation of a user on an original image of the target detection product, visually displaying defect data of the target detection product; In response to a second input operation of the user on the target detection product, screening the target detection product; The screened target detection products are listed and displayed in a one-to-one correspondence between product names and detection results.

2. The method for displaying detection results based on deep learning as claimed in claim 1, characterized in that: The step of visually displaying defect data of the target detection product in response to a first input operation of the user on the original image of the target detection product comprises: In response to the user dragging or zooming the original image of the target inspection product, defect data of different areas of the target inspection product are displayed.

3. The method for displaying detection results based on deep learning as claimed in claim 1, characterized in that: The step of visually displaying defect data of the target detection product in response to a first input operation of the user on the original image of the target detection product comprises: Detecting the index input by the user; The defect data of the part corresponding to the index on the original image of the target detection product is displayed to the user.

4. The method for displaying detection results based on deep learning as claimed in claim 1, characterized in that: The step of visually displaying defect data of the target detection product in response to a first input operation of the user on the original image of the target detection product comprises: Detecting a click by the user on a defective area on the original image of the target detection product; In response to the user clicking on a region with defects on the original image of the target inspection product, relevant information about the defects in the region is displayed to the user.

5. The method for displaying detection results based on deep learning as claimed in claim 1, characterized in that: The step of screening the target detection products in response to the user's second input operation on the target detection products comprises: Detecting the query condition input by the user; In response to the query conditions input by the user, target detection products and their detection results that meet the query conditions are screened and returned.

6. The method for displaying detection results based on deep learning as claimed in claim 5, characterized in that: The query conditions include time period, test result or test time.

7. The method for displaying detection results based on deep learning as claimed in claim 1, characterized in that: The step of screening the target detection products in response to the user's second input operation on the target detection products comprises: Detecting the product name input by the user; Performing fuzzy matching on the product name input by the user; If the fuzzy match is successful, the name of the successfully matched target detection product and its detection result are returned.

8. A display device for detection results based on deep learning, characterized in that: The device comprises: Loading module, used to load the original image of the target detection product; A first display module is used to graphically display the defect ratio of the target detection product on the original image; A second display module, configured to visually display defect data of the target detection product in response to a first input operation of a user on an original image of the target detection product; A screening module, configured to screen the target detection products in response to a second input operation of the user on the target detection products; The third display module is used to list and display the screened target detection products in a one-to-one correspondence between product names and detection results.

9. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images