A method, system and platform for extracting uneven brightness defects based on multi-region images

Abstract

The present invention belongs to the field of defect detection technology, and specifically relates to a defect extraction method, system and platform based on uneven brightness of multi-region images. By acquiring the brightness data of the middle area of ​​the coating surface in real time, and using the brightness data as the reference brightness data; acquiring the background brightness data of the coating surface area, and combining the reference brightness data, generating the coating surface area defect extraction threshold in real time; according to the area defect extraction threshold, extracting the coating surface defect area in real time, and merging the extracted coating surface defect area and the system and platform corresponding to the method in real time; it can achieve uneven brightness on the left and right sides of the image due to lighting problems, avoid extraction errors during defect extraction, resulting in misjudgment and missed judgment, and avoid the problem of lighting angle, where the brightness of the right side of the coating area is severely reduced, and defects cannot be extracted through the global threshold, and the use of local thresholds will lead to a sharp increase in detection time.

Description

Technical Field

[0001] The present invention belongs to the technical field of defect detection, and specifically relates to a method, system and platform for extracting defects based on uneven brightness of multi-region images. Background Art

[0002] Currently, in the line scan camera defect detection system, the brightness of the left and right images is uneven due to lighting problems, which leads to extraction errors during defect extraction and causes misjudgment and missed judgment.

[0003] like Figure 1 As shown in the figure, the ideal lighting effect is that the brightness on the left and right sides is consistent, and the brightness distribution curve is a horizontal line. However, due to the lighting angle problem, the brightness of the right area of ​​the coating is severely reduced, and defects cannot be extracted using the global threshold. Using a local threshold will lead to a sharp increase in detection time. Only edges can be extracted, and bright and dark defects cannot be extracted simultaneously, which cannot meet the needs of online detection. The existing algorithm library cannot effectively deal with this problem.

[0004] Therefore, in view of the above-mentioned technical problems that cause uneven brightness on the left and right sides of the image due to lighting problems, extraction errors occur during defect extraction, resulting in misjudgment and missed judgments, and due to lighting angle problems, the brightness of the right side of the coating area is severely reduced, and defects cannot be extracted through the global threshold. Using local thresholds will lead to a sharp increase in detection time, and only edges can be extracted. Bright and dark defects cannot be extracted at the same time, and it cannot adapt to online detection needs; the existing algorithm library cannot be effectively used. There is an urgent need to design and develop a method, system and platform for defect extraction based on uneven brightness of multi-region images. Summary of the Invention

[0005] In order to overcome the shortcomings and difficulties of the above-mentioned prior art, the purpose of the present invention is to provide a method, system and platform for extracting defects based on uneven brightness of multi-region images, so as to realize the uneven brightness of the left and right sides of the image caused by lighting problems, avoid extraction errors during defect extraction, resulting in misjudgment and missed judgment, and avoid problems due to lighting angles.

[0006] The first object of the present invention is to provide a method for extracting uneven brightness defects based on multi-region images;

[0007] The second object of the present invention is to provide a system for extracting uneven brightness defects based on multi-region images;

[0008] The third object of the present invention is to provide a platform for extracting uneven brightness defects based on multi-region images;

[0009] The first object of the present invention is achieved in this way: the method specifically comprises the following steps:

[0010] Acquire brightness data of the middle area of ​​the coating surface in real time, and use the brightness data as reference brightness data;

[0011] Obtaining background brightness data of the coating surface area, and combining it with the reference brightness data to generate a coating surface area defect extraction threshold in real time;

[0012] According to the regional defect extraction threshold, the coating surface defect area is extracted in real time, and the coating surface defect area is merged in real time. Furthermore, the brightness data of the middle area of ​​the coating surface is obtained in real time, and the brightness data is used as the reference brightness data, which also includes the following steps:

[0013] Set the baseline threshold for extracting defects.

[0014] Furthermore, the step of obtaining background brightness data of the coating surface area and combining it with the reference brightness data to generate a coating surface area defect extraction threshold in real time also includes the following steps:

[0015] Dividing the coating surface area into at least one longitudinal area in a transverse direction;

[0016] Obtain background brightness data of each vertical area in real time.

[0017] Furthermore, the step of obtaining background brightness data of the coating surface area and combining it with the reference brightness data to generate a coating surface area defect extraction threshold in real time also includes the following steps:

[0018] Based on the background brightness data and the reference brightness data, the defect extraction threshold of each area is calculated and generated in real time.

[0019] Furthermore, the calculation formula for the defect extraction threshold of each area is specifically as follows:

[0020] G i =B i / B base *G base (1)

[0021] Among them, B i is the background brightness data of each area; B base is the benchmark brightness data; G base To set the baseline threshold for extracting defects.

[0022] Furthermore, after extracting the coating surface defect region in real time according to the regional defect extraction threshold and merging the extracted coating surface defect region in real time, the step further includes the following steps:

[0023] Determine in real time whether there are any misjudgments in the extracted defect area, and verify the merged coating surface defect area.

[0024] The second object of the present invention is achieved in that the system specifically comprises:

[0025] an acquisition unit, configured to acquire brightness data of a middle area of ​​a coating surface layer in real time, and use the brightness data as reference brightness data;

[0026] An acquisition and generation unit is used to acquire background brightness data of the coating surface area, and generate a coating surface area defect extraction threshold in real time in combination with the reference brightness data;

[0027] The extraction and merging unit is used to extract the coating surface defect area in real time according to the regional defect extraction threshold, and merge the extracted coating surface defect area in real time.

[0028] Furthermore, the system is provided with:

[0029] The determination and detection unit is used to determine in real time whether there is any misjudgment in the extracted defect area and to verify the merged coating surface defect area.

[0030] Furthermore, the acquisition unit is further provided with: a setting module for setting a reference threshold for extracting defects;

[0031] The acquisition and generation unit is further provided with: a region separation module for dividing the coating surface region into at least one longitudinal region in a transverse direction;

[0032] A first acquisition module is used to acquire background brightness data of each longitudinal area in real time;

[0033] The first generating module is used to calculate and generate the defect extraction threshold of each area in real time according to the background brightness data and the reference brightness data.

[0034] The third object of the present invention is achieved as follows: comprising: a processor, a memory, and a control program for a platform for extracting defects based on uneven brightness of multi-region images;

[0035] The processor executes the control program for the platform for extracting defects based on uneven brightness of multi-region images, and the control program for the platform for extracting defects based on uneven brightness of multi-region images is stored in the memory. The control program for the platform for extracting defects based on uneven brightness of multi-region images implements the steps of the method for extracting defects based on uneven brightness of multi-region images.

[0036] The present invention obtains brightness data of the middle area of ​​the coating surface in real time through a method, and uses the brightness data as reference brightness data; obtains background brightness data of the coating surface area, and generates a coating surface area defect extraction threshold in real time in combination with the reference brightness data; according to the area defect extraction threshold, the coating surface defect area is extracted in real time, and the extracted coating surface defect area is merged in real time, as well as a system and platform corresponding to the method; the above scheme can not only effectively extract defects but also meet the time-consuming algorithm of online real-time detection, and can achieve uneven brightness on the left and right sides of the image due to lighting problems, avoid extraction errors during defect extraction, resulting in misjudgment and missed judgment, and avoid the serious reduction in brightness of the right side of the coating due to lighting angle problems, which makes it impossible to extract defects through the global threshold, and the use of local thresholds / local thresholds will cause the detection time to increase sharply, and only edges can be extracted; this scheme can extract bright and dark defects at the same time, and can adapt to online detection needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0038] Figure 1 This is a schematic diagram showing that uneven brightness on the left and right sides of an image due to lighting problems in the prior art leads to extraction errors during defect extraction, resulting in misjudgment and missed judgments.

[0039] Figure 2 A schematic flow chart of a method for extracting uneven brightness defects based on multi-region images according to the present invention;

[0040] Figure 3 Schematic diagram of a method for extracting uneven brightness defects in multi-region images according to the present invention, wherein the method is divided horizontally into n longitudinal regions;

[0041] Figure 4 This is a schematic diagram of a method for extracting uneven brightness defects in a multi-region image when n=1, in which all the darker areas on the right are misjudged;

[0042] Figure 5 A schematic diagram of a method for extracting defects based on uneven brightness of multi-region images according to the present invention, which can effectively extract defects when n=10 and simultaneously detect darker areas without misjudging them;

[0043] Figure 6 This is a schematic diagram of the architecture of a system for extracting uneven brightness defects in multi-region images according to the present invention;

[0044] Figure 7This is a schematic diagram of the architecture of a platform for extracting uneven brightness defects in multi-region images according to the present invention;

[0045] Figure 8 A schematic diagram of a computer-readable storage medium architecture in one embodiment of the present invention;

[0046] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0047] In order to better understand the purpose, technical solutions and advantages of the present invention, the present invention is further described below with reference to the accompanying drawings and specific embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification.

[0048] The present invention may also be implemented or applied through other different specific examples, and the details in this specification may also be modified and changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention.

[0049] It should be noted that if the embodiments of the present invention involve directional indications (such as up, down, left, right, front, back, etc.), the directional indications are only used to explain the relative position relationship, movement status, etc. between the various components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indications will also change accordingly.

[0050] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of such features. Secondly, the technical solutions between the various embodiments can be combined with each other, but this must be based on the fact that ordinary technicians in this field can implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0051] Preferably, the method for extracting uneven brightness defects based on multi-region images of the present invention is applied to one or more terminals or servers. The terminal is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to a microprocessor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital signal processor (DSP), an embedded device, etc.

[0052] The terminal can be a computing device such as a desktop computer, notebook, PDA, cloud server, etc. The terminal can interact with the client through a keyboard, mouse, remote control, touchpad, or voice control device.

[0053] The present invention provides a method, system, platform and storage medium for extracting defects based on uneven brightness of multi-region images.

[0054] like Figure 2 , which is a flow chart of a method for extracting uneven brightness defects based on multi-region images provided by an embodiment of the present invention.

[0055] In this embodiment, the method for extracting defects based on uneven brightness of multi-region images can be applied to terminals with display functions or fixed terminals. The terminals are not limited to personal computers, smart phones, tablet computers, desktop computers or all-in-one computers equipped with cameras, etc.

[0056] The multi-region image brightness unevenness defect extraction method can also be applied to a hardware environment consisting of a terminal and a server connected to the terminal via a network. The network includes, but is not limited to, a wide area network, a metropolitan area network, or a local area network. The multi-region image brightness unevenness defect extraction method of this embodiment of the present invention can be executed by a server, a terminal, or both.

[0057] For example, for a terminal that needs to perform multi-region image brightness unevenness defect extraction, the multi-region image brightness unevenness defect extraction function provided by the method of the present invention can be directly integrated on the terminal, or a client for implementing the method of the present invention can be installed. For another example, the method provided by the present invention can also be run on a server or other device in the form of a software development kit (SDK), and an interface for the multi-region image brightness unevenness defect extraction function is provided in the form of the SDK. The terminal or other device can implement the multi-region image brightness unevenness defect extraction function through the provided interface.

[0058] The present invention will be further described below with reference to the accompanying drawings.

[0059] like Figure 2-5 As shown, the present invention provides a method for extracting uneven brightness defects based on multi-region images, and the method specifically includes the following steps:

[0060] S1. Acquire brightness data of the middle area of ​​the coating surface in real time, and use the brightness data as reference brightness data;

[0061] S2. Obtain background brightness data of the coating surface area, and generate a coating surface area defect extraction threshold in real time based on the reference brightness data;

[0062] S3. Extracting coating surface defect regions in real time according to the regional defect extraction threshold, and merging the extracted coating surface defect regions in real time.

[0063] The method of acquiring brightness data of the middle area of ​​the coating surface layer in real time and using the brightness data as the reference brightness data further includes the following steps:

[0064] S11. Setting a baseline threshold for defect extraction.

[0065] The step of obtaining background brightness data of the coating surface area and combining it with the reference brightness data to generate a coating surface area defect extraction threshold in real time also includes the following steps:

[0066] S21, separating the surface area of ​​the coating into at least one longitudinal area in a transverse direction;

[0067] S22. Acquire background brightness data of each longitudinal area in real time.

[0068] The step of obtaining background brightness data of the coating surface area and combining it with the reference brightness data to generate a coating surface area defect extraction threshold in real time also includes the following steps:

[0069] S23. Calculate and generate defect extraction thresholds for each region in real time based on the background brightness data and the reference brightness data.

[0070] The calculation formula of the defect extraction threshold of each area is specifically as follows:

[0071] G i =B i / B base *G base (1)

[0072] Among them, B i is the background brightness data of each area; B baseis the benchmark brightness data; G base To set the baseline threshold for extracting defects.

[0073] After extracting the coating surface defect regions in real time according to the regional defect extraction threshold and merging the extracted coating surface defect regions in real time, the step further includes the following steps:

[0074] S4. Determine in real time whether there is any misjudgment in the extracted defect area, and verify the merged coating surface defect area.

[0075] Specifically, in the embodiment of the present invention, for the reference brightness: the brightness of the middle area is taken as the reference brightness B base , set the baseline threshold G for extracting defects base ; The reference brightness value can be freely set by the user to optimize the detection effect.

[0076] like Figure 3 The partition shown is: horizontal division into n longitudinal regions (the vertical brightness of the line scan camera is uniform) to obtain the background brightness B of each region i , that is, the peak value on the grayscale histogram; the defect extraction threshold of each area is calculated based on the background brightness and the reference brightness, and is dynamically adjusted according to the changes in the background.

[0077] Calculation formula: Defect extraction threshold for each area:

[0078] G i =B i / B base *G base (1)

[0079] Defect extraction: Increase the segmentation area n, the more accurate the background brightness, the better the defect extraction effect (no significant increase in time consumption), after extracting the defect area in each area, merge the defect areas of all areas to complete the defect extraction. Figure 4-5 As shown in the figure, when n=1, all the darker areas on the right are misjudged, while when n=10, defects can be effectively extracted and no darker areas are misjudged.

[0080] Specifically, after partitioning and extracting abnormal areas, morphological image processing is used to connect and merge similar areas into a large area, and the image of the merged area is captured. The background brightness and defect characteristics are calculated, and the defect detection algorithm is used to determine whether there is a defect, and the classification algorithm is used to determine the defect type.

[0081] To achieve the above objectives, the present invention also provides a system for extracting uneven brightness defects based on multi-region images, such as Figure 6 As shown, the system specifically includes:

[0082] an acquisition unit, configured to acquire brightness data of a middle area of ​​a coating surface layer in real time, and use the brightness data as reference brightness data;

[0083] An acquisition and generation unit is used to acquire background brightness data of the coating surface area, and generate a coating surface area defect extraction threshold in real time in combination with the reference brightness data;

[0084] The extraction and merging unit is used to extract the coating surface defect area in real time according to the regional defect extraction threshold, and merge the extracted coating surface defect area in real time.

[0085] The system is also provided with:

[0086] The determination and detection unit is used to determine in real time whether there is any misjudgment in the extracted defect area and to verify the merged coating surface defect area.

[0087] The acquisition unit is further provided with: a setting module for setting a reference threshold for extracting defects;

[0088] The acquisition and generation unit is further provided with: a region separation module for dividing the coating surface region into at least one longitudinal region in a transverse direction;

[0089] A first acquisition module is used to acquire background brightness data of each longitudinal area in real time;

[0090] The first generating module is used to calculate and generate the defect extraction threshold of each area in real time according to the background brightness data and the reference brightness data.

[0091] In the embodiment of the system solution of the present invention, the method steps involved in the extraction of uneven brightness defects in multi-region images have been described above in detail and will not be repeated here.

[0092] To achieve the above objectives, the present invention also provides a platform for extracting uneven brightness defects based on multi-region images, such as Figure 7 As shown, it includes: a processor, a memory and a control program for a platform for extracting uneven brightness defects based on multi-region images;

[0093] The processor executes the control program for the platform for extracting defects based on uneven brightness of multi-region images, which is stored in the memory. The control program for the platform for extracting defects based on uneven brightness of multi-region images implements the steps of the method for extracting defects based on uneven brightness of multi-region images, for example:

[0094] S1. Acquire brightness data of the middle area of ​​the coating surface in real time, and use the brightness data as reference brightness data;

[0095] S2. Obtain background brightness data of the coating surface area, and generate a coating surface area defect extraction threshold in real time based on the reference brightness data;

[0096] S3. Extracting coating surface defect regions in real time according to the regional defect extraction threshold, and merging the extracted coating surface defect regions in real time.

[0097] The specific details of the steps have been explained above and will not be repeated here.

[0098] In an embodiment of the present invention, the built-in processor of the platform for extracting uneven brightness defects from multi-region images can be composed of an integrated circuit, such as a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including a combination of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor utilizes various interfaces and circuits to connect various components, and executes or executes programs or units stored in the memory, as well as calls data stored in the memory, to perform various functions and process data based on the extraction of uneven brightness defects from multi-region images.

[0099] The memory is used to store program codes and various data. It is installed in the multi-region image brightness uneven defect extraction platform and realizes high-speed and automatic access to programs or data during operation.

[0100] The memory includes read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electronically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0101] To achieve the above object, the present invention also provides a computer readable storage medium, such as Figure 8 As shown, the computer-readable storage medium stores a control program for a platform for extracting defects based on uneven brightness of multi-region images. The control program for extracting defects based on uneven brightness of multi-region images implements the steps of the method for extracting defects based on uneven brightness of multi-region images, for example:

[0102] S1. Acquire brightness data of the middle area of ​​the coating surface in real time, and use the brightness data as reference brightness data;

[0103] S2. Obtain background brightness data of the coating surface area, and generate a coating surface area defect extraction threshold in real time based on the reference brightness data;

[0104] S3. Extracting coating surface defect regions in real time according to the regional defect extraction threshold, and merging the extracted coating surface defect regions in real time.

[0105] The specific details of the steps have been explained above and will not be repeated here.

[0106] In the description of the embodiments of the present invention, it should be noted that any process or method description in the flowchart or otherwise described herein can be understood as representing a module, fragment or portion of code that includes one or more executable instructions for implementing specific logical functions or steps of the process, and the scope of the preferred embodiments of the present invention includes additional implementations, in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present invention belong.

[0107] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processing module, or other system that can fetch instructions from and execute instructions on an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection having one or more wires (electronic devices), a portable computer disk cartridge (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM).

[0108] Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing it in another suitable manner if necessary, and then storing it in a computer memory.

[0109] In an embodiment of the present invention, to achieve the above-mentioned purpose, the present invention further provides a chip system, wherein the chip system includes at least one processor. When program instructions are executed in the at least one processor, the chip system performs the steps of the method for extracting brightness unevenness defects based on multi-region images, for example:

[0110] S1. Acquire brightness data of the middle area of ​​the coating surface in real time, and use the brightness data as reference brightness data;

[0111] S2. Obtain background brightness data of the coating surface area, and generate a coating surface area defect extraction threshold in real time based on the reference brightness data;

[0112] S3. Extracting coating surface defect regions in real time according to the regional defect extraction threshold, and merging the extracted coating surface defect regions in real time.

[0113] The specific details of the steps have been explained above and will not be repeated here.

[0114] Those skilled 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. Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0115] The present invention obtains brightness data of the middle area of ​​the coating surface in real time through a method, and uses the brightness data as reference brightness data; obtains background brightness data of the coating surface area, and generates a coating surface area defect extraction threshold in real time in combination with the reference brightness data; according to the area defect extraction threshold, the coating surface defect area is extracted in real time, and the extracted coating surface defect area is merged in real time, as well as a system and platform corresponding to the method; the above scheme can not only effectively extract defects but also meet the time-consuming algorithm of online real-time detection, and can achieve uneven brightness on the left and right sides of the image due to lighting problems, avoid extraction errors during defect extraction, resulting in misjudgment and missed judgment, and avoid the serious reduction in brightness of the right side of the coating due to lighting angle problems, which makes it impossible to extract defects through the global threshold, and the use of local thresholds / local thresholds will cause the detection time to increase sharply, and only edges can be extracted; this scheme can extract bright and dark defects at the same time, and can adapt to online detection needs.

[0116] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A method for extracting uneven brightness defects based on multi-region images, characterized in that The method specifically comprises the following steps: Acquire brightness data of the middle area of ​​the coating surface in real time, and use the brightness data as reference brightness data; including setting a reference threshold for extracting defects; Obtaining background brightness data of the coating surface area, and combining it with the reference brightness data to generate a defect extraction threshold for the coating surface area in real time; wherein the method includes dividing the coating surface area into at least one longitudinal area in a horizontal direction; obtaining background brightness data of each longitudinal area in real time; and calculating and generating a defect extraction threshold for each area in real time based on the background brightness data and the reference brightness data; The calculation formula of the defect extraction threshold of each area is specifically as follows: G i = B i / B base * G base (1) Among them, B i is the background brightness data of each area; B base is the benchmark brightness data; G base To set the baseline threshold for extracting defects; Extracting coating surface defect regions in real time according to a regional defect extraction threshold, and merging the extracted coating surface defect regions in real time; Determine in real time whether there are any misjudgments in the extracted defective areas, and verify the merged coating surface defective areas; including: after partitioning and extracting abnormal areas, use morphological image processing to connect and merge similar areas into a large area, and intercept the merged area image, calculate the background brightness and defect characteristics, determine whether there are defects through the defect detection algorithm, and then use the classification algorithm to determine the defect type.

2. A system for extracting uneven brightness defects based on multi-region images, characterized in that: The system is applied to the method for extracting defects based on uneven brightness of multi-region images as claimed in claim 1; The system specifically includes: an acquisition unit, configured to acquire brightness data of a middle area of ​​a coating surface layer in real time, and use the brightness data as reference brightness data; An acquisition and generation unit is used to acquire background brightness data of the coating surface area, and generate a coating surface area defect extraction threshold in real time in combination with the reference brightness data; The extraction and merging unit is used to extract the coating surface defect area in real time according to the regional defect extraction threshold, and merge the extracted coating surface defect area in real time.

3. The system for extracting uneven brightness defects based on multi-region images according to claim 2 is characterized in that The system is further provided with: The determination and detection unit is used to determine in real time whether there is any misjudgment in the extracted defect area and to verify the merged coating surface defect area.

4. The system for extracting uneven brightness defects based on multi-region images according to claim 2 is characterized in that The acquisition unit is further provided with: A setting module is used to set a baseline threshold for extracting defects; The acquisition generation unit is further provided with: A region separation module, used for separating the coating surface region into at least one longitudinal region in a transverse direction; A first acquisition module is used to acquire background brightness data of each longitudinal area in real time; The first generation module is used to calculate and generate the defect extraction threshold of each area in real time according to the background brightness data and the reference brightness data.

5. A platform for extracting uneven brightness defects based on multi-region images, characterized in that: include: Processor, memory, and control program for a platform for extracting uneven brightness defects from multi-region images; Wherein the processor executes the control program of the platform for extracting defects based on uneven brightness of multi-region images, the control program of the platform for extracting defects based on uneven brightness of multi-region images is stored in the memory, and the control program of the platform for extracting defects based on uneven brightness of multi-region images implements the steps of the method for extracting defects based on uneven brightness of multi-region images as claimed in claim 1.

Images