WO2018176370A1 - Visual inspection system and method - Google Patents

Abstract

Disclosed are a visual inspection system and method. The method comprises: acquiring a first inspection image (21, 31) and a second inspection image (22, 32) of an object to be inspected (14) under different illumination conditions and/or photographing conditions (S11); and carrying out mathematical operations on luminance values of corresponding positions on the first inspection image (21, 31) and the second inspection image (22, 32) and then distinguishing a target to be inspected and interference on the object to be inspected (14) (S12). A target to be inspected and interference are effectively distinguished by using the synthesis of two inspection images acquired under different illumination conditions and/or photographing conditions.

Description

Visual inspection system and method

[Technical Field]

Embodiments of the present invention relate to the field of visual inspection, and in particular, to a visual inspection system and method.

 【Background technique】

Industrial visual inspection generally performs image acquisition by the object to be detected, and performs image recognition on the acquired image, and identifies predetermined targets such as scratches, cracks, and the like from the image of the object to be detected. At present, there are two problems in the industrial visual inspection process: one is that the surface of the object to be inspected is easy to deposit dust, and the object to be detected is often susceptible to dust, so it needs to be tested in a dust-free environment, which increases the cost of detection; It is the object to be inspected that usually contains multiple defects, and it is difficult to effectively distinguish different defects.

 [Summary of the Invention]

In order to at least partially solve the above problems, an embodiment of the present invention provides a visual detection method, which includes: acquiring a first detection image and a second detection image of an object to be detected under different illumination conditions and/or shooting conditions; The brightness values of the corresponding positions of the first detection image and the second detection image are mathematically operated to distinguish the object to be detected and the interference on the object to be detected.

The step of acquiring the first detection image and the second detection image of the object to be detected under different illumination conditions and/or shooting conditions includes: setting different illumination conditions and/or shooting conditions according to the reflection characteristics of the object to be detected and the interference. In addition, there is a certain difference in the brightness values of the target to be detected and the interference after the mathematical operation.

The step of acquiring the first detection image and the second detection image of the object to be detected under different illumination conditions and/or shooting conditions includes: setting different illumination conditions and/or shooting conditions according to the reflection characteristics of the object to be detected and the interference. And further enabling distinguishing between the first detection image and the second detection image on the one of the first detection image and the second detection image according to the brightness value. One can distinguish the interference from the target to be detected and other areas of the object to be detected according to the brightness value.

The step of performing mathematical operations on the luminance values of the corresponding positions of the first detection image and the second detection image to further distinguish the target to be detected and the interference on the object to be detected includes: using a preset threshold segmentation condition and a logical operation The luminance values of the corresponding positions of the first detection image and the second detection image are processed to further distinguish the target to be detected and the interference.

Wherein the interference includes dust, the object to be detected includes at least one of a scratch and a crack, or the interference includes one of a scratch and a crack, and the object to be detected includes the other of the scratch and the crack.

The step of acquiring the first detection image and the second detection image of the object to be detected under different illumination conditions and/or shooting conditions includes: changing at least one of a position, a light intensity, and an illumination angle of the light source or by changing the image At least one of a position of the device, an exposure intensity, and a shooting angle is acquired to acquire different lighting conditions or shooting conditions.

The step of acquiring the first detection image and the second detection image of the object to be detected under different illumination conditions and/or shooting conditions includes: setting the light source at different height positions with respect to the object to be detected, and respectively using the image acquisition device to the high position The object to be detected and the object to be detected illuminated by the light source disposed under the light source are subjected to image acquisition to obtain the first detection image and the second detection image respectively; and corresponding positions of the first detection image and the second detection image The step of performing a mathematical operation on the brightness value to distinguish the object to be detected and the interference on the object to be detected includes: performing mathematical operations on the brightness values of the corresponding positions of the first detection image and the second detection image, thereby distinguishing the cracks on the object to be detected Or scratches the dust on the object to be inspected.

The step of acquiring the first detection image and the second detection image of the object to be detected under different illumination conditions and/or shooting conditions further includes: setting the light source and the image collection device on the same side of the object to be detected, and placing the image The angle between the normal direction of the acquisition device and the normal direction of the object to be detected is set between 15 degrees and 70 degrees.

The step of acquiring the first detection image and the second detection image of the object to be detected under different illumination conditions and/or shooting conditions further includes: normalizing the normal direction of the image collection device and the normal direction of the light source set by the high position The angle between the angles is set to be less than 10 degrees, and the angle between the normal direction of the image capturing device and the normal direction of the light source set at the lower position is set to be greater than 30 degrees.

The step of acquiring the first detection image and the second detection image of the object to be detected under different illumination conditions and/or shooting conditions includes: performing image collection on the object to be detected under different illuminations by the image acquisition device respectively. Obtaining the first detection image and the second detection image respectively; performing mathematical operations on the brightness values of the corresponding positions of the first detection image and the second detection image, and further distinguishing the target to be detected and the interference on the object to be detected include: The brightness values of the corresponding positions of the detected image and the second detected image are mathematically operated to distinguish the scratches and cracks on the object to be detected.

In order to at least partially solve the above problems, embodiments of the present invention provide a visual inspection system including a light source, an image acquisition device, and a processor, wherein the light source and the image acquisition device cooperate to further different lighting conditions and/or shooting conditions. Obtaining a first detection image and a second detection image of the object to be detected, and the processor performs a mathematical operation on the brightness values of the corresponding positions of the first detection image and the second detection image, thereby distinguishing the target to be detected and the interference on the object to be detected .

The illumination condition and/or the shooting condition are set according to the reflection target of the object to be detected and the interference, so that there is a certain difference in the brightness value of the object to be detected and the interference after the mathematical operation.

Wherein, the illumination condition and/or the shooting condition are set according to the reflection characteristic of the object to be detected and the interference, so that the target and the interference and the object to be detected can be detected according to the brightness value on one of the first detection image and the second detection image. The other areas are distinguished, and on the other of the first detection image and the second detection image, the interference can be distinguished from the object to be detected and other areas of the object to be detected according to the brightness value.

The processor processes the brightness values of the corresponding positions of the first detection image and the second detection image by using a preset threshold segmentation condition and a logic operation to further distinguish the target to be detected and the interference.

Wherein the interference includes dust, the object to be detected includes at least one of a scratch and a crack, or the interference includes one of a scratch and a crack, and the object to be detected includes the other of the scratch and the crack.

Wherein, different lighting conditions or shooting conditions are acquired by changing at least one of the position, the light intensity, and the illumination angle of the light source or by changing at least one of the position, the exposure intensity, and the shooting angle of the image capturing device.

Wherein, the light source is set at different height positions with respect to the object to be detected, and the image acquisition device respectively performs image acquisition on the object to be detected irradiated by the light source set by the high position and the object to be detected under the light source set by the low position to obtain the first detection respectively. The image and the second detected image, the processor performs a mathematical operation on the brightness values of the corresponding positions of the first detected image and the second detected image, thereby distinguishing the cracks or scratches on the object to be detected from the dust on the object to be detected.

Wherein, the light source and the image collecting device are disposed on the same side of the object to be detected, and an angle between a normal direction of the image capturing device and a normal direction of the object to be detected is set between 15 degrees and 70 degrees.

Wherein, an angle between a normal direction of the image capturing device and a normal direction of the light source disposed at a high position is set to be less than 10 degrees, and a clip between a normal direction of the image capturing device and a normal direction of the light source disposed at a low position The angle is set to be greater than 30 degrees.

The image acquisition device respectively performs image acquisition on the object to be detected under different illuminations of the light source to obtain a first detection image and a second detection image, respectively, and the corresponding position of the first detection image and the second detection image by the processor The brightness value is mathematically manipulated to distinguish between scratches and cracks on the object to be inspected.

In the above manner, the detection target and the interference are effectively distinguished by the combination of the two detection images acquired under different illumination conditions and/or shooting conditions.

 [Description of the Drawings]

1 is a schematic structural view of a visual inspection system according to an embodiment of the present invention;

2 is a schematic flow chart of a visual inspection method according to an embodiment of the invention;

FIG. 3 is a schematic diagram of a manner of acquiring a first detected image according to an embodiment of the invention; FIG.

FIG. 4 is a schematic diagram of a manner of acquiring a second detected image according to an embodiment of the invention; FIG.

FIG. 5 is a schematic diagram of performing logical operations on a first detected image and a second detected image according to an embodiment of the invention; FIG.

FIG. 6 is a schematic diagram of performing logical operations on a first detected image and a second detected image according to another embodiment of the present invention.

【detailed description】

The technical solutions in the embodiments of the present invention are clearly and completely described in the following with reference to the accompanying drawings in the embodiments of the present invention. It is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts are within the scope of the present invention.

Referring to FIG. 1, FIG. 1 is a schematic structural diagram of a visual inspection system according to an embodiment of the present invention. The visual inspection system of the present embodiment includes light sources 111, 112, an image acquisition device 12, and a processor 13. The light source 111, 112 is used to provide illumination for the object to be detected 14, the image acquisition device 12 is used for image acquisition of the object 14 to be detected under the illumination of the light source 111, 112, and the processor 13 is collected according to the image acquisition device 12. The image is identified and the object to be detected on the object 14 to be detected is extracted.

Further referring to FIG. 2, FIG. 2 is a schematic flow chart of a visual detection method according to an embodiment of the invention. In this embodiment, a visual detection method is proposed based on the visual inspection system shown in FIG. 1, which specifically includes the following steps:

Step S11, acquiring a first detection image and a second detection image of the object to be detected under different illumination conditions and/or shooting conditions;

Step S12, performing mathematical operations on the brightness values of the corresponding positions of the first detection image and the second detection image, thereby distinguishing the target to be detected and the interference on the object to be detected.

Further, in step S11, different illumination conditions and/or shooting conditions are set according to the reflection characteristics of the object to be detected and the interference, so that there is a certain difference in the brightness values of the object to be detected and the interference after the mathematical operation in step S12. Further, different illumination conditions and/or shooting conditions are set according to the reflection characteristics of the object to be detected and the interference, so that the target and the interference can be detected according to the brightness value on one of the first detection image and the second detection image. The other areas of the object to be detected are distinguished, and on the other of the first detection image and the second detection image, the interference can be distinguished from the object to be detected and other areas of the object to be detected according to the brightness value. Thus, in step S12, an appropriate mathematical operation rule can be set according to the brightness value of the first detection image and the second detection image according to the object to be detected, the interference, and other regions of the object to be detected, thereby performing mathematical operations. There is a certain difference in the brightness values of the target to be detected and the interference.

The specific lighting conditions and shooting conditions are set by acquiring at least one of the position, the light intensity, and the illumination angle of the light sources 111, 112 to obtain different lighting conditions, or by changing the position, exposure intensity, and shooting angle of the image capturing device 12. At least one shooting condition. It should be noted that two light sources 111, 112 are shown in FIG. 1. However, in a specific implementation process, the number of light sources is not limited thereto, for example, only one light source may be disposed, and the position and intensity of the light source may be And illumination angle adjustment to obtain different lighting conditions. Also, the number of image capture devices 12 and processors 13 is not limited by the one shown in FIG.

In step S12, the brightness values of the corresponding positions of the first detection image and the second detection image may be processed by using a preset threshold segmentation condition and a logical operation, and the detection target and the interference are further distinguished. For example, the first detection image and the second detection image are binarized by a preset threshold segmentation condition, and the object to be detected and the interference are distinguished according to an appropriate logical operation based on obtaining the two binarized images. Certainly, the first detection image and the second detection image may be directly logically operated, and then the threshold image segmentation condition is used to perform threshold segmentation on the computed image to distinguish the target to be detected and the interference.

In the present embodiment, the disturbance may include dust, the object to be detected includes at least one of a scratch and a crack, or the interference includes one of a scratch and a crack, and the object to be detected includes the other of the scratch and the crack.

The lighting conditions, the shooting conditions, and the threshold division conditions, and the specific arrangement of the logic operations will be described in detail below with reference to specific examples. Of course, those skilled in the art can accordingly set the above content according to the actual situation of the target to be detected and the interference in the enlightenment of the related embodiments of the present invention.

Referring further to Figures 3-5, a detailed description will be made below on how to distinguish scratches or cracks from dust.

As shown in FIG. 1, in the present embodiment, the light sources 111, 112 are disposed at different height positions with respect to the object 14 to be detected. The light sources 111, 112 as described above may be the same light source. Wherein, in order to obtain a relatively good detection effect, the light sources 111, 112 and the image acquisition device 12 are disposed on the same side of the object 14 to be detected, that is, the projection area of the surface to be detected of the object 14 to be detected shown by the broken lines B1, B2. The outer side, and the angle between the normal direction A2 of the image capturing device 12 and the normal direction A1 of the object to be detected 14 is set between 15 degrees and 70 degrees. Further, the angle between the normal direction A2 of the image capturing device 12 and the normal direction A3 of the light source 111 of the high position is set to be less than 10 degrees, and the light source direction A2 of the image capturing device 12 and the light source of the low position are set. The angle between the normal directions A4 of 112 is set to be greater than 30 degrees. The normal direction A1 is specifically the vertical direction of the surface to be inspected of the detecting object 14, and the normal directions A2, A3 and A4 are specifically the optical axis or the main axis direction of the image capturing device 12, the light sources 111, 112, respectively.

Further, as shown in FIG. 3, the image acquisition device 12 performs image acquisition on the object 14 to be detected illuminated by the light source 111 disposed at the high position to obtain the first detection image 21. As shown in FIG. 4, the second detection image 22 is obtained by performing image acquisition on the object to be detected 14 illuminated by the light source 112 disposed at the lower position by the image acquisition device 12.

Since scratches and cracks have surface reflection characteristics, dust has diffuse reflection characteristics. Therefore, in the first detected image 21, the scratches 141 and the cracks 142 (indicated by thick solid lines in the first detected image 21, respectively) are opposed to the dust 143 (indicated by thin solid lines in the first detected image 21, respectively). Other areas (scratches 141, cracks 142, and areas other than the dust 143) of the object 14 to be inspected are all highlighted. That is, the difference in luminance between the scratch 141, the crack 142, and the dust 143 is small, and the difference in brightness between the scratch 141, the crack 142, and the dust 143 and other regions of the object 14 to be detected is large, and thus the brightness can be passed. The value distinguishes the scratch 141, the crack 142, and the dust 143 from other areas of the object 14 to be detected, such as by threshold division. In the second detection image 22, the scratches 141 and the cracks 142 (indicated by thick broken lines in the second detection image 22, respectively) are rendered in a low-light state (ie, the brightness is close) with respect to other areas of the object 14 to be detected, and dust 143 (represented by thin solid lines in the second detected image 22, respectively) still exhibits a highlight state with respect to other areas of the object 14 to be detected. That is, the difference in brightness between the scratch 141 and the crack 142 and the dust 143 is large, while the difference in brightness between the scratch 141 and the crack 142 and other regions of the object 14 to be detected is small, and the dust 143 and the object 14 to be detected are different. The brightness difference of the other areas is large, and the dust 143 can be distinguished from the scratches 141, the cracks 142, and other areas of the object 14 to be detected by the brightness value.

Further, as shown in FIG. 5, in the first detection image 21 and the second detection image 22, the luminance values of the scratches 141, the cracks 142, and the dust 143 have the above difference, and the first detection image is set by setting a preset threshold value. 21 and the second detection image 22 are subjected to binarization processing, and the brightness values of the scratches 141 and the cracks 142 and the dust 143 in the first detection image 21 can be set to 1, and the brightness values of other regions of the object to be detected are 0. Alternatively, the first binarized image 23 as shown in FIG. 5 is obtained. At the same time, the brightness value of the dust 143 in the second detection image 22 can be set to 1, and the brightness values of other areas of the object 14 to be detected, the scratches 141 and the cracks 142 can be set to 0, or vice versa, thereby obtaining the figure. The second binarized image 24 shown in FIG.

Further, by performing appropriate logical operations (for example, the same OR operation or the exclusive OR operation) on the luminance values of the corresponding positions of the first binarized image 23 and the second binarized image 24, the corresponding scratches 141 can be extracted from the corresponding scratches 141. And the crack 142, as shown by the final image 25 in FIG. 5, further distinguishes the scratch 141 and the crack 142 from the dust 143.

In other embodiments, the scratches 141 and cracks 142 may be extracted by other logic operations and threshold segmentation conditions. For example, the luminance values of the corresponding positions of the first detection image 21 and the second detection image 22 are directly subtracted by a logical operation, at which time the scratches 141 and the cracks 142 are respectively presented in the first detection image 21 and the second detection image 22 The highlight and the low-light display have a large difference in brightness obtained by subtraction, and the dust 143 is highlighted in both the first detection image 21 and the second detection image 22, and the luminance difference obtained by subtraction is small. Therefore, by setting an appropriate threshold division condition, the portion having a larger difference is retained, and the portion having a smaller difference is ignored, and the scratch 141 and the crack 142 can also be extracted.

In this embodiment, the logical operations used are set according to actual conditions, including but not limited to the same OR operation or the exclusive OR operation, and may be other operations such as AND, OR, addition, multiplication, and the like.

It should be noted that after the above detection is completed on one side of the object 14 to be detected, the object to be detected 14 can be rotated by rotating the object to be detected 14, the rotating light sources 111, 112 and the image capturing device 12 or using other light sources and image collecting devices. Repeat the above detection process on one side to avoid missed detection.

Further in conjunction with FIG. 6, a detailed description will be made below on how to distinguish scratches from cracks.

In the embodiment, the image capturing device 12 respectively performs image acquisition on the object 14 to be detected under different light intensity illumination to obtain the first detection image 31 and the second detection image 32, respectively, and further utilizes the first detection image 31 and The second detected image 32 distinguishes between scratches and cracks on the object 14 to be detected.

For example, in the first detection image 31 formed under relatively small light intensity illumination, the scratches 141 and the cracks 142 (represented by thick solid lines in the first detection image 31, respectively) with respect to other areas of the object 14 to be detected are The highlight state is exhibited, that is, the difference in brightness between the scratch 141 and the crack 142 is small, and the difference in brightness between the scratch 141 and the crack 142 and other regions of the object 14 to be detected is large, and the scratch 141 can be distinguished by the brightness value. And the crack 142 and other areas of the object 14 to be inspected. In the second detection image 32 formed under relatively large light intensity illumination, the scratches 141 (indicated by thick broken lines in the second detection image 32, respectively) are rendered in a low state with respect to other areas of the object 14 to be detected, and the cracks 142 is still highlighted with respect to other areas of the object 14 to be inspected, that is, the difference in brightness between the scratch 141 and the crack 142 is large, and the difference in brightness between the scratch 141 and other areas of the object to be detected 14 is small, and the crack The difference in brightness between the other areas of the object 142 and the object to be detected 14 is large, and the dent 142 and the scratch 141 and other areas of the object 14 to be detected can be split according to the brightness value area.

Therefore, referring to the manner similar to the above description, the first detection image 31 and the second detection image 32 can be binarized by setting appropriate threshold division conditions, thereby obtaining the first binarized image 33 and the second binary value. The image 34 is imaged and the scratches 141 are extracted from the first binarized image 33 and the second binarized image 34 by appropriate logic operations to effect differentiation of the cracks 142 from the scratches 141. Of course, the first detection image 31 and the second detection image 32 can be directly subtracted and then the scratch 141 can be extracted using the threshold division condition.

As further shown in FIG. 1 , the embodiment of the present invention further provides a visual inspection system, which includes a light source 111, 112, an image acquisition device 12, and a processor 13, wherein the light sources 111, 112 and the image acquisition device 12 cooperate, and further Obtaining the first detection image and the second detection image of the object 14 to be detected under different illumination conditions and/or shooting conditions, and the processor 13 performs a mathematical operation on the brightness values of the corresponding positions of the first detection image and the second detection image, Further, the target to be detected and the interference on the object 14 to be detected are distinguished.

In the present embodiment, the above lighting conditions and/or shooting conditions are set according to the reflection characteristics of the object to be detected and the interference, so that there is a certain difference in the brightness values of the object to be detected and the interference after the mathematical operation. Further, the lighting conditions and/or the shooting conditions are set according to the reflection characteristics of the object to be detected and the interference, so that the target and the interference and the object to be detected can be detected according to the brightness value on one of the first detection image and the second detection image. The other areas of the 14 are distinguished, and on the other of the first detected image and the second detected image, the interference can be distinguished from the object to be detected and other areas of the object 14 to be detected according to the brightness value. The specific setting of the lighting conditions and/or the shooting conditions may be at least one of changing the position of the light sources 111, 112, the light intensity, and the illumination angle or by changing at least one of the position, the exposure intensity, and the shooting angle of the image capturing device 12. To get different lighting conditions or shooting conditions.

In this embodiment, the processor 13 processes the brightness values of the corresponding positions of the first detection image and the second detection image by using a preset threshold division condition and a logical operation, thereby distinguishing the target to be detected and the interference. Wherein the interference includes dust, the object to be detected includes at least one of a scratch and a crack, or the interference includes one of a scratch and a crack, and the object to be detected includes the other of the scratch and the crack.

In a specific implementation, the light sources 111, 112 are disposed at different height positions relative to the object 14 to be detected. And in order to obtain a better detection effect, the light sources 111, 112 and the image acquisition device 12 are disposed on the same side of the object 14 to be detected, and the normal direction A2 of the image acquisition device 12 and the normal direction A1 of the object 14 to be detected are The angle between the two is set between 15 degrees and 70 degrees. Further, an angle between the normal direction A2 of the image capturing device 12 and the normal direction A3 of the light source 111 disposed at the upper position is set to be less than 10 degrees, and the normal direction A2 of the image capturing device 12 and the light source 112 of the low position are set. The angle between the normal directions A4 is set to be greater than 30 degrees.

The image capturing device 12 respectively performs image acquisition on the object to be detected 14 illuminated by the light source 111 and the light source 112 disposed in the low position, respectively, to obtain the first detection image and the second detection image, respectively, and the processor 13 The brightness values of the corresponding positions of the first detection image and the second detection image are mathematically operated to distinguish the cracks or scratches on the object 14 to be detected from the dust on the object 14 to be detected.

In another specific implementation, the image acquisition device 12 respectively performs image acquisition on the object 14 to be detected under different illuminations of the light source 111 to obtain a first detection image and a second detection image, respectively, and the processor 13 detects the first detection. The brightness values of the corresponding positions of the image and the second detected image are mathematically operated to distinguish the scratches and cracks on the object 14 to be detected.

For the above components and their working principles, reference may be made to the detailed description of the specific embodiments of the visual detection method, and details are not described herein.

In summary, those skilled in the art can easily understand that the extraction of the object to be detected is performed by using a combination of two detection images acquired under different illumination conditions and/or shooting conditions, and the object to be detected and the interference can be effectively distinguished.

The above is only the embodiment of the present invention, and is not intended to limit the scope of the invention, and the equivalent structure or equivalent process transformations made by the description of the invention and the drawings are directly or indirectly applied to other related technologies. The fields are all included in the scope of patent protection of the present invention.

Claims (20)

1. A visual inspection method, the method comprising:

   Acquiring the first detection image and the second detection image of the object to be detected under different illumination conditions and/or shooting conditions;

   And performing a mathematical operation on the brightness values of the corresponding positions of the first detection image and the second detection image to further distinguish the target to be detected and the interference on the object to be detected.
2. The method according to claim 1, wherein the step of acquiring the first detected image and the second detected image of the object to be detected under different lighting conditions and/or shooting conditions comprises:

   Different illumination conditions and/or shooting conditions are set according to the to-be-detected target and the reflection characteristic of the interference, so that there is a certain difference in the brightness value of the object to be detected and the interference after the mathematical operation.
3. The method according to claim 2, wherein the step of acquiring the first detected image and the second detected image of the object to be detected under different lighting conditions and/or shooting conditions comprises:

   Setting different illumination conditions and/or shooting conditions according to the target to be detected and the reflection characteristic of the interference, so that one of the first detection image and the second detection image can be aligned according to the brightness value Determining that the detection target and the interference are distinguished from other areas of the object to be detected, and the interference and the interference can be based on the brightness value on the other of the first detection image and the second detection image The detection target and the other areas of the object to be detected are distinguished.
4. According to claims 1-3 The method according to any one of the preceding claims, wherein the brightness value of the corresponding position of the first detection image and the second detection image is mathematically operated to further distinguish the target to be detected on the object to be detected And the steps of interference include:

   The brightness values of the corresponding positions of the first detection image and the second detection image are processed by using a preset threshold segmentation condition and a logical operation to further distinguish the target to be detected and the interference.
5. The method according to claim 1, wherein said interference comprises dust, said object to be detected includes at least one of a scratch and a crack, or said interference includes one of a scratch and a crack, said The detection target includes the other of the scratches and cracks.
6. The method according to claim 5, wherein the step of acquiring the first detected image and the second detected image of the object to be detected under different lighting conditions and/or shooting conditions comprises:

   Different lighting conditions or shooting conditions are acquired by changing at least one of the position, the light intensity, and the illumination angle of the light source or by changing at least one of the position, the exposure intensity, and the shooting angle of the image capturing device.
7. The method according to claim 6, wherein the step of acquiring the first detected image and the second detected image of the object to be detected under different lighting conditions and/or shooting conditions comprises:

   And setting the light source at different height positions with respect to the object to be detected, and respectively, using the image capturing device to respectively perform image acquisition on the object to be detected and the object to be detected under the illumination of the light source set by the high-level light source, respectively Obtaining a first detection image and a second detection image;

   The step of performing a mathematical operation on the brightness values of the corresponding positions of the first detection image and the second detection image to further distinguish the target to be detected and the interference on the object to be detected includes:

   And performing a mathematical operation on the brightness values of the corresponding positions of the first detection image and the second detection image to further distinguish the cracks or scratches on the object to be detected from the dust on the object to be detected.
8. The method according to claim 7, wherein the step of acquiring the first detected image and the second detected image of the object to be detected under different lighting conditions and/or shooting conditions further comprises:

   Setting the light source and the image capturing device on the same side of the object to be detected, and setting an angle between a normal direction of the image capturing device and a normal direction of the object to be detected at 15 Degree between -70 degrees.
9. The method according to claim 8, wherein the step of acquiring the first detected image and the second detected image of the object to be detected under different lighting conditions and/or shooting conditions further comprises:

   Setting an angle between a normal direction of the image capturing device and a normal direction of the light source disposed at a high position to be less than 10 degrees, and setting the normal direction of the image capturing device to the light source at a low position The angle between the normal directions is set to be greater than 30 degrees.
10. The method according to claim 1, wherein the step of acquiring the first detected image and the second detected image of the object to be detected under different lighting conditions and/or shooting conditions comprises:

    Acquiring an image of the object to be detected under different illuminations by an image acquisition device to obtain a first detection image and a second detection image, respectively;

    The step of performing a mathematical operation on the brightness values of the corresponding positions of the first detection image and the second detection image to further distinguish the target to be detected and the interference on the object to be detected includes:

    Performing a mathematical operation on the brightness values of the corresponding positions of the first detection image and the second detection image to further distinguish the scratches and cracks on the object to be detected.
11. A visual inspection system, characterized in that the system comprises a light source, an image acquisition device and a processor, wherein the light source cooperates with the image acquisition device to obtain a detection under different illumination conditions and/or shooting conditions a first detection image and a second detection image of the object, the processor performing a mathematical operation on the brightness values of the corresponding positions of the first detection image and the second detection image, thereby distinguishing the to-be-detected object Detect targets and interference.
12. The system according to claim 11, wherein said illumination condition and/or photographing condition is set according to said reflection target and said reflection reflection characteristic, thereby causing said waiting after said mathematical operation There is a difference between the detection target and the brightness value of the interference.
13. The system according to claim 12, wherein said illumination condition and/or photographing condition is set according to said reflection target and said interference reflection characteristic, thereby causing said first detection image and said One of the second detection images is capable of distinguishing the object to be detected and the interference from other regions of the object to be detected according to a brightness value, and in the first detection image and the second detection image On the other side, the interference can be distinguished from the object to be detected and other areas of the object to be detected according to the brightness value.
14. The system according to any one of claims 11 to 13, wherein the processor cooperates with a logical operation to match a corresponding position of the first detection image and the second detection image by using a preset threshold division condition The brightness values are processed to distinguish the target to be detected and the interference.
15. The system according to claim 11, wherein said interference includes dust, said object to be detected includes at least one of a scratch and a crack, or said interference includes one of a scratch and a crack, said The detection target includes the other of the scratches and cracks.
16. The system according to claim 15, wherein at least one of changing a position, a light intensity, and an illumination angle of the light source or by changing at least one of a position, an exposure intensity, and a shooting angle of the image pickup device To get different lighting conditions or shooting conditions.
17. The system according to claim 16, wherein the light source is disposed at different height positions with respect to the object to be detected, and the image capturing device respectively irradiates the object to be detected under a light source set at a high position and Performing image acquisition on the object to be detected illuminated by the light source disposed at a low position to obtain a first detection image and a second detection image, respectively, where the processor corresponds to the first detection image and the second detection image The brightness value is mathematically operated to distinguish between cracks or scratches on the object to be detected and dust on the object to be detected.
18. The system according to claim 17, wherein the light source and the image capturing device are disposed on the same side of the object to be detected, and a normal direction of the image capturing device and an object to be detected The angle between the normal directions is set between 15 degrees and 70 degrees.
19. The system according to claim 18, wherein an angle between a normal direction of the image capturing device and a normal direction of the light source disposed at a high position is set to be less than 10 degrees, and the image capturing device The angle between the normal direction and the normal direction of the light source disposed at the lower position is set to be greater than 30 degrees.
20. The system according to claim 11, wherein the image acquisition device respectively performs image acquisition on the object to be detected under different illuminations of the light source to obtain a first detection image and a second detection image, respectively. And the processor performs a mathematical operation on the brightness values of the corresponding positions of the first detection image and the second detection image to further distinguish the scratches and cracks on the object to be detected.