CN107980094B - Visual detection system and method - Google Patents
Visual detection system and method Download PDFInfo
- Publication number
- CN107980094B CN107980094B CN201780001564.9A CN201780001564A CN107980094B CN 107980094 B CN107980094 B CN 107980094B CN 201780001564 A CN201780001564 A CN 201780001564A CN 107980094 B CN107980094 B CN 107980094B
- Authority
- CN
- China
- Prior art keywords
- detected
- image
- detection image
- detection
- light source
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8806—Specially adapted optical and illumination features
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
Abstract
A vision inspection system and method. The method comprises the following steps: acquiring a first detection image (21,31) and a second detection image (22,32) of an object (14) to be detected under different lighting conditions and/or photographing conditions (S11); the brightness values of the corresponding positions of the first detection image (21,31) and the second detection image (22,32) are mathematically manipulated to distinguish between the object to be detected and the disturbance on the object to be detected (14) (S12). The method is characterized in that the integration of two detection images acquired under different lighting conditions and/or shooting conditions is utilized to effectively distinguish the target to be detected from the interference.
Description
Technical Field
The embodiment of the invention relates to the field of visual detection, in particular to a visual detection system and a visual detection method.
Background
Industrial vision inspection generally identifies a predetermined target, such as a flaw, a crack, or the like, from an image of an object to be inspected by image-capturing the object to be inspected and image-recognizing the captured image. Currently, two problems are commonly encountered in industrial visual inspection processes: one is that dust is easily deposited on the surface of an object to be detected, and a target to be detected is often easily affected by the dust, so that the detection needs to be carried out in a dust-free environment, and the detection cost is increased; another is that the object to be inspected often contains multiple defects, and it is difficult to effectively distinguish between different defects.
Disclosure of Invention
In order to at least partially solve the above problem, an embodiment of the present invention provides a visual inspection method, including: acquiring a first detection image and a second detection image of an object to be detected under different lighting conditions and/or shooting conditions; and performing mathematical operation on the brightness values of the corresponding positions of the first detection image and the second detection image so as to distinguish the target to be detected and the interference on the object to be detected.
The method comprises the following steps of acquiring a first detection image and a second detection image of an object to be detected under different lighting conditions and/or shooting conditions: different lighting conditions and/or shooting conditions are set according to the reflection characteristics of the target to be detected and the interference, and therefore the brightness values of the target to be detected and the interference after mathematical operation are different to a certain extent.
The method comprises the following steps of acquiring a first detection image and a second detection image of an object to be detected under different lighting conditions and/or shooting conditions: different lighting conditions and/or shooting conditions are set according to the reflection characteristics of the target to be detected and the interference, so that the target to be detected, the interference and other areas of the object to be detected can be distinguished according to the brightness value on one of the first detection image and the second detection image, and the interference and other areas of the target to be detected and the object to be detected can be distinguished according to the brightness value on the other one of the first detection image and the second detection image.
The step of performing mathematical operation on the brightness values of the corresponding positions of the first detection image and the second detection image to distinguish the target to be detected and the interference on the object to be detected comprises the following steps: and processing the brightness values of the corresponding positions of the first detection image and the second detection image by utilizing the preset threshold segmentation condition and the logical operation, and further distinguishing the target to be detected and the interference.
Wherein the disturbance comprises dust and the object to be detected comprises at least one of a scratch and a crack, or the disturbance comprises one of a scratch and a crack and the object to be detected comprises the other of a scratch and a crack.
The method comprises the following steps of acquiring a first detection image and a second detection image of an object to be detected under different lighting conditions and/or shooting conditions: different lighting conditions or photographing conditions are obtained by changing at least one of the position, light intensity, and illumination angle of the light source or by changing at least one of the position, exposure intensity, and photographing angle of the image pickup device.
The method comprises the following steps of acquiring a first detection image and a second detection image of an object to be detected under different lighting conditions and/or shooting conditions: setting light sources at different height positions relative to an object to be detected, and respectively acquiring images of the object to be detected under the irradiation of the light source arranged at a high position and the object to be detected under the irradiation of the light source arranged at a low position by utilizing image acquisition equipment to respectively obtain a first detection image and a second detection image; the step of performing mathematical operation on the brightness values of the corresponding positions of the first detection image and the second detection image to distinguish the target to be detected and the interference on the object to be detected comprises the following steps: and performing mathematical operation on the brightness values of the corresponding positions of the first detection image and the second detection image so as to distinguish cracks or scratches on the object to be detected and dust on the object to be detected.
Wherein the step of acquiring the first detection image and the second detection image of the object to be detected under different lighting conditions and/or shooting conditions further comprises: the light source and the image acquisition equipment are arranged on the same side of the object to be detected, and the included angle between the normal direction of the image acquisition equipment and the normal direction of the object to be detected is set between 15 degrees and 70 degrees.
Wherein the step of acquiring the first detection image and the second detection image of the object to be detected under different lighting conditions and/or shooting conditions further comprises: an angle between a normal line direction of the image pickup device and a normal line direction of the light source disposed at a high position is set to be less than 10 degrees, and an angle between the normal line direction of the image pickup device and a normal line direction of the light source disposed at a low position is set to be greater than 30 degrees.
The method comprises the following steps of acquiring a first detection image and a second detection image of an object to be detected under different lighting conditions and/or shooting conditions: respectively acquiring images of an object to be detected under irradiation of different light intensities by using image acquisition equipment to respectively obtain a first detection image and a second detection image; the step of performing mathematical operation on the brightness values of the corresponding positions of the first detection image and the second detection image to distinguish the target to be detected and the interference on the object to be detected comprises the following steps: and performing mathematical operation on the brightness values of the corresponding positions of the first detection image and the second detection image so as to distinguish the scratch and the crack on the object to be detected.
In order to at least partially solve the above problems, an embodiment of the present invention provides a visual inspection system, which includes a light source, an image capturing device, and a processor, where the light source is matched with the image capturing device to obtain a first inspection image and a second inspection image of an object to be inspected under different lighting conditions and/or shooting conditions, and the processor performs mathematical operation on brightness values of corresponding positions of the first inspection image and the second inspection image to distinguish an object to be inspected from interference on the object to be inspected.
The lighting condition and/or the shooting condition are/is set according to the reflection characteristics of the target to be detected and the interference, and therefore the brightness values of the target to be detected and the interference after mathematical operation are different to a certain extent.
The lighting condition and/or the shooting condition are/is set according to the reflection characteristics of the target to be detected and the interference, so that the target to be detected and the interference can be distinguished from other areas of the object to be detected on one of the first detection image and the second detection image according to the brightness value, and the interference can be distinguished from the other areas of the target to be detected and the object to be detected on the other one of the first detection image and the second detection image 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 utilizing the preset threshold segmentation condition and the logical operation, and further distinguishes the target to be detected and the interference.
Wherein the disturbance comprises dust and the object to be detected comprises at least one of a scratch and a crack, or the disturbance comprises one of a scratch and a crack and the object to be detected comprises the other of a scratch and a crack.
Wherein different lighting conditions or photographing conditions are acquired by changing at least one of a position, a light intensity, and an irradiation angle of the light source or by changing at least one of a position, an exposure intensity, and a photographing angle of the image pickup device.
The processor performs mathematical operation on brightness values of corresponding positions of the first detection image and the second detection image, and further distinguishes cracks or scratches on the object to be detected and dust on the object to be detected.
The light source and the image acquisition equipment are arranged on the same side of the object to be detected, and an included angle between the normal direction of the image acquisition equipment and the normal direction of the object to be detected is set to be 15-70 degrees.
Wherein an angle between a normal direction of the image pickup device and a normal direction of the light source disposed at a high position is set to be less than 10 degrees, and an angle between the normal direction of the image pickup device and a normal direction of the light source disposed at a low position is set to be greater than 30 degrees.
The image acquisition equipment acquires images of an object to be detected under the irradiation of different light intensities of the light source respectively to obtain a first detection image and a second detection image respectively, and the processor performs mathematical operation on the brightness values of the corresponding positions of the first detection image and the second detection image to distinguish scratches and cracks on the object to be detected.
By the mode, the target to be detected and the interference are effectively distinguished by utilizing the integration of two detection images acquired under different lighting conditions and/or shooting conditions.
Drawings
FIG. 1 is a schematic diagram of a visual inspection system according to an embodiment of the present invention;
FIG. 2 is a 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 inspection image according to an embodiment of the invention;
FIG. 4 is a schematic diagram of a second inspection image acquisition mode according to an embodiment of the invention;
FIG. 5 is a schematic diagram of a logical operation performed on a first inspection image and a second inspection image according to an embodiment of the invention;
fig. 6 is a schematic diagram of performing a logical operation on a first detection image and a second detection image according to another embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and 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, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection 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 vision inspection system of the present embodiment includes light sources 111, 112, an image pickup device 12, and a processor 13. The light sources 111 and 112 are configured to provide illumination for the object 14 to be detected, the image capturing device 12 is configured to capture an image of the object 14 to be detected under the illumination of the light sources 111 and 112, and the processor 13 identifies the object to be detected on the object 14 to be detected according to the image captured by the image capturing device 12 and extracts the object to be detected on the object 14 to be detected.
Referring further to fig. 2, fig. 2 is a flow chart of a visual inspection method according to an embodiment of the invention. In this embodiment, a visual inspection method is proposed based on the visual inspection system shown in fig. 1, and specifically includes the following steps:
step S11, acquiring a first detection image and a second detection image of an object to be detected under different lighting conditions and/or shooting conditions;
step S12, performing mathematical operation 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.
Further, in step S11, different lighting conditions and/or photographing conditions are set according to the reflection characteristics of the object to be detected and the disturbance, so that the brightness values of the object to be detected and the disturbance after the mathematical operation in step S12 have a certain difference. Further, different lighting conditions and/or shooting conditions are set according to the reflection characteristics of the target to be detected and the interference, so that the target to be detected and the interference can be distinguished from other areas of the object to be detected according to the brightness value on one of the first detection image and the second detection image, and the interference can be distinguished from the target to be detected and the other areas of the object to be detected according to the brightness value on the other one of the first detection image and the second detection image. Therefore, in step S12, an appropriate mathematical operation rule may be set according to the brightness values of the target to be detected, the disturbance and other regions of the object to be detected on the first detection image and the second detection image, so that the brightness values of the target to be detected and the disturbance after the mathematical operation have a certain difference.
The specific illumination conditions and the shooting conditions are set in such a manner that different illumination conditions are obtained by changing at least one of the position, the light intensity, and the irradiation angle of the light sources 111, 112, or at least one of the position, the exposure intensity, and the shooting angle of the image pickup device 12 is changed. It is noted that two light sources 111, 112 are shown in fig. 1, however, in the specific implementation, the number of light sources is not limited thereto, for example, only one light source may be provided, and different lighting conditions may be obtained by adjusting the position, light intensity and illumination angle of the light source. Also, the number of image capturing devices 12 and processors 13 is not limited to that shown in fig. 1.
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 logic operation, so as to distinguish the target to be detected from the interference. For example, the first detection image and the second detection image are binarized through a preset threshold segmentation condition, and then the target to be detected and the interference are distinguished according to proper logic operation in the two obtained binarized images. Of course, the first detection image and the second detection image may also be directly subjected to logic operation, and then the calculated images are subjected to threshold segmentation through a preset threshold segmentation condition to distinguish the target to be detected from the interference.
In the present embodiment, the disturbance may include dust, and the object to be detected includes at least one of a scratch and a crack, or the disturbance includes one of a scratch and a crack, and the object to be detected includes the other of a scratch and a crack.
Specific setting manners of the illumination condition, the photographing condition, and the threshold value division condition, the logical operation will be described in detail with reference to specific examples. Of course, those skilled in the art can make corresponding settings according to the actual situation of the target to be detected and the disturbance in the light of the related embodiments of the present invention.
With further reference to fig. 3-5, a detailed description will be given below of how to distinguish a scratch or a crack from dust, as an example.
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 one and the same light source. In order to obtain relatively good detection effect, the light sources 111 and 112 and the image capturing device 12 are disposed on the same side of the object 14 to be detected, i.e., outside the projection area of the surface to be detected of the object 14 to be detected, which is indicated by dotted lines B1 and B2, and the included angle between the normal direction a2 of the image capturing device 12 and the normal direction a1 of the object 14 to be detected is set to be 15-70 degrees. Further, the angle between the normal direction a2 of the image pickup device 12 and the normal direction A3 of the light source 111 disposed in the high position is set to be less than 10 degrees, and the angle between the normal direction a2 of the image pickup device 12 and the normal direction a4 of the light source 112 disposed in the low position is set to be greater than 30 degrees. The normal direction a1 is specifically a vertical direction of the surface to be detected of the detection object 14, and the normal directions a2, A3, and a4 are specifically optical axis or main axis directions of the image pickup device 12 and the light sources 111, 112, respectively.
As further shown in fig. 3, the first detection image 21 is obtained by image-capturing the object to be detected 14 illuminated by the light source 111 disposed at a high position by the image-capturing device 12. As shown in fig. 4, the second inspection image 22 is obtained by image-capturing the object to be inspected 14 irradiated with the light source 112 disposed at a low position by the image-capturing device 12.
Since the scratch and the crack have a surface reflection property, the dust has a diffused reflection property. Therefore, in the first detection image 21, the scratch 141 and the crack 142 (indicated by thick solid lines in the first detection image 21, respectively) and the dust 143 (indicated by thin solid lines in the first detection image 21, respectively) each assume a highlight state with respect to other regions of the object to be detected 14 (regions other than the scratch 141, the crack 142, and the dust 143). That is, the brightness difference between the scratch 141, the crack 142, and the dust 143 is small, the brightness difference between the scratch 141, the crack 142, and the dust 143 and other regions of the object to be detected 14 is large, and thus the scratch 141, the crack 142, and the dust 143 can be distinguished from other regions of the object to be detected 14 by the brightness value, for example, by the threshold value division method. In the second inspection image 22, the scratch 141 and the crack 142 (indicated by thick broken lines in the second inspection image 22, respectively) exhibit a low-luminance state (i.e., close luminance) with respect to the other region of the object to be inspected 14, while the dust 143 (indicated by thin solid lines in the second inspection image 22, respectively) still exhibits a high-luminance state with respect to the other region of the object to be inspected 14. That is, the brightness difference between the scratch 141 and the crack 142 and the dust 143 is large, the brightness difference between the scratch 141 and the crack 142 and other regions of the object to be detected 14 is small, the brightness difference between the dust 143 and other regions of the object to be detected 14 is large, and the dust 143 can be distinguished from the scratch 141, the crack 142 and other regions of the object to be detected 14 by the brightness value.
As further shown in fig. 5, in the first detection image 21 and the second detection image 22, the luminance values of the scratch 141, the crack 142 and the dust 143 are different from each other, and by setting a preset threshold segmentation condition to perform binarization processing on the first detection image 21 and the second detection image 22, the luminance values of the scratch 141, the crack 142 and the dust 143 in the first detection image 21 can be set to 1, and the luminance value of the other area of the object to be detected can be set to 0, or vice versa, so as to obtain the first binarized image 23 shown in fig. 5. Meanwhile, the brightness value of the dust 143 in the second detection image 22 may be set to 1, and the brightness values of the other areas of the object to be detected 14, the scratch 141 and the crack 142 may be set to 0, or vice versa, thereby obtaining the second binary image 24 as shown in fig. 5.
Further, by performing an appropriate logical operation (for example, an exclusive or operation or an 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 scratch 141 and crack 142 can be extracted, as shown in the final image 25 in fig. 5, thereby distinguishing the scratch 141 and crack 142 from the dust 143.
In other embodiments, the scratch 141 and the crack 142 may be extracted by other logical 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, and at this time, since the scratch 141 and the crack 142 respectively show highlight display and low-highlight display in the first detection image 21 and the second detection image 22, the difference in luminance obtained by the subtraction is large, and the dust 143 shows highlight display in both the first detection image 21 and the second detection image 22, and the difference in luminance obtained by the subtraction is small. Therefore, by setting an appropriate threshold value dividing condition, the portion with a large difference is retained, and the portion with a small difference is ignored, and the scratch 141 and the crack 142 can be extracted as well.
In the present embodiment, the logic operation used is set according to the actual situation, and includes but is not limited to an exclusive or operation or an exclusive or operation, and may be other operations such as and, or, addition, multiplication, and the like.
It should be noted that after the detection is completed on one side of the object 14, the detection process can be repeated from the other side of the object 14 by rotating the object 14, rotating the light sources 111 and 112 and the image capturing device 12 or using other light sources and image capturing devices, thereby avoiding missing detection.
Further referring to fig. 6, the following will describe in detail how to distinguish the scratch from the crack.
In the present embodiment, the image capturing device 12 is used to capture images of the object to be detected 14 irradiated by different light intensities to obtain the first detection image 31 and the second detection image 32, respectively, and further the first detection image 31 and the second detection image 32 are used to distinguish the scratch from the crack on the object to be detected 14.
For example, in the first detection image 31 formed under the irradiation of relatively small light intensity, the scratch 141 and the crack 142 (indicated by thick solid lines in the first detection image 31, respectively) both present a high brightness state with respect to other regions of the object to be detected 14, that is, the brightness difference between the scratch 141 and the crack 142 is small, and the brightness difference between the scratch 141 and the crack 142 and other regions of the object to be detected 14 is large, so that the scratch 141 and the crack 142 can be distinguished from other regions of the object to be detected 14 by the brightness value. In the second detection image 32 formed under the irradiation of relatively large light intensity, the scratch 141 (indicated by a thick dotted line in the second detection image 32) is in a low brightness state relative to other regions of the object to be detected 14, and the crack 142 is still in a high brightness state relative to other regions of the object to be detected 14, that is, the brightness difference between the scratch 141 and the crack 142 is large, meanwhile, the brightness difference between the scratch 141 and other regions of the object to be detected 14 is small, and the brightness difference between the crack 142 and other regions of the object to be detected 14 is large, so that the crack 142 and the scratch 141 and other regions of the object to be detected 14 can be distinguished according to the brightness values.
Therefore, referring to a manner similar to that described above, the first detection image 31 and the second detection image 32 may be binarized by setting an appropriate threshold segmentation condition, thereby obtaining the first binarized image 33 and the second binarized image 34, and the scratch 141 is extracted from the first binarized image 33 and the second binarized image 34 by an appropriate logical operation, thereby achieving the distinction of the crack 142 from the scratch 141. Of course, the scratch 141 may be extracted by directly subtracting the first detection image 31 and the second detection image 32 and then using the threshold segmentation condition.
As further shown in fig. 1, an embodiment of the present invention further provides a visual inspection system, which includes light sources 111 and 112, an image capturing device 12, and a processor 13, where the light sources 111 and 112 cooperate with the image capturing device 12 to obtain a first inspection image and a second inspection image of an object 14 to be inspected under different lighting conditions and/or shooting conditions, and the processor 13 performs mathematical operations on brightness values of corresponding positions of the first inspection image and the second inspection image to distinguish an object to be inspected and interference on the object 14 to be inspected.
In this embodiment, the lighting condition and/or the shooting condition are set according to the reflection characteristics of the target to be detected and the interference, so that the brightness values of the target to be detected and the interference after mathematical operation are different from each other. Further, the lighting condition and/or the photographing condition are set according to the reflection characteristics of the target to be detected and the disturbance, so that the target to be detected and the disturbance can be distinguished from other regions of the object to be detected 14 according to the brightness value on one of the first detection image and the second detection image, and the disturbance can be distinguished from other regions of the target to be detected and the object to be detected 14 according to the brightness value on the other one of the first detection image and the second detection image. A specific setting manner of the illumination condition and/or the photographing condition may be to acquire different illumination conditions or photographing conditions by changing at least one of the position, light intensity, and illumination angle of the light sources 111, 112 or by changing at least one of the position, exposure intensity, and photographing angle of the image pickup device 12.
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 segmentation condition and matching with a logical operation, so as to distinguish the target to be detected from the interference. Wherein the disturbance comprises dust and the object to be detected comprises at least one of a scratch and a crack, or the disturbance comprises one of a scratch and a crack and the object to be detected comprises the other of a scratch and a crack.
In a particular implementation, the light sources 111, 112 are disposed at different height positions relative to the object 14 to be inspected. And in order to obtain better detection effect, the light sources 111 and 112 and the image capturing device 12 are disposed on the same side of the object 14 to be detected, and the included angle between the normal direction a2 of the image capturing device 12 and the normal direction a1 of the object 14 to be detected is set between 15 degrees and 70 degrees. Further, the angle between the normal direction a2 of the image pickup device 12 and the normal direction A3 of the light source 111 disposed in the high position is set to be less than 10 degrees, and the angle between the normal direction a2 of the image pickup device 12 and the normal direction a4 of the light source 112 disposed in the low position is set to be greater than 30 degrees.
The image capturing device 12 captures images of the object 14 to be detected under the irradiation of the light source 111 arranged at a high position and the object 14 to be detected under the irradiation of the light source 112 arranged at a low position respectively to obtain a first detection image and a second detection image, and the processor 13 performs mathematical operation on brightness values of corresponding positions of the first detection image and the second detection image to distinguish a crack or scratch on the object 14 to be detected from dust on the object 14 to be detected.
In another specific implementation manner, the image capturing device 12 respectively captures images of the object to be detected 14 irradiated by different light intensities of the light source 111 to obtain a first detection image and a second detection image, and the processor 13 performs mathematical operation on brightness values of corresponding positions of the first detection image and the second detection image to distinguish scratches and cracks on the object to be detected 14.
For the above elements and their operation, reference may be made to the above detailed description of specific embodiments of the visual inspection method, which is not repeated herein.
In summary, those skilled in the art will readily understand that the extraction of the target to be detected by using the synthesis of two detection images obtained under different illumination conditions and/or shooting conditions can effectively distinguish the target to be detected from the interference.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes performed by the present specification and drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (12)
1. A method of visual inspection, the method comprising:
acquiring a first detection image and a second detection image of an object to be detected under different lighting conditions and/or shooting conditions;
performing mathematical operation on the brightness values of the corresponding positions of the first detection image and the second detection image so as to distinguish a target to be detected and interference on the object to be detected;
the step of acquiring a first detection image and a second detection image of an object to be detected under different lighting conditions and/or shooting conditions comprises the following steps:
setting different lighting conditions and/or shooting conditions according to the reflection characteristics of the target to be detected and the interference, so that the target to be detected and the interference can be distinguished from other areas of the object to be detected according to brightness values on one of the first detection image and the second detection image, and the interference can be distinguished from the other areas of the target to be detected and the object to be detected according to brightness values on the other one of the first detection image and the second detection image;
the step of performing mathematical operation on the brightness values of the corresponding positions of the first detection image and the second detection image to distinguish the target to be detected and the interference on the object to be detected comprises the following steps:
converting the first detection image and the second detection image into a first binary image and a second binary image by using a preset threshold segmentation condition; processing the brightness values of the corresponding positions of the first binary image and the second binary image by utilizing logic operation in a matching manner, and further distinguishing the target to be detected and interference;
wherein the disturbance comprises dust and the object to be detected comprises at least one of a scratch and a crack, or the disturbance comprises one of a scratch and a crack and the object to be detected comprises the other of a scratch and a crack.
2. The method according to claim 1, wherein the step of acquiring the first and second inspection images of the object to be inspected under different lighting and/or photographic conditions comprises:
different lighting conditions or photographing conditions are obtained by changing at least one of the position, light intensity, and illumination angle of the light source or by changing at least one of the position, exposure intensity, and photographing angle of the image pickup device.
3. The method according to claim 2, wherein the step of acquiring the first and second inspection images of the object to be inspected under different lighting and/or photographic conditions comprises:
setting light sources at different height positions relative to the object to be detected, and respectively acquiring images of the object to be detected under the irradiation of the light source arranged at a high position and the object to be detected under the irradiation of the light source arranged at a low position by utilizing image acquisition equipment to respectively obtain a first detection image and a second detection image;
the step of performing mathematical operation on the brightness values of the corresponding positions of the first detection image and the second detection image to distinguish the target to be detected and the interference on the object to be detected comprises the following steps:
and performing mathematical operation on the brightness values of the corresponding positions of the first detection image and the second detection image so as to distinguish cracks or scratches on the object to be detected from dust on the object to be detected.
4. The method of claim 3, wherein the step of acquiring the first inspection image and the second inspection image of the object to be inspected under different illumination conditions and/or photographing conditions further comprises:
and arranging the light source and the image acquisition equipment at the same side of the object to be detected, and arranging an included angle between the normal direction of the image acquisition equipment and the normal direction of the object to be detected at 15-70 degrees.
5. The method of claim 4, wherein the step of acquiring the first inspection image and the second inspection image of the object to be inspected under different illumination conditions and/or photographing conditions further comprises:
setting an included angle between a normal direction of the image acquisition device and a normal direction of the light source arranged at a high position to be less than 10 degrees, and setting an included angle between the normal direction of the image acquisition device and a normal direction of the light source arranged at a low position to be more than 30 degrees.
6. The method according to claim 1, wherein the step of acquiring the first and second inspection images of the object to be inspected under different lighting and/or photographic conditions comprises:
respectively acquiring images of the object to be detected under the irradiation of different light intensities by using image acquisition equipment to respectively obtain a first detection image and a second detection image;
the step of performing mathematical operation on the brightness values of the corresponding positions of the first detection image and the second detection image to distinguish the target to be detected and the interference on the object to be detected comprises the following steps:
and performing mathematical operation on the brightness values of the corresponding positions of the first detection image and the second detection image so as to distinguish the scratch and the crack on the object to be detected.
7. A visual detection system is characterized by comprising a light source, image acquisition equipment and a processor, wherein the light source is matched with the image acquisition equipment so as to obtain a first detection image and a second detection image of an object to be detected under different illumination conditions and/or shooting conditions, and the processor performs mathematical operation on brightness values of corresponding positions of the first detection image and the second detection image so as to distinguish a target to be detected and interference on the object to be detected;
the illumination condition and/or the shooting condition are/is set according to the reflection characteristics of the target to be detected and the interference, so that the target to be detected and the interference can be distinguished from other areas of the object to be detected according to the brightness value on one of the first detection image and the second detection image, and the interference can be distinguished from the target to be detected and other areas of the object to be detected according to the brightness value on the other one of the first detection image and the second detection image;
the processor converts the first detection image and the second detection image into a first binarization image and a second binarization image by using a preset threshold segmentation condition; processing the brightness values of the corresponding positions of the first binary image and the second binary image by utilizing logic operation in a matching manner, and further distinguishing the target to be detected and interference;
wherein the disturbance comprises dust and the object to be detected comprises at least one of a scratch and a crack, or the disturbance comprises one of a scratch and a crack and the object to be detected comprises the other of a scratch and a crack.
8. The system according to claim 7, wherein different lighting conditions or photographing conditions are obtained by changing at least one of 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 photographing angle of the image capturing apparatus.
9. The system according to claim 8, wherein the light source is disposed at different height positions relative to the object to be detected, the image capturing device respectively captures images of the object to be detected under the illumination of the light source disposed at a high position and the object to be detected under the illumination of the light source disposed at a low position to respectively obtain a first detection image and a second detection image, and the processor mathematically operates brightness values of corresponding positions of the first detection image and the second detection image to distinguish a crack or scratch on the object to be detected from dust on the object to be detected.
10. The system according to claim 9, wherein the light source and the image capturing device are disposed on the same side of the object to be detected, and an included 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.
11. The system according to claim 10, wherein an angle between a normal direction of the image capturing device and a normal direction of the light source in an upper position is set to be less than 10 degrees, and an angle between a normal direction of the image capturing device and a normal direction of the light source in a lower position is set to be greater than 30 degrees.
12. The system according to claim 7, wherein the image capturing device respectively captures images of the object to be detected under different light intensities of the light source to obtain a first detection image and a second detection image, and the processor performs mathematical operation on brightness values of corresponding positions of the first detection image and the second detection image to distinguish the scratch and the crack on the object to be detected.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2017/078962 WO2018176370A1 (en) | 2017-03-31 | 2017-03-31 | Visual inspection system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107980094A CN107980094A (en) | 2018-05-01 |
| CN107980094B true CN107980094B (en) | 2021-02-26 |
Family
ID=62006190
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201780001564.9A Active CN107980094B (en) | 2017-03-31 | 2017-03-31 | Visual detection system and method |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN107980094B (en) |
| WO (1) | WO2018176370A1 (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109580631B (en) * | 2018-11-22 | 2021-04-20 | 成都市鹰诺实业有限公司 | Method for judging surface difference of measured object by using light intensity |
| CN113466233A (en) * | 2020-03-31 | 2021-10-01 | 北京配天技术有限公司 | Visual inspection method, visual inspection apparatus, and computer storage medium |
| CN111879791B (en) * | 2020-07-30 | 2023-06-20 | 西湖大学 | Machine vision system and method for enhancing raised features on pattern surface |
Family Cites Families (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US3866054A (en) * | 1973-09-28 | 1975-02-11 | Du Pont | Defect size discriminator circuit for web inspection system |
| US6256093B1 (en) * | 1998-06-25 | 2001-07-03 | Applied Materials, Inc. | On-the-fly automatic defect classification for substrates using signal attributes |
| JPWO2001041068A1 (en) * | 1999-11-29 | 2004-01-08 | オリンパス光学工業株式会社 | Defect inspection system |
| CN1955717B (en) * | 2000-09-10 | 2011-04-20 | 奥博泰克有限公司 | Reducing of error alarm in PCB detection |
| JP2007240432A (en) * | 2006-03-10 | 2007-09-20 | Omron Corp | Defect inspection device and defect inspection method |
| US7589869B2 (en) * | 2006-04-28 | 2009-09-15 | Electro Scientific Industries, Inc. | Adjusting image quality using multi-wavelength light |
| KR100894684B1 (en) * | 2007-04-26 | 2009-04-24 | 주식회사 엔케이스틸 | Inspection Apparatus and Method for Dectecting Surface Defects of Metal Plate Using Vision System and Laser Depth Profiler |
| US8223327B2 (en) * | 2009-01-26 | 2012-07-17 | Kla-Tencor Corp. | Systems and methods for detecting defects on a wafer |
| CN101937563B (en) * | 2009-07-03 | 2012-05-30 | 深圳泰山在线科技有限公司 | Target detection method and equipment and image acquisition device thereof |
| KR101377098B1 (en) * | 2011-12-19 | 2014-03-25 | (주)포스코 | Apparatus for detecting the surface of roll in annealing furnace |
| CN103245670B (en) * | 2013-05-06 | 2015-07-22 | 深圳科瑞技术股份有限公司 | Defect detection device and defect detection method of optical element |
| JP6328468B2 (en) * | 2014-03-31 | 2018-05-23 | 株式会社日立ハイテクノロジーズ | Defect inspection apparatus and inspection method |
| CN104240204B (en) * | 2014-09-11 | 2017-02-15 | 镇江苏仪德科技有限公司 | Solar silicon wafer and battery piece counting method based on image processing |
| CN104586404A (en) * | 2015-01-27 | 2015-05-06 | 深圳泰山在线科技有限公司 | Method and system for identifying posture of fitness and health monitoring |
| CN106504215A (en) * | 2016-11-10 | 2017-03-15 | 中国科学院长春光学精密机械与物理研究所 | A kind of method and device of image enhaucament |
-
2017
- 2017-03-31 WO PCT/CN2017/078962 patent/WO2018176370A1/en active Application Filing
- 2017-03-31 CN CN201780001564.9A patent/CN107980094B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN107980094A (en) | 2018-05-01 |
| WO2018176370A1 (en) | 2018-10-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TWI238366B (en) | Image processing method for appearance inspection | |
| CN107980094B (en) | Visual detection system and method | |
| JP2009145285A (en) | Defect detecting method and defect detecting apparatus | |
| JP2013185862A (en) | Defect inspection device and defect inspection method | |
| JP2007285754A (en) | Flaw detection method and flaw detector | |
| CN114897847A (en) | Image processing method and device, computer readable storage medium and electronic device | |
| JP6121253B2 (en) | Work surface defect inspection system | |
| JP2014020926A (en) | Surface defect inspection device and surface defect inspection method | |
| JP2001184510A (en) | Defect detecting method | |
| JP5088165B2 (en) | Defect detection method and defect detection apparatus | |
| JP6812118B2 (en) | Defect detector, defect detection method and program | |
| JP2006258713A (en) | Method and apparatus for detecting stain defect | |
| JP2005165387A (en) | Method and device for detecting stripe defective of picture and display device | |
| JP2008014842A (en) | Method and apparatus for detecting stain defects | |
| JP6628185B2 (en) | Inspection method for transparent objects | |
| JP2009281759A (en) | Color filter defect inspection method, inspection apparatus, and color filter manufacturing method using it | |
| JP2008070242A (en) | Noise-removing method and apparatus, unevenness defect inspecting method and apparatus | |
| KR101993654B1 (en) | Inspecting apparatus mura of display panel and method thereof | |
| JP2006226837A (en) | Method and apparatus for inspecting stain | |
| US20200151863A1 (en) | Inspection apparatus and inspection method | |
| JP6811540B2 (en) | Defect detector, defect detection method and program | |
| JP2008171142A (en) | Spot defect detection method and device | |
| JP5239275B2 (en) | Defect detection method and defect detection apparatus | |
| JP2007285868A (en) | Luminance gradient detection method, flaw detection method, luminance gradient detector and flaw detector | |
| JP6623545B2 (en) | Inspection system, inspection method, program, and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |