CN107980094A - A kind of vision detection system and method - Google Patents
A kind of vision detection system and method Download PDFInfo
- Publication number
- CN107980094A CN107980094A CN201780001564.9A CN201780001564A CN107980094A CN 107980094 A CN107980094 A CN 107980094A CN 201780001564 A CN201780001564 A CN 201780001564A CN 107980094 A CN107980094 A CN 107980094A
- Authority
- CN
- China
- Prior art keywords
- detection image
- image
- examined object
- detected
- interference
- 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.)
- Granted
Links
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
Landscapes
- Chemical & Material Sciences (AREA)
- Biochemistry (AREA)
- Pathology (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Immunology (AREA)
- Analytical Chemistry (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
A kind of vision detection system and method.This method includes：The first detection image (21,31) and the second detection image (22,32) (S11) of examined object (14) are obtained under different lighting conditions and/or shooting condition；Mathematical operations are carried out to the brightness value of the correspondence position of the first detection image (21,31) and the second detection image (22,32), and then distinguish the target to be detected in examined object (14) and interference (S12).Target to be detected and interference are effectively distinguished using the synthesis of the two width detection images obtained under different lighting conditions and/or shooting condition.
Description
Technical field
The present embodiments relate to field of visual inspection, more particularly to a kind of vision detection system and method.
Background technology
Industrial vision detection carries out image generally by examined object progress Image Acquisition, and to the image of collection
Identification, and predetermined target is identified from the image of examined object, such as the defects of cut, slight crack.At present, regarded in industry
Feel in detection process and generally face two problems：One is that examined object surface easily deposits dust, and target to be detected is frequent
Easily influenced be subject to dust, it is therefore desirable to be detected under dustfree environment, add testing cost；The other is thing to be detected
Multiple defect is generally comprised on body, it is difficult to which different defects are effectively distinguished.
The content of the invention
In order at least partly solve problem above, the embodiment of the present invention proposes a kind of visible detection method, this method bag
Include：The first detection image and the second detection image of examined object are obtained under different lighting conditions and/or shooting condition；
Mathematical operations are carried out to the brightness value of the correspondence position of the first detection image and the second detection image, and then distinguish examined object
On target to be detected and interference.
Wherein, the first detection image and the of examined object is obtained under different lighting conditions and/or shooting condition
The step of two detection images, includes：According to the target to be detected lighting condition different with the reflection characteristic setting of interference and/or bat
Condition is taken the photograph, so that there is some difference for the target to be detected after mathematical operations and the brightness value of interference.
Wherein, the first detection image and the of examined object is obtained under different lighting conditions and/or shooting condition
The step of two detection images, includes：According to the target to be detected lighting condition different with the reflection characteristic setting of interference and/or bat
Condition is taken the photograph, so that can be according to brightness value to mesh to be detected on one in the first detection image and the second detection image
Mark and interference and other regions of examined object distinguish, and another in the first detection image and the second detection image
Can be according to brightness value to disturbing other regions with target to be detected and examined object to distinguish on a.
Wherein, mathematical operations are carried out to the brightness value of the correspondence position of the first detection image and the second detection image, and then
The step of distinguishing the target to be detected in examined object and interference includes：Utilize default Threshold segmentation condition and logical operation
Coordinate and the brightness value of the correspondence position of the first detection image and the second detection image is handled, and then distinguish target to be detected
And interference.
Wherein, interference includes dust, and target to be detected includes at least one in cut and slight crack, or interference includes stroke
One in trace and slight crack, target to be detected includes another in cut and slight crack.
Wherein, the first detection image and the of examined object is obtained under different lighting conditions and/or shooting condition
The step of two detection images, includes：By varying at least one in the position of light source, light intensity and irradiating angle or by changing
Become in the position of image capture device, exposure intensity and shooting angle at least one obtains different lighting conditions or shooting
Condition.
Wherein, the first detection image and the of examined object is obtained under different lighting conditions and/or shooting condition
The step of two detection images, includes：Light source is set with different height position relative to examined object, utilizes image capture device
Examined object under the light source irradiation that examined object and low level under being irradiated respectively to high-level installed light source are set carries out
Image Acquisition obtains the first detection image and the second detection image respectively；To pair of the first detection image and the second detection image
The step of answering the brightness value of position to carry out mathematical operations, and then distinguishing the target to be detected in examined object and interference includes：
Mathematical operations are carried out to the brightness value of the correspondence position of the first detection image and the second detection image, and then distinguish examined object
On slight crack or the dust in cut and examined object.
Wherein, the first detection image and the of examined object is obtained under different lighting conditions and/or shooting condition
The step of two detection images, further comprises：Light source and image capture device are arranged to the same side of examined object, and will
Angle between the normal direction of image capture device and the normal direction of examined object is arranged between 15 degree of -70 degree.
Wherein, the first detection image and the of examined object is obtained under different lighting conditions and/or shooting condition
The step of two detection images, further comprises：By the normal direction of image capture device and the normal direction of high-level installed light source
Between angle be set smaller than 10 degree, and the normal direction for the light source that the normal direction of image capture device and low level are set
Between angle be set greater than 30 degree.
Wherein, the first detection image and the of examined object is obtained under different lighting conditions and/or shooting condition
The step of two detection images, includes：Examined object under being irradiated respectively to different light intensity using image capture device carries out image
Gather to obtain the first detection image and the second detection image respectively；To the correspondence position of the first detection image and the second detection image
The brightness value put carries out mathematical operations, and then distinguishes the target to be detected in examined object and include the step of interference：To
The brightness value of the correspondence position of one detection image and the second detection image carries out mathematical operations, and then distinguishes in examined object
Cut and slight crack.
In order at least partly solve problem above, the embodiment of the present invention proposes a kind of vision detection system, the system bag
Light source, image capture device and processor are included, wherein light source and image capture device coordinates, and then in different lighting conditions
And/or the first detection image and the second detection image of examined object are obtained under shooting condition, processor schemes the first detection
The brightness value of picture and the correspondence position of the second detection image carries out mathematical operations, and then distinguishes the mesh to be detected in examined object
Mark and interference.
Wherein, lighting condition and/or shooting condition are configured according to the reflection characteristic of target to be detected and interference, and then
So that there is some difference for target to be detected after mathematical operations and the brightness value of interference.
Wherein, lighting condition and/or shooting condition are configured according to the reflection characteristic of target to be detected and interference, and then
So that on one in the first detection image and the second detection image can according to brightness value to target to be detected and interference with
Other regions of examined object distinguish, and being capable of root on another in the first detection image and the second detection image
According to brightness value to disturbing other regions with target to be detected and examined object to distinguish.
Wherein, processor is coordinated with logical operation using default Threshold segmentation condition and the first detection image and second is examined
The brightness value of the correspondence position of altimetric image is handled, and then distinguishes target to be detected and interference.
Wherein, interference includes dust, and target to be detected includes at least one in cut and slight crack, or interference includes stroke
One in trace and slight crack, target to be detected includes another in cut and slight crack.
Wherein, adopt by varying at least one in the position of light source, light intensity and irradiating angle or by varying image
Collect in the position of equipment, exposure intensity and shooting angle at least one obtains different lighting condition or shooting condition.
Wherein, light source is configured relative to examined object with different height position, and image capture device is respectively to height
Examined object under the light source irradiation that examined object and low level under the light source irradiation that position is set are set carries out Image Acquisition
To obtain the first detection image and the second detection image, correspondence of the processor to the first detection image and the second detection image respectively
The brightness value of position carries out mathematical operations, and then distinguishes the slight crack in examined object or cut and the ash in examined object
Dirt.
Wherein, light source and image capture device are arranged at the same side of examined object, and the normal of image capture device
Angle between direction and the normal direction of examined object is arranged between 15 degree of -70 degree.
Wherein, the angle between the normal direction of image capture device and the normal direction of high-level installed light source is arranged to
Less than 10 degree, and the angle between the normal direction of image capture device and the normal direction of the light source of low level setting is arranged to greatly
In 30 degree.
Wherein, it is next to carry out Image Acquisition to the examined object under the different light intensity irradiation of light source respectively for image capture device
The first detection image and the second detection image, correspondence position of the processor to the first detection image and the second detection image are obtained respectively
The brightness value put carries out mathematical operations, and then distinguishes the cut and slight crack in examined object.
By the above-mentioned means, utilize the two width detection images obtained under different lighting conditions and/or shooting condition
Integrate effectively to be distinguished to target to be detected and interference.
Brief description of the drawings
Fig. 1 is the structure diagram of vision detection system according to an embodiment of the invention；
Fig. 2 is the flow diagram of visible detection method according to an embodiment of the invention；
Fig. 3 is the schematic diagram of the acquisition modes of the first detection image according to an embodiment of the invention；
Fig. 4 is the schematic diagram of the acquisition modes of the second detection image according to an embodiment of the invention；
Fig. 5 is according to an embodiment of the invention to carry out logical operation to the first detection image and the second detection image and show
It is intended to；
Fig. 6 is according to another embodiment of the present invention to the first detection image and the progress logical operation of the second detection image
Schematic diagram.
Embodiment
Below in conjunction with the attached drawing in the embodiment of the present invention, the technical solution in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only the part of the embodiment of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other without making creative work
Embodiment, belongs to the scope of protection of the invention.
Referring to Fig. 1, Fig. 1 is the structure diagram of vision detection system according to an embodiment of the invention.The present embodiment
Vision detection system includes light source 111,112, image capture device 12 and processor 13.Wherein, light source 111,112 is for being
Examined object 14 provides illumination, and the examined object 14 that image capture device 12 is used under being irradiated to light source 111,112 carries out
Image Acquisition, and processor 13 is then identified according to 12 acquired image of image capture device, and extract thing to be detected
Target to be detected on body 14.
With further reference to Fig. 2, Fig. 2 is the flow diagram of visible detection method according to an embodiment of the invention.At this
In embodiment, a kind of visible detection method is proposed based on the vision detection system shown in Fig. 1, specifically includes following steps：
Step S11, under different lighting conditions and/or shooting condition obtain examined object the first detection image and
Second detection image；
Step S12, mathematical operations are carried out to the brightness value of the correspondence position of the first detection image and the second detection image, into
And distinguish target to be detected and interference in examined object.
Further, in step s 11, according to the target to be detected lighting condition different with the reflection characteristic setting of interference
And/or shooting condition, so that there are one for the target to be detected after mathematical operations and the brightness value of interference in step s 12
Determine difference.Furthermore, it is understood that according to the target to be detected lighting condition different with the reflection characteristic setting of interference and/or shooting bar
Part so that on one in the first detection image and the second detection image can according to brightness value to target to be detected and
Interference and other regions of examined object distinguish, and on another in the first detection image and the second detection image
Can be according to brightness value to disturbing other regions with target to be detected and examined object to distinguish.Thus since, in step
In rapid S12, it can be examined according to other regions of target to be detected, interference and examined object in above-mentioned first detection image and second
Brightness value on altimetric image sets appropriate mathematical operations rule, so that target to be detected and interference after mathematical operations
Brightness value there is some difference.
The set-up mode of specific lighting condition and shooting condition is by varying position, light intensity and the photograph of light source 111,112
At least one in firing angle degree obtains different lighting conditions, or position by varying image capture device 12, exposure
At least one shooting condition in intensity and shooting angle.It is worth noting that, two light sources 111,112 are shown in Fig. 1,
But during specific implementation, the quantity of light source is not limited, such as can only set a light source, and by the light source
Adjusted into row position, light intensity and irradiating angle to obtain different lighting conditions.Equally, image capture device 12 and processor
13 quantity is also from the limitation shown in Fig. 1.
In step s 12, coordinate using default Threshold segmentation condition and logical operation to the first detection image and the
The brightness value of the correspondence position of two detection images is handled, and then target to be detected and interference are distinguished.For example, pass through
Default Threshold segmentation condition carries out the first detection image and the second detection image binaryzation, then based on two binaryzations of acquisition
Target to be detected and interference are distinguished according to appropriate logical operation in image.It is of course also possible to directly to the first detection image and
Second detection image carries out logical operation, then by default Threshold segmentation condition come to the image after computing into row threshold division
To distinguish target to be detected and interference.
In the present embodiment, interference can include dust, target to be detected include it is at least one in cut and slight crack, or
Person's interference includes one in cut and slight crack, and target to be detected includes another in cut and slight crack.
Lighting condition, shooting condition and Threshold segmentation condition, logic fortune is described in detail below in conjunction with instantiation
The specific set-up mode calculated.Certainly, those skilled in the art can be according to be detected under the enlightenment of related embodiment of the present invention
Target and the actual conditions of interference accordingly set the above.
With further reference to Fig. 3-5, will hereafter be retouched in detail exemplified by how distinguishing cut or slight crack with dust
State.
As shown in Figure 1, in the present embodiment, relative to examined object 14 with different height position set light source 111,
112.Light source 111,112 as described above can be same light source.Wherein, imitated to obtain relatively good detection
Light source 111,112 and image capture device 12, are arranged at the same side of examined object 14, i.e., shown in dotted line B1, B2 by fruit
The outside of the view field on the surface to be detected of examined object 14, and by the normal direction A2 of image capture device 12 with it is to be checked
The angle surveyed between the normal direction A1 of object 14 is arranged between 15 degree of -70 degree.Further, by the method for image capture device 12
Angle between line direction A2 and the normal direction A3 of high-level installed light source 111 is set smaller than 10 degree, and by Image Acquisition
Angle between the normal direction A4 for the light source 112 that the normal direction A2 and low level of equipment 12 are set is set greater than 30 degree.Method
Line direction A1 is specially the vertical direction on the surface to be detected of detection object 14, and normal direction A2, A3 and A4 are specially to scheme respectively
As collecting device 12, the optical axis or major axes orientation of light source 111,112.
Further as shown in figure 3, using image capture device 12 to the thing to be detected under the irradiation of high-level installed light source 111
Body 14 carries out Image Acquisition to obtain the first detection image 21.As shown in figure 4, low level is set using image capture device 12
Examined object 14 under light source 112 irradiates carries out Image Acquisition to obtain the second detection image 22.
Since cut and slight crack have face reflection characteristic, and dust has diffusing characteristic diffuser.Therefore, in the first detection image
In 21, cut 141 and slight crack 142 (being represented respectively with heavy line in the first detection image 21) (are detected with dust 143 first
Represented respectively with fine line in image 21) relative to other region (cut 141, slight crack 142 and dusts of examined object 14
Region beyond 143) highlighted state is presented.That is, the luminance difference between cut 141, slight crack 142 and dust 143
Smaller, the luminance difference between cut 141, slight crack 142 and dust 143 and other regions of examined object 14 is larger, and then
Cut 141, slight crack 142 and dust 143 and other regions of examined object 14 can be distinguished by brightness value, such as
Pass through Threshold segmentation mode.In the second detection image 22, cut 141 and slight crack 142 (in the second detection image 22 respectively with
Thick dashed line represents) it is presented low bright state (that is, brightness approaches) relative to other regions of examined object 14, and dust 143 (
Represented respectively with fine line in second detection image 22) highlighted state is still presented relative to other regions of examined object 14.
That is, the luminance difference between cut 141 and slight crack 142 and dust 143 is larger, while cut 141 and slight crack 142 are with treating
The luminance difference in other regions of detection object 14 is smaller, dust 143 and the luminance difference in other regions of examined object 14
It is larger, and then can be carried out other regions of dust 143 and cut 141, slight crack 142 and examined object 14 by brightness value
Distinguish.
Further as shown in figure 5, in the first detection image 21 and the second detection image 22, cut 141,142 and of slight crack
The brightness value of dust 143 is there are above-mentioned difference, by setting default Threshold segmentation condition to the first detection image 21 and second
Detection image 22 carries out binary conversion treatment, can be by the cut 141 in the first detection image 21 and slight crack 142 and dust 143
Brightness value puts 1, and by the brightness value 0 in other regions of examined object, or vice versa, and then obtain as shown in Figure 5
First binary image 23.Meanwhile the brightness value of the dust 143 in the second detection image 22 can be put to 1, and by thing to be detected
The brightness value in other regions of body 14, cut 141 and slight crack 142 is set to 0, or vice versa, and then obtains as shown in Figure 5
Two binary images 24.
Further, by being fitted to the brightness value of 24 correspondence position of the first binary image 23 and the second binary image
When logical operation (for example, with or computing or XOR operation), can such as scheme from corresponding cut 141 and slight crack 142 is extracted
Shown in final image 25 in 5, and then cut 141 and slight crack 142 are distinguished with dust 143.
In other embodiments, cut 141 and slight crack can be extracted by other logical operations and Threshold segmentation condition
142.For example, by logical operation directly by the first detection image 21 and the brightness value phase of the correspondence position of the second detection image 22
Subtract, at this time due to cut 141 and slight crack 142 the first detection image 21 and the second detection image 22 present respectively be highlighted and
Low bright display, it is larger to subtract each other the luminance difference of acquisition, and dust 143 is in the first detection image 21 and the second detection image 22
Now it is highlighted, the luminance difference for subtracting each other acquisition is smaller.Therefore, by setting appropriate Threshold segmentation condition, retain difference compared with
Big part, and ignore the less part of difference, it can equally extract cut 141 and slight crack 142.
In the present embodiment, used logical operation is configured according to actual conditions, is included but not limited to or is transported
Calculate or XOR operation, can be with or, other operations such as addition, multiplication.
It is noted that after completing above-mentioned detection in the side of examined object 14, can be by rotating examined object
14th, rotate light source 111,112 and image capture device 12 or utilize other light sources and image capture device from examined object
14 opposite side repeats above-mentioned detection process, and then avoids missing inspection.
Further combined with Fig. 6, will be hereafter described in detail exemplified by how cut is distinguished with slight crack.
In the present embodiment, the examined object 14 under being irradiated respectively to different light intensity using image capture device 12 is carried out
Image Acquisition obtains the first detection image 31 and the second detection image 32 respectively, and further utilizes 31 He of the first detection image
Second detection image 32 distinguishes the cut in examined object 14 with slight crack.
For example, under the irradiation of relatively small light intensity in the first detection image 31 for being formed, cut 141 and slight crack 142 are (the
Represented respectively with heavy line in one detection image 31) highlighted state is presented relative to other regions of examined object 14, i.e.,
The luminance difference of cut 141 and slight crack 142 is smaller, at the same other regions of cut 141 and slight crack 142 and examined object 14 it
Between luminance difference it is larger, and then brightness value can be passed through and distinguish cut 141 and slight crack 142 and other areas of examined object 14
Domain.In the second detection image 32 formed under the irradiation of relatively large light intensity, cut 141 is (in the second detection image 32 respectively
Represented with thick dashed line) low bright state is presented relative to other regions of examined object 14, and slight crack 142 is relative to thing to be detected
Highlighted state is still presented in other regions of body 14, i.e., the luminance difference between cut 141 and slight crack 142 is larger, while cut 141
It is smaller with the luminance difference in other regions of examined object 14, slight crack 142 and the brightness in other regions of examined object 14
Differ greatly, and then slight crack 142 and cut 141 and other regions of examined object 14 can be distinguished according to brightness value.
Therefore, reference and similar mode described above, can be by setting appropriate Threshold segmentation condition by the first detection
31 and second detection image 32 of image carries out binaryzation, and then obtains the first binary image 33 and the second binary image 34,
And cut 141, Jin Ershi is extracted from the first binary image 33 and the second binary image 34 by appropriate logical operation
The differentiation of existing slight crack 142 and cut 141.Of course, it is possible to after directly subtracting each other to the first detection image 31 and the second detection image 32
Threshold segmentation condition is recycled to extract cut 141.
Further as shown in Figure 1, the embodiment of the present invention further provides a kind of vision detection system, which includes light
Source 111,112, image capture device 12 and processor 13, wherein light source 111,112 and image capture device 12 coordinate, Jin Er
The first detection image and the second detection image of examined object 14, place are obtained under different lighting conditions and/or shooting condition
Manage device 13 and mathematical operations are carried out to the brightness value of the correspondence position of the first detection image and the second detection image, and then distinguish to be checked
Survey the target to be detected on object 14 and interference.
In the present embodiment, above-mentioned lighting condition and/or shooting condition are according to target to be detected and the reflection characteristic of interference
It is configured, so that there is some difference for the target to be detected after mathematical operations and the brightness value of interference.Further, shine
Bright condition and/or shooting condition are configured according to the reflection characteristic of target to be detected and interference, so that in the first detection
Can be according to brightness value to target to be detected and interference and examined object 14 on one in image and the second detection image
Other regions distinguish, and can be according to brightness value to dry on another in the first detection image and the second detection image
Disturb and distinguished with other regions of target to be detected and examined object 14.Lighting condition and/or the specific of shooting condition set
The mode of putting can be at least one in the position by varying light source 111,112, light intensity and irradiating angle or by varying
At least one in the position of image capture device 12, exposure intensity and shooting angle obtains different lighting conditions or shooting
Condition.
In the present embodiment, processor 13 is coordinated with logical operation using default Threshold segmentation condition and the first detection is schemed
The brightness value of picture and the correspondence position of the second detection image is handled, and then distinguishes target to be detected and interference.Wherein, disturb
Including dust, target to be detected includes at least one in cut and slight crack, or interference includes one in cut and slight crack,
Target to be detected includes another in cut and slight crack.
In a specific implementation, light source 111,112 is set relative to examined object 14 with different height position
Put.And in order to get more preferable detection result, light source 111,112 and image capture device 12 are arranged at examined object 14
The same side, and angle between the normal direction A2 of image capture device 12 and the normal direction A1 of examined object 14 is set
Between 15 degree of -70 degree.Further, the normal side of the normal direction A2 of image capture device 12 and high-level installed light source 111
10 degree, and the light source 112 that the normal direction A2 of image capture device 12 is set with low level are set smaller than to the angle between A3
Normal direction A4 between angle be set greater than 30 degree.
What image capture device 12 was respectively set the examined object 14 under the irradiation of high-level installed light source 111 and low level
Examined object 14 under light source 112 irradiates carries out Image Acquisition to obtain the first detection image and the second detection image respectively,
Processor 13 carries out mathematical operations to the brightness value of the correspondence position of the first detection image and the second detection image, and then distinguishes and treat
Slight crack or cut in detection object 14 and the dust in examined object 14.
In another specific implementation, image capture device 12 under the different light intensity irradiation of light source 111 respectively to treating
Detection object 14 carries out Image Acquisition to obtain the first detection image and the second detection image respectively, and processor 13 is detected to first
The brightness value of image and the correspondence position of the second detection image carries out mathematical operations, and then distinguishes the cut in examined object 14
With slight crack.
On said elements and its operation principle can refer to above with respect to visible detection method specific embodiment it is detailed
Description, details are not described herein.
In conclusion it should be readily apparent to one skilled in the art that obtained using under different lighting conditions and/or shooting condition
The synthesis of the two width detection images taken carries out the extraction of target to be detected, can carry out effective district to target to be detected and interference
Point.
The foregoing is merely embodiments of the present invention, are not intended to limit the scope of the invention, every to utilize this
The equivalent structure or equivalent flow shift that description of the invention and accompanying drawing content are made, it is relevant to be directly or indirectly used in other
Technical field, is included within the scope of the present invention.
Claims (20)
- A kind of 1. visible detection method, it is characterised in that the described method includes：The first detection image and the second detection figure of examined object are obtained under different lighting conditions and/or shooting condition Picture；Mathematical operations, Jin Erqu are carried out to the brightness value of the correspondence position of first detection image and second detection image Divide the target to be detected in the examined object and interference.
- It is 2. according to the method described in claim 1, it is characterized in that, described under different lighting conditions and/or shooting condition The step of the first detection image and the second detection image for obtaining examined object, includes：Different lighting condition and/or shooting condition are set according to the target to be detected and the reflection characteristic of the interference, into And cause the target to be detected after the mathematical operations and the brightness value of the interference there is some difference.
- It is 3. according to the method described in claim 2, it is characterized in that, described under different lighting conditions and/or shooting condition The step of the first detection image and the second detection image for obtaining examined object, includes：Different lighting condition and/or shooting condition are set according to the target to be detected and the reflection characteristic of the interference, into And cause can be according to brightness value to described to be checked on one in first detection image and second detection image Survey target and the interference and other regions of the examined object distinguish, and in first detection image and described Can be according to brightness value to the interference and the target to be detected and described to be detected on another in second detection image Other regions of object distinguish.
- 4. according to claim 1-3 any one of them methods, it is characterised in that described to first detection image and described The brightness value of the correspondence position of second detection image carries out mathematical operations, and then distinguishes the mesh to be detected in the examined object The step of mark and interference, includes：Coordinated using default Threshold segmentation condition and logical operation to first detection image and second detection image The brightness value of correspondence position handled, and then distinguish the target to be detected and interference.
- 5. according to the method described in claim 1, it is characterized in that, the interference includes dust, the target to be detected includes It is at least one in cut and slight crack, or the interference includes one in cut and slight crack, the target to be detected includes Another in cut and slight crack.
- It is 6. according to the method described in claim 5, it is characterized in that, described under different lighting conditions and/or shooting condition The step of the first detection image and the second detection image for obtaining examined object, includes：By varying at least one or by varying image capture device position in the position of light source, light intensity and irradiating angle Put, at least one in exposure intensity and shooting angle obtains different lighting condition or shooting condition.
- It is 7. according to the method described in claim 6, it is characterized in that, described under different lighting conditions and/or shooting condition The step of the first detection image and the second detection image for obtaining examined object, includes：Light source is set with different height position relative to the examined object, a high position is set respectively using image capture device The lower examined object of light source irradiation and the light source irradiation that sets of low level under examined object progress image adopt Collect to obtain the first detection image and the second detection image respectively；The brightness value of the correspondence position to first detection image and second detection image carries out mathematical operations, into And the step of distinguishing the target to be detected in the examined object and interference, includes：Mathematical operations, Jin Erqu are carried out to the brightness value of the correspondence position of first detection image and second detection image Divide the slight crack in the examined object or cut and the dust in the examined object.
- It is 8. the method according to the description of claim 7 is characterized in that described under different lighting conditions and/or shooting condition The step of the first detection image and the second detection image for obtaining examined object, further comprises：The light source and described image collecting device are arranged to the same side of the examined object, and described image is gathered Angle between the normal direction of the normal direction of equipment and the examined object is arranged between 15 degree of -70 degree.
- It is 9. according to the method described in claim 8, it is characterized in that, described under different lighting conditions and/or shooting condition The step of the first detection image and the second detection image for obtaining examined object, further comprises：Angle between the normal direction of described image collecting device and the normal direction of the high-level installed light source is set Into less than 10 degree, and between the normal direction for the light source that the normal direction of described image collecting device and low level are set Angle is set greater than 30 degree.
- It is 10. according to the method described in claim 1, it is characterized in that, described under different lighting conditions and/or shooting condition The step of the first detection image and the second detection image for obtaining examined object, includes：The examined object under being irradiated respectively to different light intensity using image capture device carries out Image Acquisition to obtain respectively Obtain the first detection image and the second detection image；The brightness value of the correspondence position to first detection image and second detection image carries out mathematical operations, into And the step of distinguishing the target to be detected in the examined object and interference, includes：Mathematical operations, Jin Erqu are carried out to the brightness value of the correspondence position of first detection image and second detection image Divide the cut and slight crack in the examined object.
- A kind of 11. vision detection system, it is characterised in that the system comprises light source, image capture device and processor, wherein The light source and described image collecting device coordinate, and then obtain under different lighting conditions and/or shooting condition to be detected The first detection image and the second detection image of object, the processor scheme first detection image and second detection The brightness value of the correspondence position of picture carries out mathematical operations, and then distinguishes the target to be detected in the examined object and interference.
- 12. system according to claim 11, it is characterised in that the lighting condition and/or shooting condition are according to Target to be detected and the reflection characteristic of the interference are configured, so that the mesh to be detected after the mathematical operations There is some difference for mark and the brightness value of the interference.
- 13. system according to claim 12, it is characterised in that the lighting condition and/or shooting condition are according to Target to be detected and the reflection characteristic of the interference are configured, so that in first detection image and second inspection Can be according to brightness value to the target to be detected and its of the interference and the examined object on one in altimetric image He distinguishes in region, and can be according to brightness on another in first detection image and second detection image Value distinguishes the interference and other regions of the target to be detected and the examined object.
- 14. according to claim 11-13 any one of them systems, it is characterised in that the processor utilizes default threshold value Segmentation condition coordinates the brightness value to the correspondence position of first detection image and second detection image with logical operation Handled, and then distinguish the target to be detected and interference.
- 15. system according to claim 11, it is characterised in that the interference includes dust, the target bag to be detected Include at least one in cut and slight crack, or the interference includes one in cut and slight crack, the target bag to be detected Include another in cut and slight crack.
- 16. system according to claim 15, it is characterised in that by varying the position of the light source, light intensity and irradiation In at least one or position by varying described image collecting device, exposure intensity and shooting angle in angle at least One obtains different lighting condition or shooting condition.
- 17. system according to claim 16, it is characterised in that the light source is relative to the examined object with difference Height and position is configured, described image collecting device respectively the examined object lower to the irradiation of high-level installed light source with The examined object under the light source irradiation that low level is set carries out Image Acquisition to obtain the first detection image and second respectively Detection image, the processor carry out the brightness value of the correspondence position of first detection image and second detection image Mathematical operations, and then distinguish the slight crack in the examined object or cut and the dust in the examined object.
- 18. system according to claim 17, it is characterised in that the light source and described image collecting device are arranged at institute State the same side of examined object, and the normal direction of the normal direction of described image collecting device and the examined object it Between angle be arranged on 15 degree -70 degree between.
- 19. system according to claim 18, it is characterised in that the normal direction of described image collecting device is set with a high position Angle between the normal direction for the light source put is set smaller than 10 degree, and the normal direction of described image collecting device with Angle between the normal direction for the light source that low level is set is set greater than 30 degree.
- 20. system according to claim 11, it is characterised in that described image collecting device respectively to the light source not The examined object under intense irradiation of sharing the same light carries out Image Acquisition to obtain the first detection image and the second detection image respectively, The processor carries out mathematical operations to the brightness value of the correspondence position of first detection image and second detection image, And then distinguish the cut and slight crack in the examined object.
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 true CN107980094A (en) | 2018-05-01 |
| CN107980094B 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) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109580631A (en) * | 2018-11-22 | 2019-04-05 | 成都市鹰诺实业有限公司 | A method of measured object surface differences are determined using light intensity |
| CN111879791A (en) * | 2020-07-30 | 2020-11-03 | 西湖大学 | Machine vision system and method for enhancing raised features on surface of pattern |
| 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 |
Citations (13)
| 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 |
| EP1090284A1 (en) * | 1998-06-25 | 2001-04-11 | Applied Materials, Inc. | Wafer defect classification |
| CN1339140A (en) * | 1999-11-29 | 2002-03-06 | 奥林巴斯光学工业株式会社 | Defect inspecting system |
| CN1468371A (en) * | 2000-09-10 | 2004-01-14 | �²�̩������˾ | Reduction of error alarm in PCB detection |
| CN101034069A (en) * | 2006-03-10 | 2007-09-12 | 欧姆龙株式会社 | Defect inspection apparatus and defect inspection method |
| KR20080096056A (en) * | 2007-04-26 | 2008-10-30 | 주식회사 엔케이스틸 | Inspection apparatus and method for dectecting surface defects of metal plate using vision system and laser depth profiler |
| CN101536483A (en) * | 2006-04-28 | 2009-09-16 | Esi电子科技工业公司 | Improving image quality via multi-wavelength light |
| CN102292805A (en) * | 2009-01-26 | 2011-12-21 | 恪纳腾公司 | Systems and methods for detecting defects on a wafer |
| KR20130069905A (en) * | 2011-12-19 | 2013-06-27 | 주식회사 포스코 | Apparatus for detecting the surface of roll in annealing furnace |
| CN104240204A (en) * | 2014-09-11 | 2014-12-24 | 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 |
| WO2015151557A1 (en) * | 2014-03-31 | 2015-10-08 | 株式会社日立ハイテクノロジーズ | Defect inspection device and inspection method |
| 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 |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
-
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
Patent Citations (13)
| 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 |
| EP1090284A1 (en) * | 1998-06-25 | 2001-04-11 | Applied Materials, Inc. | Wafer defect classification |
| CN1339140A (en) * | 1999-11-29 | 2002-03-06 | 奥林巴斯光学工业株式会社 | Defect inspecting system |
| CN1468371A (en) * | 2000-09-10 | 2004-01-14 | �²�̩������˾ | Reduction of error alarm in PCB detection |
| CN101034069A (en) * | 2006-03-10 | 2007-09-12 | 欧姆龙株式会社 | Defect inspection apparatus and defect inspection method |
| CN101536483A (en) * | 2006-04-28 | 2009-09-16 | Esi电子科技工业公司 | Improving image quality via multi-wavelength light |
| KR20080096056A (en) * | 2007-04-26 | 2008-10-30 | 주식회사 엔케이스틸 | Inspection apparatus and method for dectecting surface defects of metal plate using vision system and laser depth profiler |
| CN102292805A (en) * | 2009-01-26 | 2011-12-21 | 恪纳腾公司 | Systems and methods for detecting defects on a wafer |
| KR20130069905A (en) * | 2011-12-19 | 2013-06-27 | 주식회사 포스코 | Apparatus for detecting the surface of roll in annealing furnace |
| WO2015151557A1 (en) * | 2014-03-31 | 2015-10-08 | 株式会社日立ハイテクノロジーズ | Defect inspection device and inspection method |
| CN104240204A (en) * | 2014-09-11 | 2014-12-24 | 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 |
Non-Patent Citations (3)
| Title |
|---|
| 周启刚: "《3S支撑下的山地都市区城市扩展及其地表参量响应研究》", 31 July 2015, 西南交通大学出版社 * |
| 种劲松等: "《合成孔径雷达图像海洋目标检测》", 30 September 2006, 海洋出版社 * |
| 罗亚平等: "《刑事科学技术》", 31 August 2015, 中国人民公安大学出版社 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109580631A (en) * | 2018-11-22 | 2019-04-05 | 成都市鹰诺实业有限公司 | A method of measured object surface differences are determined 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 |
| CN111879791A (en) * | 2020-07-30 | 2020-11-03 | 西湖大学 | Machine vision system and method for enhancing raised features on surface of pattern |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2018176370A1 (en) | 2018-10-04 |
| CN107980094B (en) | 2021-02-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104777174B (en) | Axial workpiece abrupt change of cross-section portion faces fatigue crack detecting system and method | |
| KR102073229B1 (en) | Surface defect detection apparatus and surface defect detection method | |
| CN109584215A (en) | A kind of online vision detection system of circuit board | |
| EP0526489B1 (en) | Inspecting garments | |
| US8610770B2 (en) | Image sensing apparatus and method for sensing target that has defective portion region | |
| CN107980094A (en) | A kind of vision detection system and method | |
| CN106650735B (en) | A kind of LED character automatic positioning recognition methods | |
| JP6231333B2 (en) | Fire detection device and fire detection method | |
| CN108648409A (en) | A kind of smog detection method and device | |
| JP2010204051A (en) | Inspection apparatus and inspection method | |
| CN111458344A (en) | Mask defect visual detection method, equipment and storage medium | |
| JP6064942B2 (en) | Surface defect detection method and surface defect detection apparatus | |
| JP2016217989A (en) | Defect inspection device and defect inspection method | |
| JP2010223598A (en) | Flaw inspection device for sheet-like article | |
| CN105427295B (en) | A kind of image-recognizing method and image identification system based on weld seam | |
| JP2004361085A (en) | Visual examination device | |
| CN114820622A (en) | Interlayer foreign matter detection method and device | |
| EP0544752A1 (en) | Inspecting garments | |
| JP6459550B2 (en) | Anomaly detection method and anomaly detection apparatus for mechanical equipment | |
| JP3531160B2 (en) | How to inspect the quality of paper cuts | |
| CN209013288U (en) | A kind of kitchen ventilator having filtering functions vision-based detection module | |
| JPH0711414B2 (en) | Glass bottle uneven thickness inspection method | |
| JP7029693B2 (en) | Image processing system, image processing method, and program | |
| KR102117697B1 (en) | Apparatus and method for surface inspection | |
| JP2002074332A (en) | Method and device for detecting sealing defect of packing material and packing body |
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 |