CN106442540A - Optical detection method and system - Google Patents
Optical detection method and system Download PDFInfo
- Publication number
- CN106442540A CN106442540A CN201610809472.0A CN201610809472A CN106442540A CN 106442540 A CN106442540 A CN 106442540A CN 201610809472 A CN201610809472 A CN 201610809472A CN 106442540 A CN106442540 A CN 106442540A
- Authority
- CN
- China
- Prior art keywords
- image
- detection
- detection image
- testing result
- abnormal
- 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.)
- Pending
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
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Testing Of Optical Devices Or Fibers (AREA)
Abstract
The invention provides an optical detection method and system. The optical detection method includes the steps that a detection image of a to-be-detected product is compared with a standard sample image corresponding to the to-be-detected product, the compared result is obtained; when the compared result indicates that the difference between the detection image and the standard sample image is larger than a preset threshold value, the detection result when the detection image is abnormal is directly obtained; when the compared result indicates that the difference between the detection image and the standard sample image is smaller than or equal to the preset threshold value, whether a detection area with the abnormal preset display parameters exists or not is detected in the detection image; when the detection area with the abnormal preset display parameters exists in the detection image, the detection result when the detection image is abnormal is obtained; otherwise, the detection result when the detection image is normal is obtained. By means of the optical detection method and system, the problems that an optical detection mode in the prior art is single, it cannot be guaranteed that the detection result is excellently and rapidly obtained can be solved.
Description
Technical field
The present invention relates to optical detective technology, refer in particular to a kind of optical detecting method and Systems for optical inspection.
Background technology
Automatic optics inspection (AOI, Automatic Optic Inspection) is a kind of recently emerging measuring technology,
Its function is as the common deficiency obtaining product after welding carries out automatic detection based on optical principle to production process.
Upon automatic detection, testing equipment passes through photographic head automatically scanning product to be detected, gathers image, at image
After reason, check the defect on product to be detected, and defect is shown or marks by display or Automatic Logos, with
Repaired for maintainer.
However, existing automated optical detection equipment is when being detected, no matter which kind of state product to be detected assumes, detection
Mode is sample contrast, form more single it is impossible to according to the different shape of product to be detected, using different detection modes,
To realize high-quality, rapidly to detect.
Content of the invention
The purpose of technical solution of the present invention is to provide a kind of optical detecting method and Systems for optical inspection, to solve existing skill
The form of art optical detection more single it is impossible to ensure high-quality, the quick problem obtaining testing result.
The present invention provides a kind of optical detecting method, including：
The detection image of product to be detected and master sample image corresponding with product to be detected are contrasted, it is right to obtain
Compare result；
Difference between described comparing result instruction described detection image and described master sample image is more than default threshold
During value, directly obtaining described detection image is abnormal testing result；
Difference between described comparing result instruction described detection image and described master sample image is less than or equal to pre-
If during threshold value, with the presence or absence of the abnormal detection zone of predetermined display parameters in detection described detection image；
When there is the detection zone of predetermined display parameters exception in described detection image, it is different for obtaining described detection image
Normal testing result；Otherwise obtaining described detection image is normal testing result.
Preferably, optical detecting method described above, wherein, the described detection image by product to be detected and with to be checked
Survey product corresponding master sample image to be contrasted, before obtaining the step of comparing result, described optical detecting method also wraps
Include：
Receive the instruction indicating the detection image of product to be detected for regular image or irregular image；
When described instruction instruction described detection image be irregular image when, obtain described comparing result step it
Afterwards, described optical detecting method also includes：
Difference between described comparing result instruction described detection image and described master sample image is less than or equal to pre-
If during threshold value, directly obtaining described detection image is normal testing result.
Preferably, optical detecting method described above, wherein, is abnormal testing result obtaining described detection image
Step after, described optical detecting method also includes：
With detection image described in the first logic value record for abnormal described testing result, and preserve described detection shadow
Picture；
After obtaining described detection image and being the step of normal testing result, described optical detecting method also includes：
With detection image described in the second logic value record for normally described testing result.
Preferably, optical detecting method described above, wherein, described optical detecting method also includes：
Obtain described testing result；
When described testing result record is for the first logic value, then export described detection image.
Preferably, optical detecting method described above, wherein, the described detection image by product to be detected and with to be checked
Survey product corresponding master sample image to be contrasted, the step obtaining comparing result includes：
By each unit range image and unit range image described in described master sample image in described detection image
Correspondence image be compared, when compare for inconsistent when, make difference value accumulating values 1, wherein said difference value initial
It is worth for 0；
According to the described difference value after adding up, obtain comparing result.
Preferably, optical detecting method described above, wherein, with the presence or absence of predetermined display in detection described detection image
The step of the detection zone of abnormal parameters includes：
Obtain the predetermined display parameter value of first module range image therein in described detection image；
Obtain predetermined apart from multiple second unit range image corresponding to described first module range image preset distance
Display parameters；
Calculate the meansigma methodss of the predetermined display parameters of multiple second unit range image；
The predetermined display parameter value of described first module range image and described meansigma methodss are compared, when described first
Difference between the predetermined display parameter value of unit range image and described meansigma methodss is more than during preset difference value it is determined that described the
It is abnormal to there are predetermined display parameters in the detection zone corresponding to one unit range image.
The present invention also provides a kind of Systems for optical inspection, in, including：
Contrast module, for entering the detection image of product to be detected and master sample image corresponding with product to be detected
Row contrast, obtains comparing result；
First determining module, between described comparing result instruction described detection image and described master sample image
Difference be more than predetermined threshold value when, directly obtain described detection image be abnormal testing result；
Detection module, for the difference between described comparing result instruction described detection image and described master sample image
Different less than or equal to predetermined threshold value when, with the presence or absence of the abnormal detection zone of predetermined display parameters in detection described detection image；
Second determining module, for when there is the detection zone of predetermined display parameters exception in described detection image, obtaining
Obtaining described detection image is abnormal testing result；Otherwise obtaining described detection image is normal testing result.
Preferably, Systems for optical inspection described above, wherein, described Systems for optical inspection also includes
Command reception module, is regular image or irregular image for receiving the detection image indicating product to be detected
Instruction；
3rd determining module, for when described instruction instruction described detection image is irregular image, described obtaining
After comparing result, the difference between described comparing result instruction described detection image and described master sample image is less than
During equal to predetermined threshold value, directly obtaining described detection image is normal testing result.
Preferably, Systems for optical inspection described above, wherein, described Systems for optical inspection also includes：
First logging modle, for after obtaining described detection image and being abnormal testing result, with the first logical number
It is abnormal described testing result that value records described detection image, and preserves described detection image；
Second logging modle, for after obtaining described detection image and being normal testing result, with the second logical number
It is normally described testing result that value records described detection image.
Preferably, Systems for optical inspection described above, wherein, described Systems for optical inspection also includes:
Result acquisition module, for obtaining described testing result；
Image output module, for when described testing result record is for the first logic value, then exporting described detection
Image.
Preferably, Systems for optical inspection described above, wherein, described contrast module includes：
Comparing unit, for detecting selected each unit range image and described master sample image in image by described
Described in the correspondence image of unit range image be compared, when compare for inconsistent when, make difference value accumulating values 1, its
Described in difference value initial value be 0；
First computing unit, for according to the described difference value after adding up, obtaining comparing result.
Preferably, Systems for optical inspection described above, wherein, described detection module includes：
First image selection unit, shows for obtaining the predetermined of first module range image therein in described detection image
Show parameter value；
Second image selection unit, for obtaining apart from corresponding to described first module range image preset distance multiple the
The predetermined display parameters of two unit range image；
Second computing unit, for calculating the meansigma methodss of the predetermined display parameters of multiple second unit range image；
3rd computing unit, for entering the predetermined display parameter value of described first module range image and described meansigma methodss
Row compares, and the difference between the predetermined display parameter value of described first module range image and described meansigma methodss is more than default poor
It is determined that the detection zone corresponding to described first module range image has predetermined display parameters extremely during value.
At least one of specific embodiment of the invention technique scheme has the advantages that：
Optical detecting method described in the embodiment of the present invention, by by the detection image of product to be detected and with product to be detected
Corresponding master sample image is contrasted, and realizes the profile contrast of detection image and master sample image, inconsistent contrasting
When be directly output as abnormal testing result, this process can be with using large area comparison and detection mode, situation when making inconsistent
Quickly it is detected；When contrasting consistent, the display parameters (for example, grey decision-making) of detection image itself are detected, realizes inspection
Survey the whole face detection of image, to obtain high-quality testing result, therefore this detection method solution prior art test format is single, no
Can guarantee that the problem of high-quality, quick detection.
Brief description
Fig. 1 is the schematic flow sheet of optical detecting method described in first embodiment of the invention；
Fig. 2 is the schematic flow sheet of optical detecting method described in second embodiment of the invention；
Fig. 3 is the schematic flow sheet of optical detecting method described in third embodiment of the invention；
Fig. 4 is for detecting in described detection image with the presence or absence of the abnormal detection zone of predetermined display parameters for explanation
Mode schematic diagram；
Fig. 5 is the structural representation of Systems for optical inspection described in the embodiment of the present invention.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation description is it is clear that described embodiment is only a part of embodiment of the present invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of not making creative work
Embodiment, broadly falls into the scope of protection of the invention.
Refering to shown in Fig. 1, optical detecting method described in first embodiment of the invention, including step：
S110, the detection image of product to be detected and master sample image corresponding with product to be detected are contrasted,
Obtain comparing result；
Specifically, in this step, can be using in one of detection image unit range image and master sample image
The mode that corresponding image is contrasted one by one, judges that whether the unit range image of each group of contrast is consistent, and add up
The quantity of inconsistent comparing result.The size of the wherein selected unit range image being contrasted can be according to preliminary comparison
The requirement of detection speed is preset, when using large-area way of contrast, it is possible to achieve quickly, preliminarily detect knot
Really；When the documents using small area, compared to large-area way of contrast, detection speed is slow, but be capable of high-quality,
Rapidly detect.
S120, the difference between described comparing result instruction described detection image and described master sample image is more than pre-
If during threshold value, directly obtaining described detection image is abnormal testing result；
Specifically, in this step, judge in the detection of above-mentioned steps S110, whether detection image is abnormal predetermined threshold value
Can require to be preset according to accuracy of detection.When carrying out in above-mentioned steps S110, the contrast inconsistent quantity that added up is big
When this predetermined threshold value, then obtaining detection image is abnormal testing result.
S130, when described comparing result indicates that the described difference detecting between image and described master sample image is less than
When predetermined threshold value, with the presence or absence of the abnormal detection zone of predetermined display parameters in detection described detection image；
In order to realize that the detection whole face of image is detected and obtained more high-quality testing result, by this step S130, enter one
Step detects to the predetermined display parameters (as grey decision-making) in detection image, it is determined whether there is predetermined display parameters exception
Detection zone.
S140, when there is the detection zone of predetermined display parameters exception in described detection image, obtains described detection shadow
Picture is abnormal testing result；
S150, when there is not the detection zone of predetermined display parameters exception in described detection image, obtains described detection
Image is normal testing result.
By the described optical detecting method of above-mentioned steps, by by the detection image of product to be detected and with product to be detected
Product corresponding master sample image is contrasted, and realizes the profile contrast of detection image and master sample image, differs in contrast
It is directly output as abnormal testing result, this process can be with using large area comparison and detection mode, feelings when making inconsistent during cause
Shape is quickly detected；When contrasting consistent, the display parameters (for example, grey decision-making) of detection image itself are detected, realizes
The whole face detection of detection image, to obtain high-quality testing result, therefore this detection method can solve the problem that prior art test format
Single it is impossible to ensure high-quality, the problem of quick detection.
Optical detecting method described in the embodiment of the present invention can be applied to automated optical detection equipment, using optical imagery inspection
Survey mode is realized detecting the abnormality detection of image, by determining that whether detection image is abnormal, detects possess this detection image
Product to be detected whether there is defect.
Before adopting optical detecting method described in above-described embodiment further, need to obtain the detection image of product to be detected
And master sample image corresponding with product to be detected, wherein this master sample image is to be obtained ahead of time and described product to be detected
Structure is consistent and the image of a standard sample that there is not any defect.Specifically, the detection shadow of usual this product to be detected
Picture and master sample image corresponding with product to be detected are to be obtained by scanning image sensor (scanning CCD).
Further, the present invention also provides optical detecting method described in second embodiment, as shown in Fig. 2 second embodiment
In, the step S210 to S250 of described optical detecting method is identical with first embodiment, but in this second embodiment, is obtaining respectively
After must detecting that image is normal and abnormal step, also include exporting testing result with Different Logic numerical value further respectively
Step, specifically optical detecting method described in second embodiment include：
S210, the detection image of product to be detected and master sample image corresponding with product to be detected are contrasted,
Obtain comparing result；
The mode being contrasted in this step is identical with first embodiment, will not be described here.
S220, the difference between described comparing result instruction described detection image and described master sample image is more than pre-
If during threshold value, directly obtaining described detection image is abnormal testing result, and downward execution step S260；
S230, when described comparing result indicates that the described difference detecting between image and described master sample image is less than
When predetermined threshold value, with the presence or absence of the abnormal detection zone of predetermined display parameters in detection described detection image；
S240, when there is the detection zone of predetermined display parameters exception in described detection image, obtains described detection shadow
Picture is abnormal testing result, and downward execution step S260；
S250, when there is not the detection zone of predetermined display parameters exception in described detection image, obtains described detection
Image is normal testing result, and downward execution step S270；
Step S260, with detection image described in the first logic value record for abnormal described testing result, and preserves institute
State detection image, such as this first logic value can be recorded as 0；
Step S270, with detection image described in the second logic value record for normally described testing result；As this first
Logic value can be recorded as 1；
Further, according to Fig. 2, in second embodiment, described optical detecting method also includes：
S280, obtains described testing result；
S290, when described testing result record is for the first logic value, then exports described detection image.
By the method for above-mentioned steps, abnormal result is detected as by the first logic value record, by the second logic
Records of values is detected as normal result, so when carrying out testing result output it is only necessary to carry out logical judgment, thus
Reach the purpose of optimizing detection result output program.
Additionally, the present invention also provides the optical detecting method of 3rd embodiment, refering to shown in Fig. 3, described in 3rd embodiment
Optical detecting method includes：
Step S300, receives the instruction indicating the detection image of product to be detected for regular image or irregular image；
Specifically, this instruction can directly input acquisition after determining by user.Wherein, regular image refers to detect image
Have the characteristics that subregion arranges, such as detection image can be divided into multiple regions, and the image in each of which region is
Identical, then it is considered that this detection image is regular image；And irregular image refers to detect that image does not have any arrangement spy
Point.In this embodiment, by determining the systematicness of detection image, can be using different detection modes, with according to detection image
Feature reach more quick, detect to high-quality.
Step S310, it is right that the detection image of product to be detected and master sample image corresponding with product to be detected are carried out
Ratio obtains comparing result；
This step is identical with first embodiment, the step bag specifically being contrasted detection image with master sample image
Include：
By in detection image each unit range image and unit range image described in described master sample image right
Answer image to be compared, when compare for inconsistent when, make difference value accumulating values 1, the initial value of wherein said difference value is
0；
According to the described difference value after adding up, obtain comparing result.
The size of the wherein selected unit range image being contrasted can be according to the requirement of preliminary comparison's detection speed
Preset, when using large-area way of contrast, it is possible to achieve quick, preliminarily testing result；When using little face
During long-pending documents, compared to large-area way of contrast, detection speed is slow, but is capable of high-quality, rapidly detects.
Step S320, the difference between described comparing result instruction described detection image and described master sample image is big
When predetermined threshold value, directly obtaining described detection image is abnormal testing result；
Specifically, in this step, judge in the detection of above-mentioned steps S310, whether detection image is abnormal predetermined threshold value
Can require to be preset according to accuracy of detection.When carrying out in above-mentioned steps S310, the cumulative difference value of contrast institute is pre- more than this
If during threshold value, then the difference between explanation detection image and master sample image is excessive, thus it is abnormal for obtaining detection image
Testing result.
When acquisition detection image is abnormal testing result, execution step S360 further downward；
Step S311, the difference between described comparing result instruction described detection image and described master sample image is little
In equal to predetermined threshold value, and when to instruct instruction detection image be regular image, directly obtaining described detection image is normal inspection
Survey result, and execution step S370 further downward；
S330, when described comparing result indicates that the described difference detecting between image and described master sample image is less than
In predetermined threshold value, and when instructing instruction detection image for regular image, show with the presence or absence of predetermined in detection described detection image
The detection zone of abnormal parameters；
Using display parameters in regular image in the rule detecting in image and periodic characteristics, and in order to realize to inspection
Survey the whole face of image to detect and obtain more high-quality testing result, by this step S330, further to predetermined in detection image
Display parameters (as grey decision-making) are detected, it is determined whether there is the abnormal detection zone of predetermined display parameters.
Specifically, in this step, for detecting in described detection image with the presence or absence of the abnormal detection of predetermined display parameters
The step in region includes：
Obtain the predetermined display parameter value of first module range image therein in described detection image；
Obtain predetermined apart from multiple second unit range image corresponding to described first module range image preset distance
Display parameters；
Calculate the meansigma methodss of the predetermined display parameters of multiple second unit range image；
The predetermined display parameter value of described first module range image and described meansigma methodss are compared, when described first
Difference between the predetermined display parameter value of unit range image and described meansigma methodss is more than during preset difference value it is determined that described the
It is abnormal to there are predetermined display parameters in the detection zone corresponding to one unit range image.
In conjunction with Fig. 4, so that predetermined display parameter value is as grey decision-making as a example, above-mentioned detection process is specially：
Obtain the grey decision-making of X pixel；
Obtain the grey decision-making apart from unit range pixel corresponding to X pixel preset distance respectively；For example, X pixel upper,
Under, around left and right, choose and the pixel of one pixel cell of X pixel distance respectively, as second unit scope, be also and scheme
Tetra- pixels of a, b, c and d in 4 are second unit scope, obtain the grey decision-making of this four pixels；
Calculate meansigma methodss M of grey decision-making at tetra- pixels of a, b, c and d；
The grey decision-making of X pixel and meansigma methodss M are compared, between the grey decision-making of X pixel and meansigma methodss M, difference is exhausted
Value is more than during preset difference value it is determined that the detection zone corresponding to X pixel has grey decision-making extremely；Grey decision-making when X pixel
The absolute value of difference is less than or equal to during preset difference value it is determined that the detection zone corresponding to X pixel does not exist and meansigma methodss M between
Grey decision-making is abnormal.
S340, when there is the detection zone of predetermined display parameters exception in described detection image, obtains described detection shadow
Picture is abnormal testing result, and downward execution step S360；
S350, when there is not the detection zone of predetermined display parameters exception in described detection image, obtains described detection
Image is normal testing result, and downward execution step S370；
Step S360, with detection image described in the first logic value record for abnormal described testing result, and preserves institute
State detection image, such as this first logic value can be recorded as 0；
Step S370, with detection image described in the second logic value record for normally described testing result；As this first
Logic value can be recorded as 1；
S380, obtains described testing result；
S390, when described testing result record is for the first logic value, then exports described detection image.
Using optical detecting method described in above-described embodiment, using rule in detection image for the display parameters in regular image
Then and periodic characteristics, the different detection modes of regular image and irregular image are formed as.By determining the rule of detection image
Then property, can using different detection modes, with according to the feature of detection image reach more quick, detect to high-quality.Further
By the mode of comparison and detection mode and the display parameters of itself detection, this two ways combines, and is formed as according to detection
Multiple detection logics of the feature of image, in concrete perform detection, according to the feature of detection image, according to set by detection method
Fixed detection logical order detection, can optimizing detection effect, reduce detection time, thus realizing the automated optical of excellent performance
Detection.
It is understood that mentioned predetermined display parameter value in above-described embodiment is not limited to for grey decision-making, also may be used
Think other display parameter values, such as brightness value.
In addition, in step S320, for determining whether detection image is abnormal predetermined threshold value, and using in step S330
In determining detection zone with the presence or absence of the abnormal preset difference value of predetermined display parameters, can want according to accuracy of detection and detection speed
Ask, preset.
On the other hand the embodiment of the present invention also provides a kind of Systems for optical inspection, as shown in figure 5, including：
Contrast module, for entering the detection image of product to be detected and master sample image corresponding with product to be detected
Row contrast, obtains comparing result；
First determining module, between described comparing result instruction described detection image and described master sample image
Difference be more than predetermined threshold value when, directly obtain described detection image be abnormal testing result；
Detection module, for the difference between described comparing result instruction described detection image and described master sample image
Different less than or equal to predetermined threshold value when, with the presence or absence of the abnormal detection zone of predetermined display parameters in detection described detection image；
Second determining module, for when there is the detection zone of predetermined display parameters exception in described detection image, obtaining
Obtaining described detection image is abnormal testing result；Otherwise obtaining described detection image is normal testing result.
The described Systems for optical inspection of said structure, by the detection image of product to be detected and corresponding with product to be detected
Master sample image is contrasted, and this process can be with using large area comparison and detection mode, the quickly quilt of situation when making inconsistent
Detection；When contrasting consistent, the display parameters (for example, grey decision-making) of detection image itself are detected, realize detection image
The detection of whole face, to obtain high-quality testing result, therefore this detection method can solve the problem that prior art test format single it is impossible to
Ensure high-quality, the problem of quick detection.
It is preferred that above-mentioned Systems for optical inspection is used for detecting the detection that image is regular image, using aobvious in regular image
Show parameter detection image in rule and periodic characteristics, complete with the comparison and detection of master sample image after, to inspection
Survey the whole face of image to be detected again using predetermined display parameters (as grey decision-making), be obtained in that more high-quality testing result.
It is preferred that described Systems for optical inspection also includes：
Command reception module, is regular image or irregular image for receiving the detection image indicating product to be detected
Instruction；
3rd determining module, for when described instruction instruction described detection image is irregular image, described obtaining
After comparing result, the difference between described comparing result instruction described detection image and described master sample image is less than
During equal to predetermined threshold value, directly obtaining described detection image is normal testing result.
By above-mentioned steps, when detecting that image is irregular image, because the display parameters detection process in whole face is complicated,
For saving detection time, need not detect whether there is the abnormal detection zone of predetermined display parameters further.
It is preferred that described Systems for optical inspection also includes：
First logging modle, for after obtaining described detection image and being abnormal testing result, with the first logical number
It is abnormal described testing result that value records described detection image, and preserves described detection image；
Second logging modle, for after obtaining described detection image and being normal testing result, with the second logical number
It is normally described testing result that value records described detection image.
Further, described Systems for optical inspection also includes:
Result acquisition module, for obtaining described testing result；
Image output module, for when described testing result record is for the first logic value, then exporting described detection
Image.
Using above-mentioned module, abnormal result is detected as by the first logic value record, is remembered by the second logic value
Record is detected as normal result, so when carrying out testing result output it is only necessary to carry out logical judgment, thus reaching excellent
Change the purpose of testing result output program.
It is preferred that described contrast module includes：
Comparing unit, for detecting selected each unit range image and described master sample image in image by described
Described in the correspondence image of unit range image be compared, when compare for inconsistent when, make difference value accumulating values 1, its
Described in difference value initial value be 0；
First computing unit, for according to the described difference value after adding up, obtaining comparing result.
It is preferred that described detection module includes：
First image selection unit, shows for obtaining the predetermined of first module range image therein in described detection image
Show parameter value；
Second image selection unit, for obtaining apart from corresponding to described first module range image preset distance multiple the
The predetermined display parameters of two unit range image；
Second computing unit, for calculating the meansigma methodss of the predetermined display parameters of multiple second unit range image；
3rd computing unit, for entering the predetermined display parameter value of described first module range image and described meansigma methodss
Row compares, and the difference between the predetermined display parameter value of described first module range image and described meansigma methodss is more than default poor
It is determined that the detection zone corresponding to described first module range image has predetermined display parameters extremely during value.
Optical detecting method described in the embodiment of the present invention and Systems for optical inspection, by providing the detection of product to be detected
Image and being carried out with master sample image contrasted, the display parameters (for example, grey decision-making) of detection image itself are carried out detecting two
Plant detection mode, and consider to detect the systematicness of image, multiple different detection logics are provided, solve prior art test format list
One it is impossible to ensure high-quality, the problem of quick detection.
The above is the preferred embodiment of the present invention it is noted that for those skilled in the art
For, on the premise of without departing from principle of the present invention, some improvements and modifications can also be made, these improvements and modifications
Should be regarded as protection scope of the present invention.
Claims (12)
1. a kind of optical detecting method is it is characterised in that include：
The detection image of product to be detected and master sample image corresponding with product to be detected are contrasted, is obtained contrast knot
Really；
When difference between described comparing result instruction described detection image and described master sample image is more than predetermined threshold value,
Directly obtaining described detection image is abnormal testing result；
Difference between described comparing result instruction described detection image and described master sample image is less than or equal to default threshold
During value, with the presence or absence of the abnormal detection zone of predetermined display parameters in detection described detection image；
When there is the detection zone of predetermined display parameters exception in described detection image, it is abnormal for obtaining described detection image
Testing result；Otherwise obtaining described detection image is normal testing result.
2. optical detecting method according to claim 1 it is characterised in that the described detection image by product to be detected and
Master sample image corresponding with product to be detected is contrasted, before obtaining the step of comparing result, described optical detection side
Method also includes：
Receive the instruction indicating the detection image of product to be detected for regular image or irregular image；
When described instruction instruction described detection image is irregular image, after obtaining the step of described comparing result, institute
State optical detecting method also to include：
Difference between described comparing result instruction described detection image and described master sample image is less than or equal to default threshold
During value, directly obtaining described detection image is normal testing result.
3. optical detecting method according to claim 1 and 2 is it is characterised in that be abnormal obtaining described detection image
The step of testing result after, described optical detecting method also includes：
With detection image described in the first logic value record for abnormal described testing result, and preserve described detection image；
After obtaining described detection image and being the step of normal testing result, described optical detecting method also includes：
With detection image described in the second logic value record for normally described testing result.
4. optical detecting method according to claim 3 is it is characterised in that described optical detecting method also includes：
Obtain described testing result；
When described testing result record is for the first logic value, then export described detection image.
5. optical detecting method according to claim 1 it is characterised in that the described detection image by product to be detected and
Master sample image corresponding with product to be detected is contrasted, and the step obtaining comparing result includes：
By in described detection image each unit range image and unit range image described in described master sample image right
Answer image to be compared, when compare for inconsistent when, make difference value accumulating values 1, the initial value of wherein said difference value is
0；
According to the described difference value after adding up, obtain comparing result.
6. optical detecting method according to claim 1 is it is characterised in that whether there is pre- in detection described detection image
The step determining the abnormal detection zone of display parameters includes：
Obtain the predetermined display parameter value of first module range image therein in described detection image；
Obtain the predetermined display apart from multiple second unit range image corresponding to described first module range image preset distance
Parameter；
Calculate the meansigma methodss of the predetermined display parameters of multiple second unit range image；
The predetermined display parameter value of described first module range image and described meansigma methodss are compared, when described first module
Difference between the predetermined display parameter value of range image and described meansigma methodss is more than during preset difference value it is determined that described first is single
It is abnormal to there are predetermined display parameters in the detection zone corresponding to first range image.
7. a kind of Systems for optical inspection is it is characterised in that include：
Contrast module is right for carrying out the detection image of product to be detected and master sample image corresponding with product to be detected
Ratio obtains comparing result；
First determining module, for the difference between described comparing result instruction described detection image and described master sample image
Different more than predetermined threshold value when, directly obtain described detection image be abnormal testing result；
Detection module is little for the difference between described comparing result instruction described detection image and described master sample image
When equal to predetermined threshold value, with the presence or absence of the abnormal detection zone of predetermined display parameters in detection described detection image；
Second determining module, for when there is the detection zone of predetermined display parameters exception in described detection image, obtaining institute
Stating detection image is abnormal testing result；Otherwise obtaining described detection image is normal testing result.
8. Systems for optical inspection according to claim 7 is it is characterised in that described Systems for optical inspection also includes
Command reception module, for receiving the finger that the detection image indicating product to be detected is regular image or irregular image
Order；
3rd determining module, for when described instruction instruction described detection image is irregular image, obtaining described contrast
After result, the difference between described comparing result instruction described detection image and described master sample image is less than or equal to
During predetermined threshold value, directly obtaining described detection image is normal testing result.
9. the Systems for optical inspection according to claim 7 or 8 is it is characterised in that described Systems for optical inspection also includes：
First logging modle, for, after obtaining described detection image and being abnormal testing result, being remembered with the first logic value
Record described detection image is abnormal described testing result, and preserves described detection image；
Second logging modle, for, after obtaining described detection image and being normal testing result, being remembered with the second logic value
Record described detection image is normally described testing result.
10. Systems for optical inspection according to claim 9 is it is characterised in that described Systems for optical inspection also includes:
Result acquisition module, for obtaining described testing result；
Image output module, for when described testing result record is for the first logic value, then exporting described detection image.
11. Systems for optical inspections according to claim 7 are it is characterised in that described contrast module includes：
Comparing unit, for detecting selected each unit range image and institute in described master sample image in image by described
The correspondence image stating unit range image is compared, when compare for inconsistent when, make difference value accumulating values 1, wherein institute
The initial value stating difference value is 0；
First computing unit, for according to the described difference value after adding up, obtaining comparing result.
12. Systems for optical inspections according to claim 7 are it is characterised in that described detection module includes：
First image selection unit, for obtaining the predetermined display ginseng of first module range image therein in described detection image
Numerical value；
Second image selection unit, single apart from corresponding to described first module range image preset distance multiple second for obtaining
The predetermined display parameters of first range image；
Second computing unit, for calculating the meansigma methodss of the predetermined display parameters of multiple second unit range image；
3rd computing unit, for being compared the predetermined display parameter value of described first module range image and described meansigma methodss
Relatively, the difference between the predetermined display parameter value of described first module range image and described meansigma methodss is more than preset difference value
When it is determined that the detection zone corresponding to described first module range image to there are predetermined display parameters abnormal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610809472.0A CN106442540A (en) | 2016-09-07 | 2016-09-07 | Optical detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610809472.0A CN106442540A (en) | 2016-09-07 | 2016-09-07 | Optical detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106442540A true CN106442540A (en) | 2017-02-22 |
Family
ID=58165371
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610809472.0A Pending CN106442540A (en) | 2016-09-07 | 2016-09-07 | Optical detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106442540A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110824105A (en) * | 2018-08-14 | 2020-02-21 | 领凡新能源科技(北京)有限公司 | Colloid detection method and colloid detection system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4454541A (en) * | 1982-06-14 | 1984-06-12 | Rca Corporation | Charge coupled device based blemish detection system and method |
| JPH0642935A (en) * | 1992-07-27 | 1994-02-18 | Taiyo Yuden Co Ltd | Appearance inspection apparatus of electronic component |
| CN1610826A (en) * | 2001-11-28 | 2005-04-27 | 应用材料有限公司 | Method for detecting defects |
| JP3867615B2 (en) * | 2002-04-19 | 2007-01-10 | 住友電装株式会社 | Work appearance inspection apparatus and appearance inspection method |
| US20090268950A1 (en) * | 2008-04-29 | 2009-10-29 | Kuo Shun-Kun | Product-Quality Inspection System and Method thereof |
| CN101592620A (en) * | 2008-05-28 | 2009-12-02 | 华硕电脑股份有限公司 | Circuit substrate detection device and method |
| CN103685839A (en) * | 2012-09-14 | 2014-03-26 | 株式会社理光 | Image inspection apparatus and image inspection method |
| CN104730078A (en) * | 2013-12-23 | 2015-06-24 | 北京红源光电技术公司 | Thermal infrared imager-based AOI circuit board detection method |
| CN105572137A (en) * | 2015-12-15 | 2016-05-11 | 重庆瑞阳科技股份有限公司 | Appearance defect test method |
-
2016
- 2016-09-07 CN CN201610809472.0A patent/CN106442540A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4454541A (en) * | 1982-06-14 | 1984-06-12 | Rca Corporation | Charge coupled device based blemish detection system and method |
| JPH0642935A (en) * | 1992-07-27 | 1994-02-18 | Taiyo Yuden Co Ltd | Appearance inspection apparatus of electronic component |
| CN1610826A (en) * | 2001-11-28 | 2005-04-27 | 应用材料有限公司 | Method for detecting defects |
| JP3867615B2 (en) * | 2002-04-19 | 2007-01-10 | 住友電装株式会社 | Work appearance inspection apparatus and appearance inspection method |
| US20090268950A1 (en) * | 2008-04-29 | 2009-10-29 | Kuo Shun-Kun | Product-Quality Inspection System and Method thereof |
| CN101592620A (en) * | 2008-05-28 | 2009-12-02 | 华硕电脑股份有限公司 | Circuit substrate detection device and method |
| CN103685839A (en) * | 2012-09-14 | 2014-03-26 | 株式会社理光 | Image inspection apparatus and image inspection method |
| CN104730078A (en) * | 2013-12-23 | 2015-06-24 | 北京红源光电技术公司 | Thermal infrared imager-based AOI circuit board detection method |
| CN105572137A (en) * | 2015-12-15 | 2016-05-11 | 重庆瑞阳科技股份有限公司 | Appearance defect test method |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110824105A (en) * | 2018-08-14 | 2020-02-21 | 领凡新能源科技(北京)有限公司 | Colloid detection method and colloid detection system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100499057C (en) | Chip detection method | |
| TWI557650B (en) | System and method for identifying defects in a material | |
| CN112577969B (en) | Defect detection method and defect detection system based on machine vision | |
| CN103792705B (en) | Detecting method and detecting device for detecting substrate defects | |
| KR101256369B1 (en) | Flat display pannel test equipment and test method using multi ccd camera | |
| CN107515481B (en) | Display panel detection method and device | |
| CN107315011A (en) | Image processing apparatus, image processing method and storage medium | |
| JP5786622B2 (en) | Image quality inspection method, image quality inspection apparatus, and image quality inspection program | |
| CN102854195B (en) | Method for detecting defect coordinates on color filter | |
| US20220076404A1 (en) | Defect management apparatus, method and non-transitory computer readable medium | |
| CN101487934B (en) | Optical detection device and optical detection method | |
| KR100759950B1 (en) | Device and method for inspection external appearance | |
| JP2018179698A (en) | Sheet inspection device | |
| KR20060070423A (en) | Appearance inspection method and device | |
| CN106442540A (en) | Optical detection method and system | |
| CN104157589B (en) | Wafer defect scan method | |
| CN112465780B (en) | Method and device for monitoring abnormal film thickness of insulating layer | |
| CN102735689A (en) | Paper defect detection system based on image pattern recognition | |
| US10254594B2 (en) | Liquid crystal drop filling system and control method | |
| CN104427210A (en) | A method and device for detecting a random abnormal blinking dot | |
| CN107356343A (en) | Semiconductor refrigerating chip detection method based on infrared thermal imaging technique | |
| JP2010054246A (en) | Method for detecting joint and method for inspecting external appearance of joint using the method | |
| CN115861234A (en) | Rule defect analysis method and system | |
| CN107767372A (en) | The online vision detection system of chip pin and its method that a kind of hierarchic parallel calculates | |
| KR102212318B1 (en) | Apparatus for display inspection and method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170222 |
|
| RJ01 | Rejection of invention patent application after publication |