CN109886956A - Detect the method and device of defect point aggregation - Google Patents
Detect the method and device of defect point aggregation Download PDFInfo
- Publication number
- CN109886956A CN109886956A CN201910169245.XA CN201910169245A CN109886956A CN 109886956 A CN109886956 A CN 109886956A CN 201910169245 A CN201910169245 A CN 201910169245A CN 109886956 A CN109886956 A CN 109886956A
- Authority
- CN
- China
- Prior art keywords
- defect point
- subregion
- normalization
- detected
- mode
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 321
- 230000002776 aggregation Effects 0.000 title claims abstract description 73
- 238000004220 aggregation Methods 0.000 title claims abstract description 73
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000010586 diagram Methods 0.000 claims abstract description 131
- 238000010606 normalization Methods 0.000 claims abstract description 103
- 238000012545 processing Methods 0.000 claims abstract description 69
- 238000001514 detection method Methods 0.000 claims abstract description 56
- 238000005192 partition Methods 0.000 claims abstract description 56
- 230000011218 segmentation Effects 0.000 claims abstract description 27
- 230000003321 amplification Effects 0.000 claims description 18
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 18
- 238000003860 storage Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 14
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 238000007689 inspection Methods 0.000 abstract description 3
- 239000000758 substrate Substances 0.000 description 12
- 230000008859 change Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000008901 benefit Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Abstract
The invention discloses a kind of method and devices for detecting defect point aggregation, it is related to automatic optics inspection technical field, improve detection efficiency and accuracy that whether the defects of detection defect point diagram point has aggregation, main technical schemes of the invention are as follows: obtain defect point diagram, partitioned mode, number of partitions and variance threshold values to be detected;Region segmentation processing is carried out to the defect point diagram to be detected according to the partitioned mode and the number of partitions, to obtain multiple subregions;It determines the corresponding defect point quantity of each subregion, and the corresponding normalization accounting value of each subregion is calculated according to the corresponding defect point quantity of each subregion;Calculate the corresponding variance yields of multiple normalization accounting values;Judge whether the variance yields is greater than the variance threshold values;If so, determining that the defects of described defect point diagram to be detected point has aggregation.Whether the present invention is applied to the defects of detection defect point diagram point with during aggregation.
Description
Technical field
The present invention relates to automatic optics inspection technical field more particularly to a kind of methods and dress for detecting defect point aggregation
It sets.
Background technique
With the continuous development of science and technology, AOI (automatic optics inspection) technology has been widely used for electronics manufacturing.
In the fabrication process of the array substrate, detecting the defect point in array substrate whether to have aggregation is highly important link.
For AOI detection device during carrying out AOI detection to array substrate, AOI detection device can be according to preset coordinate system, and recording should
The coordinate of each defect point in array substrate, and after detection, according to the corresponding coordinate of each defect point of record, draw
The corresponding defect point diagram of the array substrate is produced, can determine whether the defect point in the array substrate has according to the defect point diagram
There is aggregation.
Currently, determining whether the defect point in the array substrate has aggregation according to the corresponding defect point diagram of array substrate
When property, the mode of artificial detection, i.e. the defects of staff's manual identified defect point diagram point are generallyd use, when determining unit plane
When the defects of product point is more than certain amount, it can determine that the defects of defect point diagram point has aggregation, so as to true
Defect point in the fixed array substrate has aggregation.
In the implementation of the present invention, following technical problem exists in the prior art in inventor, due to, need into
The quantity of the defect point diagram of row detection is excessive, therefore, when staff detects all defect point diagram, inherently expends
Plenty of time;Also, the examination criteria of different operating personnel and disunity, thus not can guarantee the accuracy of testing result, because
This, the defects of defect point diagram point is detected by the way of artificial detection, and whether the detection efficiency with aggregation is lower, accurate
Property is poor.
Summary of the invention
In view of this, the present invention provides a kind of method and device for detecting defect point aggregation, main purpose is to improve
Detect detection efficiency and accuracy that whether the defects of defect point diagram point has aggregation.
To solve the above-mentioned problems, present invention generally provides following technical solutions:
On the one hand, the present invention provides a kind of methods for detecting defect point aggregation, this method comprises:
Obtain defect point diagram, partitioned mode, number of partitions and variance threshold values to be detected;
Region segmentation processing is carried out to the defect point diagram to be detected according to the partitioned mode and the number of partitions, with
Obtain multiple subregions;
Determine the corresponding defect point quantity of each subregion, and according to the corresponding defect point quantity meter of each subregion
Calculate the corresponding normalization accounting value of each subregion;
Calculate the corresponding variance yields of multiple normalization accounting values;
Judge whether the variance yields is greater than the variance threshold values;
If so, determining that the defects of described defect point diagram to be detected point has aggregation.
Optionally, the partitioned mode is vertical division block mode or horizontal partition mode;It is described according to each subregion
Corresponding defect point quantity calculates the corresponding normalization accounting value of each subregion, comprising:
The corresponding defect points of the defect point diagram to be detected are calculated according to the corresponding defect point quantity of each subregion
Amount;
It calculates the corresponding defect point quantity of each subregion and accounts for the corresponding defect point quantity of the defect point diagram to be detected
Ratio, to obtain the corresponding normalization accounting value of each subregion.
Optionally, the partitioned mode, which is positive, oblique partitioned mode or bears oblique partitioned mode;It is described according to each subregion
Corresponding defect point quantity calculates the corresponding normalization accounting value of each subregion, comprising:
Determine the corresponding area of the defect point diagram to be detected and the corresponding area of each subregion;
By the corresponding defect point quantity of each subregion, the corresponding area of each subregion and described to be detected lack
The corresponding area of trapping spot figure substitutes into preset algorithm, calculates the corresponding normalization accounting value of each subregion.
Optionally, return described according to each subregion of each corresponding defect point quantity calculating of subregion is corresponding
After one changes accounting value, the method also includes:
Processing is amplified to each normalization accounting value using default amplification factor;
The square value of the default amplification factor is calculated, and place is amplified to the variance threshold values using the square value
Reason;
It is described to calculate the corresponding variance yields of multiple normalization accountings values, comprising:
It calculates multiple normalization accountings after enhanced processing and is worth corresponding variance yields;
It is described to judge whether the variance yields is greater than the variance threshold values, comprising:
Judge whether the corresponding variance yields of multiple normalization accounting values after enhanced processing is greater than by amplification
The variance threshold values that treated.
Optionally, the partitioned mode is vertical division block mode, horizontal partition mode, just oblique partitioned mode, bears oblique subregion
Any one in mode.
To achieve the goals above, according to another aspect of the present invention, a kind of electronic equipment, the electronic equipment are provided
Include: memory, processor and storage on a memory and the program that can run on a processor, described in the processor executes
When program, the method for realizing detection defect point aggregation described above.
To achieve the goals above, according to another aspect of the present invention, a kind of computer readable storage medium is provided,
On be stored with computer program, the method that described program realizes detection defect point aggregation described above when running.
On the other hand, the present invention also provides a kind of device for detecting defect point aggregation, which includes:
Acquiring unit, for obtaining defect point diagram, partitioned mode, number of partitions and variance threshold values to be detected;
Region segmentation unit, the partitioned mode and the number of partitions for being obtained according to the acquiring unit are to institute
It states defect point diagram to be detected and carries out region segmentation processing, to obtain multiple subregions;
First determination unit, for determining the corresponding defect point quantity of each subregion;
First computing unit, for being counted according to the corresponding defect of each of first determination unit determination subregion
Amount calculates the corresponding normalization accounting value of each subregion;
Second computing unit, for calculating the corresponding variance yields of multiple normalization accounting values;
Whether judging unit, the variance yields for judging that second computing unit calculates are greater than the variance threshold
Value;
Second determination unit, for determining when the judging unit judges that the variance yields is greater than the variance threshold values
The defects of described defect point diagram to be detected point has aggregation.
Optionally, the partitioned mode is vertical division block mode or horizontal partition mode;First computing unit includes:
First computing module, for according to each corresponding defect point quantity calculating of subregion defect point to be detected
Scheme corresponding defect point quantity;
Second computing module accounts for the defect point diagram to be detected for calculating the corresponding defect point quantity of each subregion
The ratio of corresponding defect point quantity, to obtain the corresponding normalization accounting value of each subregion.
Optionally, the partitioned mode, which is positive, oblique partitioned mode or bears oblique partitioned mode;First computing unit includes:
Determining module, for determining the corresponding area of the defect point diagram to be detected and the corresponding face of each subregion
Product;
Third computing module, for by the corresponding defect point quantity of each subregion, the corresponding face of each subregion
The corresponding area of long-pending and described defect point diagram to be detected substitutes into preset algorithm, calculates the corresponding normalization of each subregion
Accounting value.
Optionally, described device further include:
First amplifying unit, by based on first computing unit is according to the corresponding defect point quantity of each subregion
After calculating the corresponding normalization accounting value of each subregion, using default amplification factor to each normalization accounting value into
Row enhanced processing;
Third computing unit, for calculating the square value of the default amplification factor;
Second amplifying unit, the square value for using the third computing unit to calculate to the variance threshold values into
Row enhanced processing;
Second computing unit, it is corresponding specifically for calculating multiple normalization accounting values after enhanced processing
Variance yields;
The judging unit, specifically for judging the corresponding side of multiple normalization accounting values after enhanced processing
Whether difference is greater than the variance threshold values after enhanced processing.
Optionally, the partitioned mode is vertical division block mode, horizontal partition mode, just oblique partitioned mode, bears oblique subregion
Any one in mode.
By above-mentioned technical proposal, technical solution provided by the invention is at least had the advantage that
The present invention provides a kind of method and device for detecting defect point aggregation, and in the prior art, using artificial detection
Mode detect whether the defects of defect point diagram point is compared with aggregation, the present invention can be acquired in terminal device
Partitioned mode, the number of partitions that the defect point diagram to be detected and staff that AOI detection device is drawn are set according to detection demand
After amount and variance threshold values, region segmentation is carried out to defect point figure to be detected according to partitioned mode and number of partitions by terminal device
Reason, to obtain multiple subregions;Terminal device is after determining the corresponding defect point quantity of each subregion, according to each subregion pair
The defect point quantity answered calculates the corresponding normalization accounting value of each subregion, and calculates the corresponding variance of multiple normalization accounting values
Value;Terminal device can determine to be detected when determining the corresponding variance yields of multiple normalization accounting values greater than variance threshold values
The defects of defect point diagram point has aggregation.Due to whether being had by the defects of terminal device detection defect point diagram point
Therefore aggregation can be improved the detection efficiency whether the defects of detection defect point diagram point has aggregation;Also, terminal
Equipment can detect multiple defect point diagrams using identical examination criteria, therefore, can be improved in detection defect point diagram
Defect point whether there is the accuracy of aggregation.
The above description is only an overview of the technical scheme of the present invention, in order to better understand the technical means of the present invention,
And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects of the present invention, feature and advantage can
It is clearer and more comprehensible, the followings are specific embodiments of the present invention.
Detailed description of the invention
By reading the following detailed description of the preferred embodiment, various other advantages and benefits are common for this field
Technical staff will become clear.The drawings are only for the purpose of illustrating a preferred embodiment, and is not considered as to the present invention
Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings:
Fig. 1 is a kind of method flow diagram for detecting defect point aggregation provided in an embodiment of the present invention;
Fig. 2 a shows a kind of use vertical division block mode provided in an embodiment of the present invention and carries out to defect point figure to be detected
The schematic diagram of region segmentation processing;
Fig. 2 b shows a kind of use horizontal partition mode provided in an embodiment of the present invention and carries out to defect point figure to be detected
The schematic diagram of region segmentation processing;
Fig. 2 c shows a kind of just oblique partitioned mode of use provided in an embodiment of the present invention and carries out to defect point figure to be detected
The schematic diagram of region segmentation processing;
Fig. 2 d shows provided in an embodiment of the present invention a kind of carried out to defect point figure to be detected using bearing oblique partitioned mode
The schematic diagram of region segmentation processing;
Fig. 3 is the method flow diagram of another detection defect point aggregation provided in an embodiment of the present invention;
Fig. 4 is a kind of composition block diagram of device for detecting defect point aggregation provided in an embodiment of the present invention;
Fig. 5 is the composition block diagram of the device of another detection defect point aggregation provided in an embodiment of the present invention.
Specific embodiment
The exemplary embodiment that the present invention will be described in more detail below with reference to accompanying drawings.Although showing the present invention in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the present invention without should be by embodiments set forth here
It is limited.It is to be able to thoroughly understand the present invention on the contrary, providing these embodiments, and can be by the scope of the present invention
It is fully disclosed to those skilled in the art.
The embodiment of the present invention provides a kind of method for detecting defect point aggregation, as shown in Figure 1, which comprises
101, defect point diagram, partitioned mode, number of partitions and variance threshold values to be detected are obtained.
Wherein, defect point diagram to be detected is the corresponding defect point diagram of array substrate to be detected, in AOI detection device to be checked
During surveying array substrate progress AOI detection, AOI detection device can record the array base to be detected according to preset coordinate system
The coordinate of each defect point on plate, and after detection, according to the corresponding coordinate of each defect point of record, draw out this
The corresponding defect point diagram (defect point diagram i.e. to be detected) of array substrate to be detected, at this point, the defect to be detected just can be acquired
Point diagram;Wherein, partitioned mode, number of partitions and variance threshold values are staff according to detection demand sets itself, subregion
Mode is vertical division block mode, horizontal partition mode, just oblique partitioned mode, bears any one in oblique partitioned mode.
In embodiments of the present invention, in order to detect whether the defects of defect point diagram point has aggregation, terminal device is first
The square partition that the defect point diagram to be detected and staff for first needing to obtain the drafting of AOI detection device are set according to detection demand
Formula, number of partitions and variance threshold values.
102, region segmentation processing is carried out to defect point figure to be detected according to partitioned mode and number of partitions, it is multiple to obtain
Subregion.
In embodiments of the present invention, terminal device is acquiring defect point diagram, partitioned mode and number of partitions to be detected
Afterwards, region segmentation processing can be carried out to defect point figure to be detected according to the partitioned mode and number of partitions acquired, thus
Obtain multiple subregions.
Specifically, in this step, when the partitioned mode acquired is vertical division block mode, terminal device uses vertical
Region segmentation processing directly is carried out to defect point figure to be detected in a plurality of line of demarcation of defect point diagram horizontal axis to be detected, to obtain number
Amount is multiple subregions of number of partitions, wherein the spacing in a plurality of line of demarcation is equal, specifically can be as shown in Figure 2 a;When obtaining
When the partitioned mode arrived is horizontal partition mode, terminal device uses a plurality of line of demarcation for being parallel to defect point diagram horizontal axis to be detected
Region segmentation processing is carried out to defect point figure to be detected, to obtain multiple subregions that quantity is number of partitions, wherein a plurality of point
The spacing in boundary line is equal, specifically can be as shown in Figure 2 b;When the partitioned mode acquired is positive oblique partitioned mode, terminal is set
It is standby that region segmentation processing is carried out to defect point figure to be detected using a plurality of line of demarcation that slope is positive value, so that obtaining quantity is point
Multiple subregions of area's quantity, wherein the spacing in a plurality of line of demarcation is equal, specifically can be as shown in Figure 2 c;When point acquired
Area's mode be negative oblique partitioned mode when, terminal device using slope be negative value a plurality of line of demarcation defect point figure to be detected is carried out
Region segmentation processing, to obtain multiple subregions that quantity is number of partitions, wherein the spacing in a plurality of line of demarcation is equal, specifically
Can be as shown in Figure 2 d, but not limited to this.
103, it determines the corresponding defect point quantity of each subregion, and is calculated often according to the corresponding defect point quantity of each subregion
The corresponding normalization accounting value of a subregion.
In embodiments of the present invention, terminal device is being lacked according to the partitioned mode and number of partitions acquired to be detected
Trapping spot figure carries out region segmentation processing, after obtaining multiple subregions, can determine the corresponding defect point quantity of each subregion.By
In when the corresponding defect point quantity of some defect point diagram is relatively more, but the distribution of the defects of defect point diagram point is relatively uniform
When, it should determine that the defects of defect point diagram point does not have aggregation;And work as the corresponding defect point quantity ratio of some defect point diagram
It is less, but when the comparison concentration of the defects of defect point diagram point distribution, it is poly- should to determine that the defects of defect point diagram point has
Collection property, therefore, in order to eliminate influence of the corresponding defect point quantity of defect point diagram to be detected to testing result, terminal device needs
The corresponding defect point quantity of each subregion is normalized, i.e., is calculated according to the corresponding defect point quantity of each subregion every
The corresponding normalization accounting value of a subregion.
Specifically, in this step, when the partitioned mode acquired is vertical division block mode or horizontal partition mode,
Since the corresponding area of each subregion is identical, therefore, can directly be calculated according to the corresponding defect point quantity of each subregion each
The corresponding normalization accounting value of subregion calculates defect point diagram pair to be detected according to the corresponding defect point quantity of each subregion first
The defect point quantity answered, then calculate the corresponding defect point quantity of each subregion and account for the corresponding defect point quantity of defect point diagram to be detected
Ratio, to obtain the corresponding normalization accounting value of each subregion;When the partitioned mode acquired is positive oblique partitioned mode
Or when bearing oblique partitioned mode, since the corresponding area of each subregion is different, therefore, according to the corresponding defect point of each subregion
When quantity calculates each subregion corresponding normalization accounting value, also need that place is normalized to the corresponding area of each subregion
Reason, i.e., determine the corresponding area of defect point diagram to be detected and the corresponding area of each subregion, then by each subregion pair first
The corresponding area of defect point quantity, the corresponding area of each subregion and the defect point diagram to be detected answered substitutes into preset algorithm,
To calculate the corresponding normalization accounting value of each subregion.
104, multiple normalization accountings are calculated and is worth corresponding variance yields.
In embodiments of the present invention, terminal device is after calculating the corresponding normalization accounting value of each subregion, Bian Keji
The corresponding variance yields of multiple normalized ratios is calculated, i.e., calculates the corresponding average value of multiple normalization accounting values first, it then will be more
A normalization accounting value and the corresponding average value of multiple normalization accounting values are updated in variance calculation formula, can be calculated more
A normalization accounting is worth corresponding variance yields.
105, judge whether variance yields is greater than variance threshold values.
In embodiments of the present invention, terminal device is after calculating the corresponding variance yields of multiple normalization accounting values,
Judge whether calculated variance yields is greater than the variance threshold values acquired in a step 101, so as to subsequent according to judging result
Determine whether the defects of defect point diagram to be detected point has aggregation.
106, if so, determining that the defects of defect point diagram to be detected point has aggregation.
In embodiments of the present invention, when terminal device determines the corresponding variance of multiple normalization accounting values in step 105
When value is greater than variance threshold values, it can determine that the defects of defect point diagram to be detected point has aggregation.
It needs to be illustrated, in actual application, staff can concurrently set more according to detection demand
A partitioned mode and the corresponding number of partitions of each partitioned mode and variance threshold values, and terminal device acquire it is to be checked
Survey defect point diagram, multiple partitioned modes, the corresponding number of partitions of each partitioned mode and the corresponding variance threshold of each partitioned mode
After value, it can be detected under every kind of partitioned mode respectively, defect to be detected using method documented by above-mentioned steps 101-106
Whether the defects of point diagram point has aggregation, and is detecting under any one partitioned mode, in defect point diagram to be detected
Defect point when there is aggregation, the defects of defect point diagram to be detected point can be determined with aggregation.
The embodiment of the present invention provides a kind of method for detecting defect point aggregation, and in the prior art, using artificial detection
Mode detect whether the defects of defect point diagram point is compared with aggregation, the embodiment of the present invention can be obtained in terminal device
It obtains the defect point diagram to be detected that AOI detection device is drawn and the partitioned mode that staff sets according to detection demand, divide
After area's quantity and variance threshold values, region point is carried out to defect point figure to be detected according to partitioned mode and number of partitions by terminal device
Processing is cut, to obtain multiple subregions;Terminal device is after determining the corresponding defect point quantity of each subregion, according to each point
The corresponding defect point quantity in area calculates the corresponding normalization accounting value of each subregion, and it is corresponding to calculate multiple normalization accounting values
Variance yields;Terminal device when determining the corresponding variance yields of multiple normalization accounting values greater than variance threshold values, can determine to
Detecting the defects of defect point diagram point has aggregation.Due to being whether to detect the defects of defect point diagram point by terminal device
With aggregation, therefore, the detection efficiency whether the defects of detection defect point diagram point has aggregation can be improved;Also,
Terminal device can detect multiple defect point diagrams using identical examination criteria, therefore, can be improved detection defect point
Whether the defects of figure point has the accuracy of aggregation.
Below in order to be explained in more detail, the embodiment of the invention provides the sides of another detection defect point aggregation
Method, especially terminal device calculate the corresponding normalization accounting value of each subregion according to the corresponding defect point quantity of each subregion
Specific method, it is specific as shown in figure 3, this method comprises:
201, defect point diagram, partitioned mode, number of partitions and variance threshold values to be detected are obtained.
Wherein, about step 201, obtain defect point diagram, partitioned mode, number of partitions and variance threshold values to be detected, can be with
With reference to the description of Fig. 1 corresponding part, the embodiment of the present invention will not be described in great detail herein.
202, region segmentation processing is carried out to defect point figure to be detected according to partitioned mode and number of partitions, it is multiple to obtain
Subregion.
Wherein, defect point figure to be detected is carried out at region segmentation about step 202, according to partitioned mode and number of partitions
Reason can refer to the description of Fig. 1 corresponding part to obtain multiple subregions, and the embodiment of the present invention will not be described in great detail herein.
203, the corresponding defect point quantity of each subregion is determined.
Wherein, about step 203, determine the corresponding defect point quantity of each subregion, can be retouched with reference to Fig. 1 corresponding part
It states, the embodiment of the present invention will not be described in great detail herein.
204, the corresponding normalization accounting value of each subregion is calculated according to the corresponding defect point quantity of each subregion.
In embodiments of the present invention, in order to eliminate the corresponding defect point quantity of defect point diagram to be detected to the shadow of testing result
Ring, terminal device after determining the corresponding defect point quantity of each subregion, need to the corresponding defect point quantity of each subregion into
Row normalized calculates the corresponding normalization accounting value of each subregion according to the corresponding defect point quantity of each subregion.With
Under how the corresponding normalization accounting value of each subregion will be calculated according to the corresponding defect point quantity of each subregion to terminal device
It is described in detail.
(1) when the partitioned mode acquired is vertical division block mode or horizontal partition mode, due to each subregion pair
The area answered is identical, therefore, can directly calculate the corresponding normalizing of each subregion according to the corresponding defect point quantity of each subregion
Change accounting value: firstly, calculating the corresponding defect point quantity of defect point diagram to be detected according to the corresponding defect point quantity of each subregion;
Then, the ratio that the corresponding defect point quantity of each subregion accounts for the corresponding defect point quantity of defect point diagram to be detected is calculated, thus
The corresponding normalization accounting value of each subregion is obtained, for example, in abovementioned steps, using vertical division block mode by defect to be detected
Point image is divided into 5 subregions, respectively subregion A, subregion B, subregion C, subregion D and subregion E, wherein subregion A is corresponding to be lacked
Trapping spot quantity is 10, the corresponding defect point quantity of subregion B is 15, the corresponding defect point quantity of subregion C is 20, subregion D is corresponding
Defect point quantity is 5, the corresponding defect point quantity of subregion E is 15, therefore, the corresponding defect point quantity of the defect point diagram to be detected
For 10+15+20+5+15=65, so that the corresponding normalization accounting value of subregion A is 10/65=0.154, the corresponding normalizing of subregion B
Change accounting value is 15/65=0.231, the corresponding normalization accounting value of subregion C is 20/65=0.308, the corresponding normalizing of subregion D
Change accounting value is 5/65=0.077, the corresponding normalization accounting value of subregion E is 15/65=0.231.
(2) when the partitioned mode acquired is positive oblique partitioned mode or when bearing oblique partitioned mode, due to each subregion pair
The area answered is different, therefore, is calculating the corresponding normalization accounting of each subregion according to the corresponding defect point quantity of each subregion
It when value, also needs that the corresponding area of each subregion is normalized: firstly, determining that defect point diagram to be detected is corresponding
Area and the corresponding area of each subregion;Then, by the corresponding defect point quantity of each subregion, the corresponding area of each subregion
And the corresponding area of defect point diagram to be detected substitutes into preset algorithm, to calculate the corresponding normalization accounting of each subregion
Value, wherein preset algorithm is specific as follows:
Wherein, n is the corresponding quantity of multiple subregions, and the value range of i is [1, n], AiFor the corresponding normalizing of i-th of subregion
Change accounting value, XiFor the corresponding defect point quantity of i-th of subregion, STFor the corresponding area of defect point diagram to be detected, SiIt is i-th
The corresponding area of subregion, X1For the corresponding defect point quantity of the 1st subregion, S1For the 1st corresponding area of subregion, X2It is the 2nd
The corresponding defect point quantity of subregion, S2For corresponding area ... the X of the 2nd subregionnFor the corresponding defect point quantity of n-th of subregion, Sn
For the corresponding area of n-th of subregion.
205, processing is amplified to multiple normalization accounting values and variance threshold values.
In embodiments of the present invention, due to, the operand magnitude for calculating multiple normalization accounting values of acquisition is smaller, because
This, for the ease of operation, terminal device needs to amplify processing to multiple normalization accounting values and variance threshold values.Specifically,
In this step, default amplification factor pair can be used when amplifying processing to multiple normalization accounting values in terminal device
Each normalization accounting value amplifies processing;And when amplifying processing to variance threshold values, it can first calculate default amplification
The square value of multiple, the square value for reusing default amplification factor amplify processing to variance threshold values, wherein default times magnification
Number can be, but not limited to are as follows: 50,100,200 etc..
206, multiple normalization accountings after enhanced processing are calculated and is worth corresponding variance yields.
In embodiments of the present invention, terminal device can calculate after amplifying processing to multiple normalization accounting values
Multiple normalization accountings after enhanced processing are worth corresponding variance yields, i.e., first calculate multiple normalizings after enhanced processing
Change accounting and be worth corresponding average value, then by the average value of multiple normalization accounting values and calculating acquisition after enhanced processing
It is updated in variance calculation formula, the corresponding variance yields of multiple normalization accounting values after enhanced processing can be calculated.
207, judge whether the corresponding variance yields of multiple normalization accounting values after enhanced processing is greater than by amplification
Variance threshold values that treated.
In embodiments of the present invention, terminal device is calculating the correspondence of multiple normalization accounting values after enhanced processing
Variance yields after, can judge whether calculated variance yields is greater than the variance threshold values after enhanced processing, so as to subsequent
It is judged that result determines whether the defects of defect point diagram to be detected point has aggregation.
208, if so, determining that the defects of defect point diagram to be detected point has aggregation.
Wherein, about step 208, if so, determining that the defects of defect point diagram to be detected point has aggregation, Ke Yican
The description of Fig. 1 corresponding part is examined, the embodiment of the present invention will not be described in great detail herein.
To achieve the goals above, according to another aspect of the present invention, the embodiment of the invention also provides a kind of electronics to set
It is standby, the electronic equipment include: memory, processor and storage on a memory and the program that can run on a processor, institute
When stating processor and executing described program, the method for realizing detection defect point aggregation described above.
To achieve the goals above, according to another aspect of the present invention, the embodiment of the invention also provides a kind of computers
Readable storage medium storing program for executing, is stored thereon with computer program, and described program realizes detection defect point aggregation described above when running
The method of property.
Further, as the realization to method shown in above-mentioned Fig. 1, Fig. 3, the embodiment of the invention provides a kind of detections to lack
The device of trapping spot aggregation.The Installation practice is corresponding with preceding method embodiment, and to be easy to read, present apparatus embodiment is no longer
Detail content in preceding method embodiment is repeated one by one, it should be understood that the device in the present embodiment can correspond to
Realize the full content in preceding method embodiment.The device is applied to improve whether the defects of detection defect point diagram point has
The detection efficiency and accuracy of aggregation, specifically as shown in figure 4, the device includes:
Acquiring unit 301, for obtaining defect point diagram, partitioned mode, number of partitions and variance threshold values to be detected;
Region segmentation unit 302, the partitioned mode and the number of partitions pair for being obtained according to acquiring unit 301
The defect point diagram to be detected carries out region segmentation processing, to obtain multiple subregions;
First determination unit 303, for determining the corresponding defect point quantity of each subregion;
First computing unit 304, for according to each of the first determination unit 303 determination corresponding defect point of the subregion
Quantity calculates the corresponding normalization accounting value of each subregion;
Second computing unit 305, for calculating the corresponding variance yields of multiple normalization accounting values;
Whether judging unit 306, the variance yields for judging that the second computing unit 305 calculates are greater than the variance threshold
Value;
Second determination unit 307, for when judging unit 306 judge the variance yields be greater than the variance threshold values when, really
The defects of fixed described defect point diagram to be detected point has aggregation.
Further, as shown in figure 5, the partitioned mode is vertical division block mode or horizontal partition mode;First calculates
Unit 304 includes:
First computing module 3041, for calculating described to be detected lack according to the corresponding defect point quantity of each subregion
The corresponding defect point quantity of trapping spot figure;
Second computing module 3042 accounts for the defect to be detected for calculating the corresponding defect point quantity of each subregion
The ratio of the corresponding defect point quantity of point diagram, to obtain the corresponding normalization accounting value of each subregion.
Further, oblique partitioned mode or oblique partitioned mode is born as shown in figure 5, the partitioned mode is positive;First calculates
Unit 304 includes:
Determining module 3043, for determining that the corresponding area of the defect point diagram to be detected and each subregion are corresponding
Area;
Third computing module 3044, for will the corresponding defect point quantity of each subregion, each subregion correspondence
Area and the corresponding area of the defect point diagram to be detected substitute into preset algorithm, calculate that each subregion is corresponding to return
One changes accounting value.
Further, as shown in figure 5, the device further include:
First amplifying unit 308, in the first computing unit 304 according to the corresponding defect point quantity of each subregion
After calculating the corresponding normalization accounting value of each subregion, using default amplification factor to each normalization accounting value
Amplify processing;
Third computing unit 309, for calculating the square value of the default amplification factor;
Second amplifying unit 310, the square value for using third computing unit 309 to calculate is to the variance threshold values
Amplify processing;
Second computing unit 305, it is corresponding specifically for calculating multiple normalization accounting values after enhanced processing
Variance yields;
Judging unit 306, specifically for judging the corresponding side of multiple normalization accounting values after enhanced processing
Whether difference is greater than the variance threshold values after enhanced processing.
Further, as shown in figure 5, the partitioned mode is vertical division block mode, horizontal partition mode, just oblique square partition
Formula bears any one in oblique partitioned mode.
In conclusion the embodiment of the present invention provides a kind of method and device for detecting defect point aggregation, with the prior art
In, detect whether the defects of defect point diagram point is compared with aggregation by the way of artificial detection, the present invention can be at end
Point that end equipment acquires the defect point diagram to be detected of AOI detection device drafting and staff sets according to detection demand
After area's mode, number of partitions and variance threshold values, by terminal device according to partitioned mode and number of partitions to defect point figure to be detected
Region segmentation processing is carried out, to obtain multiple subregions;Terminal device after determining the corresponding defect point quantity of each subregion,
The corresponding normalization accounting value of each subregion is calculated according to the corresponding defect point quantity of each subregion, and calculates multiple normalization and accounts for
The corresponding variance yields of ratio;Terminal device when determining the corresponding variance yields of multiple normalization accounting values greater than variance threshold values,
It can determine that the defects of defect point diagram to be detected point has aggregation.Due to being by terminal device detection defect point diagram
Whether defect point has aggregation, therefore, can be improved the detection whether the defects of detection defect point diagram point has aggregation
Efficiency;Also, terminal device can detect multiple defect point diagrams using identical examination criteria, therefore, can be improved
Detect the accuracy whether the defects of defect point diagram point has aggregation.
The device of the detection defect point aggregation includes processor and memory, above-mentioned acquiring unit, region segmentation list
Member, the first determination unit, the first computing unit, the second computing unit, judging unit and the second determination unit etc. are used as program
Unit stores in memory, executes above procedure unit stored in memory by processor to realize corresponding function.
Include kernel in processor, is gone in memory to transfer corresponding program unit by kernel.Kernel can be set one
Or more, by adjusting kernel parameter come improve detection the defects of defect point diagram point whether detection efficiency with aggregation and
Accuracy.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/
Or the forms such as Nonvolatile memory, if read-only memory (ROM) or flash memory (flash RAM), memory include that at least one is deposited
Store up chip.
The embodiment of the invention provides a kind of electronic equipment, the electronic equipment includes: memory, processor and is stored in
On memory and the program that can run on a processor, when the processor executes described program, the detection defect is realized
The method of point aggregation.
The embodiment of the invention provides a kind of computer readable storage mediums, are stored thereon with computer program, the journey
The method of detection defect point aggregation described above is realized when sort run.
The embodiment of the invention provides a kind of equipment, equipment include processor, memory and storage on a memory and can
The program run on a processor, processor perform the steps of when executing program
Obtain defect point diagram, partitioned mode, number of partitions and variance threshold values to be detected;
Region segmentation processing is carried out to the defect point diagram to be detected according to the partitioned mode and the number of partitions, with
Obtain multiple subregions;
Determine the corresponding defect point quantity of each subregion, and according to the corresponding defect point quantity meter of each subregion
Calculate the corresponding normalization accounting value of each subregion;
Calculate the corresponding variance yields of multiple normalization accounting values;
Judge whether the variance yields is greater than the variance threshold values;
If so, determining that the defects of described defect point diagram to be detected point has aggregation.
Further, the partitioned mode is vertical division block mode or horizontal partition mode;Each described point of the basis
The corresponding defect point quantity in area calculates the corresponding normalization accounting value of each subregion, comprising:
The corresponding defect points of the defect point diagram to be detected are calculated according to the corresponding defect point quantity of each subregion
Amount;
It calculates the corresponding defect point quantity of each subregion and accounts for the corresponding defect point quantity of the defect point diagram to be detected
Ratio, to obtain the corresponding normalization accounting value of each subregion.
Further, the partitioned mode, which is positive, oblique partitioned mode or bears oblique partitioned mode;Each described point of the basis
The corresponding defect point quantity in area calculates the corresponding normalization accounting value of each subregion, comprising:
Determine the corresponding area of the defect point diagram to be detected and the corresponding area of each subregion;
By the corresponding defect point quantity of each subregion, the corresponding area of each subregion and described to be detected lack
The corresponding area of trapping spot figure substitutes into preset algorithm, calculates the corresponding normalization accounting value of each subregion.
Further, corresponding according to each subregion of each corresponding defect point quantity calculating of subregion described
After normalizing accounting value, the method also includes:
Processing is amplified to each normalization accounting value using default amplification factor;
The square value of the default amplification factor is calculated, and place is amplified to the variance threshold values using the square value
Reason;
It is described to calculate the corresponding variance yields of multiple normalization accountings values, comprising:
It calculates multiple normalization accountings after enhanced processing and is worth corresponding variance yields;
It is described to judge whether the variance yields is greater than the variance threshold values, comprising:
Judge whether the corresponding variance yields of multiple normalization accounting values after enhanced processing is greater than by amplification
The variance threshold values that treated.
Further, the partitioned mode is vertical division block mode, horizontal partition mode, just oblique partitioned mode, bears and tiltedly divide
Any one in area's mode.
Equipment herein can be server, PC etc..
Present invention also provides a kind of computer program products, when executing on data processing equipment, are adapted for carrying out just
The program code of beginningization there are as below methods step: defect point diagram, partitioned mode, number of partitions and variance threshold values to be detected are obtained;
Region segmentation processing is carried out to the defect point diagram to be detected according to the partitioned mode and the number of partitions, it is multiple to obtain
Subregion;It determines the corresponding defect point quantity of each subregion, and is calculated according to the corresponding defect point quantity of each subregion
The corresponding normalization accounting value of each subregion;Calculate the corresponding variance yields of multiple normalization accounting values;Described in judgement
Whether variance yields is greater than the variance threshold values;If so, determining that the defects of described defect point diagram to be detected point has aggregation.
It should be understood by those skilled in the art that, embodiments herein can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the application, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The application is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
In a typical configuration, calculating equipment includes one or more processors (CPU), input/output interface, net
Network interface and memory.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/
Or the forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable Jie
The example of matter.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM),
Digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices
Or any other non-transmission medium, can be used for storage can be accessed by a computing device information.As defined in this article, it calculates
Machine readable medium does not include temporary computer readable media (traHsitory media), such as the data-signal and carrier wave of modulation.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including element
There is also other identical elements in process, method, commodity or equipment.
It will be understood by those skilled in the art that embodiments herein can provide as method, system or computer program product.
Therefore, complete hardware embodiment, complete software embodiment or embodiment combining software and hardware aspects can be used in the application
Form.It is deposited moreover, the application can be used to can be used in the computer that one or more wherein includes computer usable program code
The shape for the computer program product implemented on storage media (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
Formula.
The above is only embodiments herein, are not intended to limit this application.To those skilled in the art,
Various changes and changes are possible in this application.It is all within the spirit and principles of the present application made by any modification, equivalent replacement,
Improve etc., it should be included within the scope of the claims of this application.
Claims (12)
1. a kind of method for detecting defect point aggregation, which is characterized in that the described method includes:
Obtain defect point diagram, partitioned mode, number of partitions and variance threshold values to be detected;
Region segmentation processing is carried out to the defect point diagram to be detected according to the partitioned mode and the number of partitions, to obtain
Multiple subregions;
It determines the corresponding defect point quantity of each subregion, and is calculated according to the corresponding defect point quantity of each subregion every
The corresponding normalization accounting value of a subregion;
Calculate the corresponding variance yields of multiple normalization accounting values;
Judge whether the variance yields is greater than the variance threshold values;
If so, determining that the defects of described defect point diagram to be detected point has aggregation.
2. the method according to claim 1, wherein the partitioned mode is vertical division block mode or horizontal partition
Mode;It is described that the corresponding normalization accounting value of each subregion is calculated according to the corresponding defect point quantity of each subregion,
Include:
The corresponding defect point quantity of the defect point diagram to be detected is calculated according to the corresponding defect point quantity of each subregion;
Calculate the ratio that the corresponding defect point quantity of each subregion accounts for the corresponding defect point quantity of the defect point diagram to be detected
Value, to obtain the corresponding normalization accounting value of each subregion.
3. oblique partitioned mode or bearing oblique subregion the method according to claim 1, wherein the partitioned mode is positive
Mode;It is described that the corresponding normalization accounting value of each subregion is calculated according to the corresponding defect point quantity of each subregion,
Include:
Determine the corresponding area of the defect point diagram to be detected and the corresponding area of each subregion;
By the corresponding defect point quantity of each subregion, each corresponding area of subregion and the defect point to be detected
Scheme corresponding area to substitute into preset algorithm, calculates the corresponding normalization accounting value of each subregion.
4. method according to any one of claim 1-3, which is characterized in that described corresponding according to each subregion
Defect point quantity calculate the corresponding normalization accounting value of each subregion after, the method also includes:
Processing is amplified to each normalization accounting value using default amplification factor;
The square value of the default amplification factor is calculated, and processing is amplified to the variance threshold values using the square value;
It is described to calculate the corresponding variance yields of multiple normalization accountings values, comprising:
It calculates multiple normalization accountings after enhanced processing and is worth corresponding variance yields;
It is described to judge whether the variance yields is greater than the variance threshold values, comprising:
Judge whether the corresponding variance yields of multiple normalization accounting values after enhanced processing is greater than by enhanced processing
The variance threshold values afterwards.
5. the method according to claim 1, wherein the partitioned mode is vertical division block mode, horizontal partition
Mode, just oblique partitioned mode bear any one in oblique partitioned mode.
6. a kind of device for detecting defect point aggregation, which is characterized in that described device includes:
Acquiring unit, for obtaining defect point diagram, partitioned mode, number of partitions and variance threshold values to be detected;
Region segmentation unit, the partitioned mode and the number of partitions for being obtained according to the acquiring unit to it is described to
It detects defect point diagram and carries out region segmentation processing, to obtain multiple subregions;
First determination unit, for determining the corresponding defect point quantity of each subregion;
First computing unit, based on the corresponding defect point quantity of the subregion each of determining according to first determination unit
Calculate the corresponding normalization accounting value of each subregion;
Second computing unit, for calculating the corresponding variance yields of multiple normalization accounting values;
Whether judging unit, the variance yields for judging that second computing unit calculates are greater than the variance threshold values;
Second determination unit, described in determining when the judging unit judges that the variance yields is greater than the variance threshold values
The defects of defect point diagram to be detected point has aggregation.
7. device according to claim 6, which is characterized in that the partitioned mode is vertical division block mode or horizontal partition
Mode;First computing unit includes:
First computing module, for according to each corresponding defect point quantity calculating of subregion defect point diagram pair to be detected
The defect point quantity answered;
Second computing module accounts for the defect point diagram correspondence to be detected for calculating the corresponding defect point quantity of each subregion
Defect point quantity ratio, to obtain the corresponding normalization accounting value of each subregion.
8. device according to claim 6, which is characterized in that the partitioned mode, which is positive, oblique partitioned mode or bears oblique subregion
Mode;First computing unit includes:
Determining module, for determining the corresponding area of the defect point diagram to be detected and the corresponding area of each subregion;
Third computing module, for by the corresponding defect point quantity of each subregion, the corresponding area of each subregion with
And the corresponding area of the defect point diagram to be detected substitutes into preset algorithm, calculates the corresponding normalization accounting of each subregion
Value.
9. device a method according to any one of claims 6-8, which is characterized in that described device further include:
First amplifying unit, it is every for being calculated in first computing unit according to the corresponding defect point quantity of each subregion
After the corresponding normalization accounting value of a subregion, each normalization accounting value is put using default amplification factor
Big processing;
Third computing unit, for calculating the square value of the default amplification factor;
Second amplifying unit, the square value for being calculated using the third computing unit put the variance threshold values
Big processing;
Second computing unit is worth corresponding side specifically for calculating multiple normalization accountings after enhanced processing
Difference;
The judging unit, specifically for judging the corresponding variance yields of multiple normalization accounting values after enhanced processing
Whether the variance threshold values after enhanced processing are greater than.
10. device according to claim 6, which is characterized in that the partitioned mode is vertical division block mode, horizontal partition
Mode, just oblique partitioned mode bear any one in oblique partitioned mode.
11. a kind of electronic equipment characterized by comprising memory, processor and storage are on a memory and can be in processor
The program of upper operation when the processor executes described program, realizes such as detection defect point as claimed in any one of claims 1 to 5
The method of aggregation.
12. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that when described program is run
Realize the method such as detection defect point aggregation as claimed in any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910169245.XA CN109886956B (en) | 2019-03-06 | 2019-03-06 | Method and device for detecting defect point aggregations |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910169245.XA CN109886956B (en) | 2019-03-06 | 2019-03-06 | Method and device for detecting defect point aggregations |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109886956A true CN109886956A (en) | 2019-06-14 |
CN109886956B CN109886956B (en) | 2021-11-30 |
Family
ID=66930992
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910169245.XA Expired - Fee Related CN109886956B (en) | 2019-03-06 | 2019-03-06 | Method and device for detecting defect point aggregations |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109886956B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111090685A (en) * | 2019-12-19 | 2020-05-01 | 第四范式(北京)技术有限公司 | Method and device for detecting data abnormal characteristics |
CN111403309A (en) * | 2020-03-30 | 2020-07-10 | 上海华力集成电路制造有限公司 | Wafer aggregation-like defect detection method and detection system thereof |
CN114911085A (en) * | 2022-01-03 | 2022-08-16 | 友达光电股份有限公司 | Method for analyzing defects |
US11972548B2 (en) | 2020-12-03 | 2024-04-30 | Boe Technology Group Co., Ltd. | Computer-implemented method for defect analysis, apparatus for defect analysis, computer-program product, and intelligent defect analysis system |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020181756A1 (en) * | 2001-04-10 | 2002-12-05 | Hisae Shibuya | Method for analyzing defect data and inspection apparatus and review system |
US20040032979A1 (en) * | 2002-08-12 | 2004-02-19 | Hitachi High-Technologies Corporation | Defect inspection method |
CN101432864A (en) * | 2006-04-27 | 2009-05-13 | 夏普株式会社 | Method and system for classifying defect distribution, method and system for specifying causative equipment, computer program and recording medium |
CN106054421A (en) * | 2016-07-28 | 2016-10-26 | 京东方科技集团股份有限公司 | Liquid crystal display panel defect detecting method and device |
CN107534756A (en) * | 2016-03-24 | 2018-01-02 | 香港应用科技研究院有限公司 | Fast density method of estimation for defect inspection application |
CN108445020A (en) * | 2018-01-31 | 2018-08-24 | 彩虹显示器件股份有限公司 | A kind of glass substrate defect aggregation recognition methods |
-
2019
- 2019-03-06 CN CN201910169245.XA patent/CN109886956B/en not_active Expired - Fee Related
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020181756A1 (en) * | 2001-04-10 | 2002-12-05 | Hisae Shibuya | Method for analyzing defect data and inspection apparatus and review system |
US20040032979A1 (en) * | 2002-08-12 | 2004-02-19 | Hitachi High-Technologies Corporation | Defect inspection method |
CN101432864A (en) * | 2006-04-27 | 2009-05-13 | 夏普株式会社 | Method and system for classifying defect distribution, method and system for specifying causative equipment, computer program and recording medium |
CN107534756A (en) * | 2016-03-24 | 2018-01-02 | 香港应用科技研究院有限公司 | Fast density method of estimation for defect inspection application |
CN106054421A (en) * | 2016-07-28 | 2016-10-26 | 京东方科技集团股份有限公司 | Liquid crystal display panel defect detecting method and device |
CN108445020A (en) * | 2018-01-31 | 2018-08-24 | 彩虹显示器件股份有限公司 | A kind of glass substrate defect aggregation recognition methods |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111090685A (en) * | 2019-12-19 | 2020-05-01 | 第四范式(北京)技术有限公司 | Method and device for detecting data abnormal characteristics |
CN111090685B (en) * | 2019-12-19 | 2023-08-22 | 第四范式(北京)技术有限公司 | Method and device for detecting abnormal characteristics of data |
CN111403309A (en) * | 2020-03-30 | 2020-07-10 | 上海华力集成电路制造有限公司 | Wafer aggregation-like defect detection method and detection system thereof |
US11972548B2 (en) | 2020-12-03 | 2024-04-30 | Boe Technology Group Co., Ltd. | Computer-implemented method for defect analysis, apparatus for defect analysis, computer-program product, and intelligent defect analysis system |
CN114911085A (en) * | 2022-01-03 | 2022-08-16 | 友达光电股份有限公司 | Method for analyzing defects |
Also Published As
Publication number | Publication date |
---|---|
CN109886956B (en) | 2021-11-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR102513713B1 (en) | Methods and systems for fault classification | |
CN109886956A (en) | Detect the method and device of defect point aggregation | |
CN103748670A (en) | Region setting device, observation device or inspection device, region setting method, and observation method or inspection method using region setting method | |
CN109283182A (en) | A kind of detection method of battery welding point defect, apparatus and system | |
CN110189300A (en) | Detection method, detection device, storage medium and the processor of pass structure processing quality | |
CN115824993B (en) | Method and device for determining water body chemical oxygen demand, computer equipment and medium | |
CN111506731B (en) | Method, device and equipment for training field classification model | |
US9652836B2 (en) | Defect cell clustering method and apparatus thereof | |
CN110188322A (en) | A kind of wave-shape amplitude uncertainty determines method and system | |
CN109726068A (en) | A kind of data detection method and device | |
Choudhary et al. | Autonomous visual detection of defects from battery electrode manufacturing | |
US20120029863A1 (en) | Particle distribution analysis method for computer readable storage medium for storing program for executing the method | |
CN110017998A (en) | Vehicle checking method, device and equipment | |
CN115510998A (en) | Transaction abnormal value detection method and device | |
CN107369093A (en) | A kind of business determines method and apparatus | |
CN109523530A (en) | A kind of micro strip circular pad detection method and system | |
CN113255671B (en) | Target detection method, system, device and medium for object with large length-width ratio | |
CN107818051A (en) | The branch instruction analysis method, apparatus and server of a kind of test case | |
CN109443697B (en) | Optical center testing method, device, system and equipment | |
CN104933705B (en) | A kind of space-time loop data structure carries out the method and device of slot detection | |
CN109472772A (en) | Image smear detection method, device and equipment | |
CN109857665A (en) | A kind of test execution method and device of test case | |
CN116012330B (en) | Pole piece defect detection method, device, equipment and computer storage medium | |
CN108763092A (en) | A kind of aacode defect detection method and device based on cross validation | |
CN114637868B (en) | Product data processing method and system applied to fast-moving industry |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20211130 |
|
CF01 | Termination of patent right due to non-payment of annual fee |