CN118351111B - Method, device, equipment and storage medium for detecting chip surface defects - Google Patents
Method, device, equipment and storage medium for detecting chip surface defects Download PDFInfo
- Publication number
- CN118351111B CN118351111B CN202410763844.5A CN202410763844A CN118351111B CN 118351111 B CN118351111 B CN 118351111B CN 202410763844 A CN202410763844 A CN 202410763844A CN 118351111 B CN118351111 B CN 118351111B
- Authority
- CN
- China
- Prior art keywords
- defect
- defects
- chip
- minimum
- minimum comparison
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000007547 defect Effects 0.000 title claims abstract description 210
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000003860 storage Methods 0.000 title claims abstract description 10
- 238000001514 detection method Methods 0.000 claims abstract description 46
- 230000011218 segmentation Effects 0.000 claims abstract description 16
- 238000012545 processing Methods 0.000 claims abstract description 10
- 239000011159 matrix material Substances 0.000 claims abstract description 9
- 230000002950 deficient Effects 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 12
- 238000012216 screening Methods 0.000 claims description 8
- 238000009826 distribution Methods 0.000 claims description 4
- 238000005070 sampling Methods 0.000 abstract description 2
- 238000007619 statistical method Methods 0.000 abstract description 2
- 238000004519 manufacturing process Methods 0.000 description 19
- 238000004891 communication Methods 0.000 description 10
- 238000003466 welding Methods 0.000 description 8
- 239000000306 component Substances 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000003064 k means clustering Methods 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 239000012467 final product Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
- G06V10/763—Non-hierarchical techniques, e.g. based on statistics of modelling distributions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30148—Semiconductor; IC; Wafer
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Probability & Statistics with Applications (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a method, a device, equipment and a storage medium for detecting surface defects of a chip, which belong to the technical field of image data processing, wherein the method comprises the following steps: obtaining a standard template and a sample data set of the same batch, and carrying out segmentation processing on each sample image to obtain a minimum comparison unit; setting a difference threshold, and comparing each minimum comparison unit of the sample image with the chip image in the standard template to obtain a defect unit; carrying out probability statistics on defect units of the sample image to obtain a difference matrix, and obtaining the defect probability of each minimum comparison unit; and then, carrying out statistical analysis on the defects obtained by detection, obtaining a defect region set under different confidence levels, and reasonably planning the detection center region in the defect region set, so that the scanning times and the sampling amount of defect detection can be greatly reduced, the rest chips in the same batch of chips can be reasonably planned, and the whole regions of the rest chips do not need to be photographed one by one, thereby saving time.
Description
Technical Field
The invention belongs to the technical field of image data processing, and particularly relates to a method, a device, equipment and a storage medium for detecting surface defects of a chip.
Background
Chips play a critical role in modern technology and electronics. Chips are the core components of computers and other electronic devices with highly integrated electronic components. By providing processors, memory, and other critical functions, chips have driven a continual rise in computing power so that electronic devices can perform more complex, efficient tasks. The chip is a key for realizing the intellectualization of the electronic equipment. Through integrated sensor, processing unit and communication function, the chip makes equipment can perception, analysis and response environment to realize more intelligent function, such as artificial intelligence, thing networking equipment etc..
For chips, any surface defect is likely to affect the performance and reliability, the problem of the chip surface can be found and repaired early through defect detection, the quality of the final product is ensured to reach the specified standard, an automatic surface defect detection system can realize rapid and accurate detection on a production line, the inefficiency and the manual error caused by the traditional manual inspection mode are avoided, the production efficiency is improved, the production cost is reduced, and the mass production is supported.
With rapid development of pattern recognition, machine vision, deep learning, etc., and urgent need for chip surface defect detection, more and more modern technologies are applied to chip surface defect detection.
However, the current chip detection is more time-consuming, and the chip surface defect detection device is high-precision scanning device or image device, which has higher cost, and although the automatic detection can be realized, the shooting scanning detection of all the areas of the chip one by one still needs a lot of time cost, so that the chip surface defect detection of the large-scale chip production line is difficult to be qualified, the detection efficiency of the chip surface defect in the large-scale chip production line is low, the defect detection result cannot be given in real time, and the production efficiency is reduced.
Disclosure of Invention
In order to solve the technical problems that the current chip surface defect detection algorithm based on deep learning needs to carry out photographing scanning detection on all areas to be detected of a chip one by one when detecting the chip surface defects, and although automatic detection can be realized, photographing scanning on the chip one by one still needs to take a lot of time, so that the detection of the surface defects of a large-scale chip production line is difficult to be qualified, the detection efficiency of the chip surface defects in the large-scale chip production line is low, the defect detection result cannot be given in real time, and the production efficiency is reduced.
First aspect
The invention provides a method for detecting surface defects of a chip, which comprises the following steps:
s1: obtaining a standard template and a sample data set, wherein the sample data set comprises a plurality of chip images of the same batch;
s2: representing sample images in a sample dataset as Where i represents the ith sample image and the chip image in the standard template is represented as，Representing pixel coordinates, and dividing each sample image to obtain a minimum comparison unit；
S3: setting a difference thresholdEach minimum comparison unit for sample imagesComparing with the chip image in the standard template, and when the minimum comparison unit is used forThe difference degree of the minimum unit corresponding to the standard template is larger than the difference degree threshold valueWhen the minimum comparison unit is marked as a defect unit;
s4: carrying out probability statistics on defective units of the sample image to obtain a difference matrix And obtain the defect probability of each minimum comparison unitAccording to the normal distribution rule, the mean value is utilizedAnd standard deviationObtaining the confidence intervalAll minimum alignment units with defects in the set are defect area sets, wherein x is a selected confidence level;
s5: calculating the distance between the minimum alignment units in the defect area set Setting the radius value r and the circle center position asCalculating the minimum number of aligned units having defects in the set circular region:
s6: setting a defect quantity threshold value a and adjusting the circle center Obtaining a circle center coordinate set A with the number of the minimum comparison units with defects not less than aBased on circle center coordinate set AAnd performing defect detection on the rest chips in the same batch.
In the method for detecting a surface defect of a chip, preferably, the step S3 includes:
S301: definition of degree of difference For each pixel pointSum of squares of luminance differences at:
，
s302: setting a difference threshold Each minimum comparison unit for sample imagesComparing with the chip image in the standard template, ifThen the cell is determined to be a defective cell.
In the method for detecting a chip surface defect, preferably, the step S4 calculates a defect probability of each minimum alignment unitComprising the following steps:
S401: carrying out probability statistics on defective units of the sample image to obtain a difference matrix ；
S402: defining probability of defectFor pixel coordinatesSurrounding is provided withAverage value of the minimum comparison unit difference degree in the region, wherein:
，
In the method for detecting a chip surface defect, preferably, the average value is used in S4 And standard deviationObtaining the confidence intervalThe total minimum comparison units with defects in the defect area set is as follows:
。
In the method for detecting a defect on a chip surface, preferably, the step of calculating the minimum number of comparison units having a defect in the circular area in S5 includes:
s501: calculating the distance between the minimum alignment units in the defect area set ；
S502: setting the radius value r and the circle center position asCalculating the minimum number of aligned units having defects in the set circular region，To set the radius value r and the circle center position asLeast alignment unit in circular area of (a)Is the total of (a):
；
In the method for detecting the surface defects of the chip, preferably, the radius value r is 1/5 of the long side of the visual field of the image acquisition equipment for the surface defects of the chip.
In the method for detecting a chip surface defect, preferably, in S6, a set of center coordinates a is determinedThe method comprises the following steps:
s601: setting a defect number threshold a;
s602: adjusting the center of a circle Obtaining a circle center coordinate set A with the number of the minimum comparison units with defects not less than a；
S603: the numerical value of the defect quantity threshold value a is adjusted to enable the circle center coordinate set AThe number of center circles is 5-20;
s604: based on circle center coordinate set A And performing defect detection on the rest chips in the same batch.
Second aspect
The invention provides a device for detecting surface defects of a chip, which comprises:
The acquisition module is used for acquiring a standard template and a sample data set, wherein the sample data set comprises a plurality of chip images of the same batch;
The segmentation module is used for carrying out segmentation processing on the sample images in the sample data set to obtain a minimum comparison unit;
The marking module is used for marking the minimum comparison unit as a defect unit when the difference degree of the minimum comparison unit corresponding to the standard template is larger than a difference degree threshold;
The first screening module is used for carrying out probability statistics on defect units of the sample image, obtaining the defect probability of each minimum comparison unit, and obtaining that all the minimum comparison units with defects in a confidence interval are defect area sets by means of the mean value and the standard deviation;
The second screening module is used for calculating the distance between the minimum comparison units in the defect area set, setting a radius value and a circular area with the circle center position, and calculating the number of the minimum comparison units with defects in the set circular area:
And an output module: setting a defect number threshold value, adjusting the position of a circle center, obtaining a circle center coordinate set with the number of the minimum comparison units with defects not smaller than the defect number threshold value, and detecting the defects of the rest chips in the same batch based on the circle center coordinate set.
Third aspect of the invention
The present invention provides a computer device comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method for detecting a chip surface defect according to the first aspect when executing the computer program.
Fourth aspect of
The present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of detecting a chip surface defect as described in the first aspect.
Compared with the prior art, the invention has at least the following beneficial technical effects:
According to the invention, small batch spot inspection and detailed detection can be performed on chips in the same batch, then statistical analysis is performed on defects obtained by detection, a defect area set under different confidence levels is obtained, the scanning times and sampling amount of defect detection can be greatly reduced by reasonably planning the detection center area in the defect area set, the rest chips in the same batch can be reasonably planned, the whole areas of the rest chips are not required to be photographed one by one, the time is saved, the surface defect detection of a large-scale chip production line can be realized, the surface defect detection efficiency of the large-scale chip production line is improved, the defect detection result is given in real time, and the production efficiency is improved.
Drawings
The above features, technical features, advantages and implementation of the present invention will be further described in the following description of preferred embodiments with reference to the accompanying drawings in a clear and easily understood manner.
Fig. 1 is a schematic flow chart of a method for detecting a chip surface defect according to the present invention.
Fig. 2 is a schematic structural diagram of a device for detecting surface defects of a chip according to the present invention.
Detailed Description
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following description will explain the specific embodiments of the present invention with reference to the accompanying drawings. It is evident that the drawings in the following description are only examples of the invention, from which other drawings and other embodiments can be obtained by a person skilled in the art without inventive effort.
For simplicity of the drawing, only the parts relevant to the invention are schematically shown in each drawing, and they do not represent the actual structure thereof as a product. Additionally, in order to simplify the drawing for ease of understanding, components having the same structure or function in some of the drawings are shown schematically with only one of them, or only one of them is labeled. Herein, "a" means not only "only this one" but also "more than one" case.
It should also be understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
In this context, it should be noted that the terms "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected, unless otherwise explicitly stated and defined. It may be a mechanical connection that is made, or may be an electrical connection. Can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
In addition, in the description of the present invention, the terms "first," "second," and the like are used merely to distinguish between descriptions and are not to be construed as indicating or implying relative importance.
Example 1
In one embodiment, referring to fig. 1 of the specification, a schematic flow chart of a method for detecting a chip surface defect according to the present invention is shown. Referring to fig. 2 of the specification, a schematic structural diagram of a method for detecting a chip surface defect according to the present invention is shown.
The invention provides a method for detecting surface defects of a chip, which comprises the following steps:
s1: obtaining a standard template and a sample data set, wherein the sample data set comprises a plurality of chip images of the same batch;
Where a standard template generally refers to a reference template representing a good or normal state for comparison with the chip image in the sample dataset. The standard template is obtained by analyzing and summarizing a large number of normal chip images, and contains information such as characteristics, shapes, colors and the like of welding spot areas of the normal chips. The standard template may be a common defect pattern in the chip design drawing such as surface redundancy, flow defects, particle defects, etc.
S2: representing sample images in a sample dataset asWhere i represents the ith sample image and the chip image in the standard template is represented as，Representing pixel coordinates, and dividing each sample image to obtain a minimum comparison unit；
When the minimum comparison unit is obtained in the process of dividing the sample image, an edge-based dividing method can be used, for example, by detecting the edges of different areas to solve the dividing problem. For example, by setting appropriate filter parameters, edges of the image are identified and segmentation of the image is achieved based on image gray level variations and discontinuities. In addition, the division of the sample image may also be performed using a fixed image size, for example, by dividing the image by a fixed a×a square unit, where the total length or the total width of the sample image is an integer multiple of a.
In the invention, the preset segmentation template for the same batch of chip sample images can be obtained by using the edge-based segmentation method or the least unit-based segmentation method, and the same template is applied to a plurality of sample images, so that the image can be rapidly segmented.
When the image is used for identifying the edges of the image and dividing the image based on the gray level change and the discontinuity of the image, the units for dividing the sample image can be made small enough by reasonably setting the parameters of the filter; similarly, when dividing an image by a×a square cell, a proper cell size can be obtained by reasonably selecting the value of the cell side length a, and thus the efficiency and accuracy of defect identification can be both achieved.
S3: setting a difference thresholdEach minimum comparison unit for sample imagesComparing with the chip image in the standard template, and when the minimum comparison unit is used forThe difference degree of the minimum unit corresponding to the standard template is larger than the difference degree threshold valueWhen the minimum comparison unit is marked as a defect unit;
In one possible implementation manner, the present invention proposes a new defect comparison algorithm, and S3 specifically includes sub-steps S301 to S302:
S301: definition of degree of difference For each pixel pointSum of squares of luminance differences at:
，
Wherein the method comprises the steps of 、The pixel number of the minimum comparison unit in the sample image in the x direction and the y direction is represented, and the difference between all the minimum comparison units in the sample image and the standard template can be obtained through traversal calculation by summing up the squares of the brightness differences between the pixels in the minimum comparison unit area.
S302: setting a difference thresholdEach minimum comparison unit for sample imagesComparing with the chip image in the standard template, ifDetermining the minimum alignment unit as a defective unit:
In the invention, by reasonably setting the difference threshold value All minimum comparison units with defects can be screened, wherein the threshold value isCan be statistically derived from historical chip surface defects. In addition, the person skilled in the art can also set the difference threshold according to the actual situationThe size of (3) is not limited in the present invention.
S4: carrying out probability statistics on defective units of the sample image to obtain a difference matrixAnd obtain the defect probability of each minimum comparison unitAccording to the normal distribution rule, the mean value is utilizedAnd standard deviationObtaining the confidence intervalAll minimum alignment units with defects in the set are defect area sets, wherein x is a selected confidence level;
In the invention, the S4 has the function of calculating the defect probability of each minimum comparison unit The method specifically comprises the following steps:
S401: carrying out probability statistics on defective units of the sample image to obtain a difference matrix ；
S402: defining probability of defectFor pixel coordinatesAround which it is arrangedAverage value of the minimum comparison unit difference degree in the region, wherein:
,
the probability of the outgoing line defect unit of each region can be obtained by counting the difference degree of the minimum comparison unit in each region, and each region can be obtained by integration Defect probability of (a)。
S403: the mean value is utilized in the S4And standard deviationObtaining the confidence intervalThe total minimum comparison units with defects in the defect area set specifically comprises the following steps:
By setting three typical confidence interval probabilities of 90%,95% and 99%, the set area of the defect area under the corresponding defect probability can be obtained after the required defect probability confidence interval is selected, and the set area of the defect area under the corresponding defect probability can be obtained by scanning the areas, so that the number of the defect areas detected can be reduced.
S5: calculating the distance between the minimum alignment units in the defect area setSetting the radius value r and the circle center position asCalculating the minimum number of aligned units having defects in the set circular region:
in the present invention, the specific step of calculating the minimum number of aligned units with defects in the circular area in S5 includes:
s501: calculating the distance between the minimum alignment units in the defect area set ；
S502: setting the radius value r and the circle center position asCalculating the minimum number of aligned units having defects in the set circular region，To set the radius value r and the circle center position asLeast alignment unit in circular area of (a)Is the total of (a):
in the invention, the radius value r is 1/5 of the long side of the visual field of the chip surface defect image acquisition equipment. The radius value r is selected, so that the scanning times are reduced, the scanning times are matched with the common die size of the mobile phone chip by about 6mm, and the definition of the acquired image can be ensured.
S6: setting a defect quantity threshold value a and adjusting the circle centerObtaining a circle center coordinate set A with the number of the minimum comparison units with defects not less than aBased on circle center coordinate set AAnd performing defect detection on the rest chips in the same batch.
In the invention, a circle center coordinate set A is determined in S6The specific steps of (a) include:
s601: setting a defect number threshold a so that;
s602: adjusting the center of a circle Obtaining a circle center coordinate set A with the number of the minimum comparison units with defects not less than a；
S603: the numerical value of the defect quantity threshold value a is adjusted to enable the circle center coordinate set AThe number of center of the circle in (a) is 5-20;
s604: based on circle center coordinate set A And performing defect detection on the rest chips in the same batch.
Example 2
In one embodiment, referring to fig. 2 of the specification, a schematic structural diagram of a device for detecting a chip surface defect according to the present invention is shown.
The present invention provides a device 20 for detecting surface defects of a chip, comprising:
An acquisition module 201, configured to acquire a standard template and a sample data set, where the sample data set includes a plurality of chip images of a same batch;
The segmentation module 202 is configured to perform segmentation processing on a sample image in the sample data set to obtain a minimum comparison unit;
The marking module 203 is configured to mark the minimum comparison unit as a defect unit when the difference between the minimum comparison unit and the minimum unit corresponding to the standard template is greater than a difference threshold;
The first screening module 204 is configured to perform probability statistics on defective units of the sample image, obtain a defect probability of each minimum comparison unit, and obtain, by using a mean value and a standard deviation, that all the minimum comparison units having defects in the confidence interval are defect area sets;
The second screening module 205 is configured to calculate a distance between minimum comparison units in the defect area set, set a radius value and a circular area with a circle center position, and calculate the number of minimum comparison units in the set circular area, where defects exist:
And the output module 206 is configured to set a defect number threshold, adjust a position of a circle center, obtain a circle center coordinate set with a number of minimum comparison units with defects not less than the defect number threshold, and detect defects of the remaining chips in the same batch based on the circle center coordinate set.
In one possible implementation, the obtaining module 201 is specifically configured to: obtaining a standard template and a sample data set, wherein the sample data set comprises a plurality of chip images of the same batch;
The standard template is usually referred to as a reference template representing a good or normal state for comparison with the chip image in the sample dataset. The standard template is obtained by analyzing and summarizing a large number of normal chip images, and contains information such as characteristics, shapes, colors and the like of welding spot areas of the normal chips. The standard template may be a common defect pattern in the chip design drawing such as surface redundancy, flow defects, particle defects, etc.
The segmentation module 202 is specifically configured to: representing sample images in a sample dataset asWhere i represents the ith sample image and the chip image in the standard template is represented as，Representing pixel coordinates, and dividing each sample image to obtain a minimum comparison unit；
When the minimum comparison unit is obtained in the process of dividing the sample image, an edge-based dividing method can be used, for example, by detecting the edges of different areas to solve the dividing problem. For example, by setting appropriate filter parameters, edges of the image are identified and segmentation of the image is achieved based on image gray level variations and discontinuities. In addition, the division of the sample image may also be performed using a fixed image size, for example, by dividing the image by a fixed a×a square unit, where the total length or the total width of the sample image is an integer multiple of a.
In the invention, the preset segmentation template for the same batch of chip sample images can be obtained by using the edge-based segmentation method or the least unit-based segmentation method, and the same template is applied to a plurality of sample images, so that the image can be rapidly segmented.
When the image is used for identifying the edges of the image and dividing the image based on the gray level change and the discontinuity of the image, the units for dividing the sample image can be made small enough by reasonably setting the parameters of the filter; similarly, when dividing an image by a×a square cell, a proper cell size can be obtained by reasonably selecting the value of the cell side length a, and thus the efficiency and accuracy of defect identification can be both achieved.
The marking module 203 is specifically configured to: setting a difference thresholdEach minimum comparison unit for sample imagesComparing with the chip image in the standard template, and when the minimum comparison unit is used forThe difference degree of the minimum unit corresponding to the standard template is larger than the difference degree threshold valueWhen the minimum comparison unit is marked as a defect unit;
In one possible implementation manner, the present invention proposes a new defect comparison algorithm, and S3 specifically includes sub-steps S301 to S302:
S301, defining a degree of difference For each pixel pointSum of squares of luminance differences at:
，
Wherein the method comprises the steps of 、The pixel number of the minimum comparison unit in the sample image in the x direction and the y direction is represented, and the difference between all the minimum comparison units in the sample image and the standard template can be obtained through traversal calculation by summing up the squares of the brightness differences between the pixels in the minimum comparison unit area.
S302, setting a difference thresholdEach minimum comparison unit for sample imagesComparing with the chip image in the standard template, ifDetermining the minimum alignment unit as a defective unit:
In the invention, by reasonably setting the difference threshold value All minimum comparison units with defects can be screened, wherein the threshold value isCan be statistically derived from historical chip surface defects. In addition, the person skilled in the art can also set the difference threshold according to the actual situationThe size of (3) is not limited in the present invention.
The first screening module 204 is specifically configured to: carrying out probability statistics on defective units of the sample image to obtain a difference matrixAnd obtain the defect probability of each minimum comparison unitAccording to the normal distribution rule, the mean value is utilizedAnd standard deviationObtaining the confidence intervalAll minimum alignment units with defects in the set are defect area sets, wherein x is a selected confidence level;
In the invention, the S4 has the function of calculating the defect probability of each minimum comparison unit The method specifically comprises the following steps:
S401: carrying out probability statistics on defective units of the sample image to obtain a difference matrix ；
S402: defining probability of defectFor pixel coordinatesIs around (2)Average value of the minimum comparison unit difference degree in the region, wherein:
，
the probability of the outgoing line defect unit of each region can be obtained by counting the difference degree of the minimum comparison unit in each region, and each region can be obtained by integration Defect probability of (a)。
S403: the mean value is utilized in the S4And standard deviationObtaining the confidence intervalThe total minimum comparison units with defects in the defect area set specifically comprises the following steps:
，
By setting three typical confidence interval probabilities of 90%,95% and 99%, the set area of the defect area under the corresponding defect probability can be obtained after the required defect probability confidence interval is selected, and the set area of the defect area under the corresponding defect probability can be obtained by scanning the areas, so that the number of the defect areas detected can be reduced.
The second screening module 205 is specifically configured to: calculating the distance between the minimum alignment units in the defect area setSetting the radius value r and the circle center position asCalculating the minimum number of aligned units having defects in the set circular region:
in the present invention, the specific step of calculating the minimum number of aligned units with defects in the circular area in S5 includes:
s501: calculating the distance between the minimum alignment units in the defect area set ；
S502: setting the radius value r and the circle center position asCalculating the minimum number of aligned units having defects in the set circular region:
，
in the invention, the radius value r is 1/5 of the long side of the visual field of the chip surface defect image acquisition equipment. The radius value r is selected, so that the scanning times are reduced, the scanning times are matched with the common die size of the mobile phone chip by about 6mm, and the definition of the acquired image can be ensured.
The output module 206 is specifically configured to: setting a defect quantity threshold value a and adjusting the circle centerObtaining a circle center coordinate set A with the number of the minimum comparison units with defects not less than aBased on circle center coordinate set AAnd performing defect detection on the rest chips in the same batch.
In the invention, a circle center coordinate set A is determined in S6The specific steps of (a) include:
s601: setting a defect number threshold a so that;
s602: adjusting the center of a circle Obtaining a circle center coordinate set A with the number of the minimum comparison units with defects not less than a；
S603: the numerical value of the defect quantity threshold value a is adjusted to enable the circle center coordinate set AThe number of center of the circle in (a) is 5-20;
s604: based on circle center coordinate set A And performing defect detection on the rest chips in the same batch.
Example 3
In one embodiment, the present invention provides a computer device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the method of detecting a chip surface defect as in any one of embodiment 1 when the computer program is executed.
The computer device may include a processor and a memory storing computer program instructions.
In particular, the processor may comprise a Central Processing Unit (CPU), or an Application SPECIFIC INTEGRATED Circuit (ASIC), or may be configured as one or more integrated circuits that implement embodiments of the present invention.
The memory may include, among other things, mass storage for data or instructions. By way of example, and not limitation, the memory may comprise a hard disk drive (HARD DISK DRIVE, abbreviated HDD), a floppy disk drive, a solid state drive (SolidState Drive, abbreviated SSD), flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (Universal SerialBus, abbreviated USB) drive, or a combination of two or more of these. The memory may include removable or non-removable (or fixed) media, where appropriate. The memory may be internal or external to the data processing apparatus, where appropriate. In a particular embodiment, the memory is a Non-Volatile (Non-Volatile) memory. In particular embodiments, the Memory includes Read-Only Memory (ROM) and random access Memory (RandomAccess Memory RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (Programmable Read-Only Memory, abbreviated PROM), an erasable PROM (Erasable ProgrammableRead-Only Memory, abbreviated EPROM), an electrically erasable PROM (ELECTRICALLY ERASABLE PROGRAMMABLEREAD-Only Memory, abbreviated EEPROM), an electrically rewritable ROM (ELECTRICALLY ALTERABLE READ-Only Memory, abbreviated EAROM) or a FLASH Memory (FLASH), or a combination of two or more of these. The RAM may be a Static Random-Access Memory (SRAM) or a dynamic Random-Access Memory (Dynamic Random Access Memory DRAM), where the DRAM may be a fast page mode dynamic Random-Access Memory (Fast Page Mode Dynamic Random Access Memory, FPMDRAM), an extended data output dynamic Random-Access Memory (Extended Date Out Dynamic RandomAccess Memory, EDODRAM), a synchronous dynamic Random-Access Memory (Synchronous Dynamic Random-Access Memory, SDRAM), or the like, as appropriate.
The memory may be used to store or cache various data files that need to be processed and/or communicated, as well as possible computer program instructions for execution by the processor.
The processor reads and executes the computer program instructions stored in the memory to implement any of the chip surface defect detection methods of embodiment 1.
In some of these embodiments, the computer device may also include a communication interface and a bus. The processor, the memory and the communication interface are connected through a bus and complete communication with each other.
The communication interface is used to implement communication between modules, devices, units and/or units in the embodiments of the invention. The communication interface may also enable communication with other components such as: and the external equipment, the image/data acquisition equipment, the database, the external storage, the image/data processing workstation and the like are used for data communication.
The bus includes hardware, software, or both, coupling components of the computer device to each other. The bus includes, but is not limited to, at least one of: data Bus (Data Bus), address Bus (Address Bus), control Bus (Control Bus), expansion Bus (Expansion Bus), local Bus (Local Bus). By way of example, and not limitation, the buses may include a graphics acceleration interface (ACCELERATED GRAPHICS Port, abbreviated as AGP) or other graphics Bus, an enhanced industry standard architecture (Extended Industry Standard Architecture, abbreviated as EISA) Bus, a Front Side Bus (Front Side Bus, abbreviated as FSB), a HyperTransport (HT) interconnect, an industry standard architecture (Industry Standard Architecture, abbreviated as ISA) Bus, a wireless bandwidth (InfiniBand) interconnect, a Low Pin Count (LPC) Bus, a memory Bus, a micro channel architecture (Micro ChannelArchitecture, abbreviated as MCA) Bus, a peripheral component interconnect (PERIPHERAL COMPONENT INTERCONNECT, abbreviated as PCI) Bus, a PCI-Express (PCI-X) Bus, a serial advanced technology attachment (Serial AdvancedTechnology Attachment, abbreviated as SATA) Bus, a video electronics standards Association local (Video ElectronicsStandards Association Local Bus, abbreviated as VLB) Bus, or other suitable Bus, or a combination of two or more of these. The bus may include one or more buses, where appropriate. Although embodiments of the invention have been described and illustrated with respect to a particular bus, the invention contemplates any suitable bus or interconnect.
The steps and effects of the method for detecting a chip surface defect in the foregoing embodiment 1 can be implemented by a computer device provided by the present invention, and in order to avoid repetition, the disclosure is not repeated.
Compared with the prior art, the invention has at least the following beneficial technical effects:
According to the invention, the whole chip image can be acquired, then the chip image is segmented through a K-Means clustering algorithm, a plurality of welding spot areas in the chip image are segmented, and then defect detection is carried out on the welding spot areas, so that the plurality of welding spot areas in the whole chip can be detected simultaneously, photographing one by one is not needed, the time is saved, the surface defect detection of a large-scale chip production line can be realized, the surface defect detection efficiency of the large-scale chip production line is improved, the defect detection result is given in real time, and the production efficiency is improved.
Example 4
The present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method for detecting a chip surface defect according to any one of embodiment 1.
The steps and effects of the method for detecting a chip surface defect in the foregoing embodiment 1 can be implemented by a computer readable storage medium provided by the present invention, and in order to avoid repetition, the disclosure is not repeated.
Compared with the prior art, the invention has at least the following beneficial technical effects: according to the invention, the whole chip image can be acquired, then the chip image is segmented through a K-Means clustering algorithm, a plurality of welding spot areas in the chip image are segmented, and then defect detection is carried out on the welding spot areas, so that the plurality of welding spot areas in the whole chip can be detected simultaneously, photographing one by one is not needed, the time is saved, the surface defect detection of a large-scale chip production line can be realized, the surface defect detection efficiency of the large-scale chip production line is improved, the defect detection result is given in real time, and the production efficiency is improved.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the invention, which are described in detail and are not to be construed as limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (8)
1. The method for detecting the surface defects of the chip is characterized by comprising the following steps of:
s1: obtaining a standard template and a sample data set, wherein the sample data set comprises a plurality of chip images of the same batch;
s2: representing sample images in a sample dataset as WhereinThe serial number of the sample image is represented, and the chip image in the standard template is represented as，Representing pixel coordinates, and dividing each sample image to obtain a minimum comparison unit；
S3: setting a difference thresholdEach minimum comparison unit for sample imagesComparing with the chip image in the standard template, and when the minimum comparison unit is used forThe difference degree of the minimum unit corresponding to the standard template is larger than the difference degree threshold valueWhen the minimum comparison unit is marked as a defect unit;
s4: carrying out probability statistics on defective units of the sample image to obtain a difference matrix And obtain the defect probability of each minimum comparison unitAccording to the normal distribution rule, the mean value is utilizedAnd standard deviationObtaining the confidence intervalAll minimum alignment units with defects in the set are defect area sets, wherein x is a selected confidence level;
S5: setting the radius value r and the circle center position as Calculating the minimum comparison unit number of defects in the set circular area;
s6: setting a defect quantity threshold value a and adjusting the circle center Obtaining a circle center coordinate set A with the number of the minimum comparison units with defects not less than aBased on circle center coordinate set APerforming defect detection on the rest chips in the same batch;
wherein the S4 calculates the defect probability of each minimum comparison unit Comprising the following steps:
S401: carrying out probability statistics on defective units of the sample image to obtain a difference matrix ；
S402: defining probability of defectFor pixel coordinatesSurrounding is provided withAverage value of the minimum comparison unit difference degree in the region, wherein:
，
and, the mean value is used in the S4 And standard deviationObtaining the confidence intervalThe total minimum comparison units with defects in the defect area set is as follows:
。
2. the method for detecting surface defects of a chip according to claim 1, wherein the step S3 comprises:
S301: definition of degree of difference For each pixel pointSum of squares of luminance differences at:
; wherein k and l represent the number of pixels of the minimum alignment unit in the sample image in the x direction and the y direction;
s302: setting a difference threshold Each minimum comparison unit for sample imagesComparing with the chip image in the standard template, ifThen the cell is determined to be a defective cell.
3. The method for detecting surface defects of chips as defined in claim 1, wherein said step of calculating the minimum number of alignment units having defects in the circular area in S5 comprises:
Setting the radius value r and the circle center position as Calculating the minimum number of aligned units having defects in the set circular region，To set the radius value r and the circle center position asLeast alignment unit in circular area of (a)Is the total of (a):
。
4. The method for detecting surface defects of chips as defined in claim 3, wherein said radius r is 1/5 of the long side of the field of view of the image capturing device for surface defects of chips.
5. The method for detecting surface defects of a chip according to claim 1, wherein the step S6 comprises:
s601: setting a defect number threshold a;
s602: adjusting the center of a circle Obtaining a circle center coordinate set A with the number of the minimum comparison units with defects not less than a；
S603: the numerical value of the defect quantity threshold value a is adjusted to enable the circle center coordinate set AThe number of circle centers in the center is 5-20;
s604: based on circle center coordinate set A And performing defect detection on the rest chips in the same batch.
6. A chip surface defect detection apparatus, wherein the detection apparatus implements the chip surface defect detection method according to any one of claims 1 to 5, comprising:
The acquisition module is used for acquiring a standard template and a sample data set, wherein the sample data set comprises a plurality of chip images of the same batch;
The segmentation module is used for carrying out segmentation processing on the sample images in the sample data set to obtain a minimum comparison unit;
The marking module is used for marking the minimum comparison unit as a defect unit when the difference degree of the minimum comparison unit corresponding to the standard template is larger than a difference degree threshold;
The first screening module is used for carrying out probability statistics on defect units of the sample image, obtaining the defect probability of each minimum comparison unit, and obtaining that all the minimum comparison units with defects in a confidence interval are defect area sets by means of the mean value and the standard deviation;
The second screening module is used for setting a radius value and a circular area with a circle center position and calculating the number of minimum comparison units with defects in the set circular area;
And an output module: setting a defect number threshold value, adjusting the position of a circle center, obtaining a circle center coordinate set with the number of the minimum comparison units with defects not smaller than the defect number threshold value, and detecting the defects of the rest chips in the same batch based on the circle center coordinate set.
7. A computer device, comprising: memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method for detecting a chip surface defect according to any one of claims 1 to 5 when executing the computer program.
8. A computer-readable storage medium, on which a computer program is stored, characterized in that the program, when executed by a processor, implements the method for detecting a chip surface defect according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410763844.5A CN118351111B (en) | 2024-06-14 | 2024-06-14 | Method, device, equipment and storage medium for detecting chip surface defects |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410763844.5A CN118351111B (en) | 2024-06-14 | 2024-06-14 | Method, device, equipment and storage medium for detecting chip surface defects |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118351111A CN118351111A (en) | 2024-07-16 |
| CN118351111B true CN118351111B (en) | 2024-10-01 |
Family
ID=91814259
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410763844.5A Active CN118351111B (en) | 2024-06-14 | 2024-06-14 | Method, device, equipment and storage medium for detecting chip surface defects |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118351111B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103646893A (en) * | 2013-11-29 | 2014-03-19 | 上海华力微电子有限公司 | A wafer defect detecting method |
| CN113298793A (en) * | 2021-06-03 | 2021-08-24 | 中国电子科技集团公司第十四研究所 | Circuit board surface defect detection method based on multi-view template matching |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104022050A (en) * | 2014-04-22 | 2014-09-03 | 上海华力微电子有限公司 | Detection method for repeated position defects in batch of wafers |
| CN114879005A (en) * | 2022-01-25 | 2022-08-09 | 龚小玲 | LSTM-based hardware drive circuit board batch detection system and detection method thereof |
| PL4322106T3 (en) * | 2022-06-30 | 2025-05-19 | Contemporary Amperex Technology (Hong Kong) Limited | METHOD AND APPARATUS FOR DETECTION OF DEFECTS |
| CN115830004A (en) * | 2022-12-27 | 2023-03-21 | 凌云光技术股份有限公司 | Surface defect detection method, device, computer equipment and storage medium |
-
2024
- 2024-06-14 CN CN202410763844.5A patent/CN118351111B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103646893A (en) * | 2013-11-29 | 2014-03-19 | 上海华力微电子有限公司 | A wafer defect detecting method |
| CN113298793A (en) * | 2021-06-03 | 2021-08-24 | 中国电子科技集团公司第十四研究所 | Circuit board surface defect detection method based on multi-view template matching |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118351111A (en) | 2024-07-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110060237B (en) | Fault detection method, device, equipment and system | |
| CN110544231B (en) | Surface defect detection method of lithium battery electrode based on background normalization and centralized compensation algorithm | |
| CN114581446B (en) | Battery core abnormity detection method and system of laminated battery | |
| CN114627089B (en) | Defect identification method, defect identification device, computer equipment and computer readable storage medium | |
| CN115761270A (en) | Color card detection method and device, electronic equipment and storage medium | |
| CN116168351A (en) | Inspection method and device for power equipment | |
| CN118822940A (en) | Defect detection methods, devices, media, products and equipment | |
| CN117011216A (en) | Defect detection method and device, electronic equipment and storage medium | |
| CN119831992A (en) | Self-iterative membrane electrode assembly defect detection method, device and equipment | |
| CN118898600B (en) | Full-automatic analyzer sample state evaluation method based on AI visual detection | |
| CN118671078B (en) | New energy battery packing detection method, device, electronic equipment and storage medium | |
| CN118351111B (en) | Method, device, equipment and storage medium for detecting chip surface defects | |
| CN119152388A (en) | Automatic law enforcement monitoring method, equipment and storage medium based on remote sensing image | |
| CN113392455A (en) | House type graph scale detection method and device based on deep learning and electronic equipment | |
| CN114549393A (en) | Image annotation method, device, equipment and computer storage medium | |
| CN116993654B (en) | Camera module defect detection method, device, equipment, storage medium and product | |
| CN116188502B (en) | Method for dividing infrared image of photovoltaic panel, storage medium and electronic device | |
| CN117830255A (en) | Defect detection method, defect detection device, and storage medium | |
| CN111950493A (en) | Image recognition method, device, terminal device and readable storage medium | |
| CN119359538B (en) | Image stitching method, computer readable storage medium and computer program product | |
| CN119477917B (en) | Defect type determining method and device, electronic equipment and storage medium | |
| CN118941568B (en) | Round hole burr defect detection method, system and storage medium based on deep learning | |
| CN117690846B (en) | Visual detection method, device and equipment for solar silicon wafer and storage medium | |
| CN119494839B (en) | A battery pole piece detection method and system based on image recognition | |
| CN114187294B (en) | Regular wafer positioning method based on prior information |
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 |