CN115619761A - Method, system, equipment and storage medium for detecting gap coverage abnormity - Google Patents
Method, system, equipment and storage medium for detecting gap coverage abnormity Download PDFInfo
- Publication number
- CN115619761A CN115619761A CN202211370150.2A CN202211370150A CN115619761A CN 115619761 A CN115619761 A CN 115619761A CN 202211370150 A CN202211370150 A CN 202211370150A CN 115619761 A CN115619761 A CN 115619761A
- Authority
- CN
- China
- Prior art keywords
- picture
- notch
- wafer
- region
- pixel value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000003860 storage Methods 0.000 title claims abstract description 11
- 230000002159 abnormal effect Effects 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims description 29
- 238000001514 detection method Methods 0.000 claims description 26
- 238000004422 calculation algorithm Methods 0.000 claims description 17
- 238000007781 pre-processing Methods 0.000 claims description 17
- 230000005856 abnormality Effects 0.000 claims description 14
- 238000003708 edge detection Methods 0.000 claims description 10
- 238000012216 screening Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 235000012431 wafers Nutrition 0.000 description 126
- 238000010586 diagram Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 6
- 230000008859 change Effects 0.000 description 4
- 238000001914 filtration Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000011109 contamination Methods 0.000 description 2
- 239000013078 crystal Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000000717 retained effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000013024 troubleshooting Methods 0.000 description 2
- 239000011248 coating agent Substances 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000005034 decoration Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000003475 lamination Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013618 particulate matter Substances 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
-
- 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)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the disclosure discloses a method, a system, a device and a storage medium for detecting abnormal notch coverage, wherein the method comprises the following steps: determining the position of a notch in the picture of the wafer circumscribed circle, and constructing an interested area which is proportional to the area of the notch label and can cover the notch; judging whether the average pixel value of the region of interest is within a preset pixel value set or not; when the average pixel value of the region of interest is within a preset pixel value set, determining that the notch label covers a wafer notch; otherwise, moving the interested region in the wafer circumcircle picture until the average pixel value of the interested region is in a preset pixel value set and the distance between the center of the interested region and the center of the notch is in a preset range, and determining that the notch label covers the notch of the wafer. By utilizing the exemplary embodiment of the disclosure, whether the notch is in the reasonable range of the notch label can be detected in advance, and the problem of continuous yield loss caused by mismatching of the notch and the notch label is solved.
Description
Technical Field
The embodiment of the disclosure relates to the technical field of semiconductors, in particular to a method, a system, equipment and a storage medium for detecting notch coverage abnormity.
Background
The Notch (Notch) is a groove cut at the inner position of the edge of the Wafer (Wafer), the Notch can help the subsequent process to determine the placing position of the Wafer, the crystal orientation of the single crystal growth is marked, and the subsequent cutting and testing are convenient; notch labels (Notch tabs) are very important tools in DRAM manufacturing processes, and are commonly used to cover the notches in the wafer to avoid particle contamination during the lamination process.
In the semiconductor processing process, the gap label cannot cover the gap, particle pollution is generated at the gap, and then yield loss is caused, and how to detect the abnormal gap covering to avoid the yield loss and reduce the time loss of troubleshooting accidents is an urgent problem to be solved by the invention.
Disclosure of Invention
Embodiments of the present disclosure provide a method, system, device and storage medium for detecting a gap coverage anomaly, so as to solve or alleviate one or more of the above technical problems in the prior art.
According to an aspect of the present disclosure, there is provided a method for detecting an anomaly in notch coverage, including:
determining the position of a gap in the picture of the wafer circumscribed circle, and constructing an interested area which is proportional to the area of a gap label and can cover the gap;
judging whether the average pixel value of the region of interest is within a preset pixel value set or not;
when the average pixel value of the region of interest is within a preset pixel value set, determining that the notch label covers the notch of the wafer;
otherwise, moving the interested region in the wafer circumcircle picture until the average pixel value of the interested region is in a preset pixel value set and the distance between the center of the interested region and the center of the notch is in a preset range, and determining that the notch label covers the notch of the wafer.
In a possible implementation manner, the determining a position of a gap in a wafer circumscribed circle picture, and before constructing an area of interest that is proportional to an area of a gap label and can cover the gap, includes:
acquiring an original picture;
preprocessing the original picture to form a preprocessed picture;
and determining whether a gap label exists in the preprocessed picture.
In one possible implementation, the preprocessing the original picture includes:
processing the original picture in a gray scale mode to form a gray scale picture;
and binarizing the gray-scale picture, and denoising the binarized gray-scale picture to obtain a preprocessed picture.
In a possible implementation manner, the determining whether a gap label exists in the preprocessed picture includes:
detecting the number of angular points in the preprocessed picture by adopting an edge detection algorithm;
judging whether the number of angular points existing in the preprocessed picture is larger than a preset number of angular points or not;
determining the preprocessed pictures with the angular points more than or equal to the preset angular points as notched labels;
and screening out the preprocessed pictures of which the angular points are less than the preset angular points.
In a possible implementation manner, the preprocessing the original picture to form a preprocessed picture, further includes:
and extracting a pixel value set of the notch label from the gray picture as a preset pixel value set.
In a possible implementation manner, the determining a position of a notch in the wafer circumscribed circle picture includes:
carrying out gray processing on the original picture to form a gray picture;
acquiring the outline of the wafer in the gray level picture by utilizing an outline detection algorithm, and drawing an outer circle of the outline of the wafer to form a wafer outer circle picture;
calculating the circle center and the diameter of the circumscribed circle in the picture of the circumscribed circle of the wafer;
calculating to obtain an image scale according to the diameter of the circumscribed circle and the actual diameter of the wafer;
calculating the picture radius of the wafer in the wafer circumcircle picture according to the image scale;
and moving the wafer in the direction of the fixed position of the notch by a distance equal to the radius of the wafer picture by taking the circle center of the circumscribed circle as a starting point, and determining the position of the notch in the wafer circumscribed circle picture.
In a possible implementation manner, the center of the region of interest is the position of the notch, and the length and width of the region of interest are equal to a value obtained by subtracting a preset value from the length and width of an actual notch label and then reducing the size according to an image scale.
In a possible implementation manner, the average pixel value of the region of interest includes a vertex pixel value of the region of interest and values of all pixel points in the region of interest.
In a possible implementation manner, moving the region of interest within the wafer circumscribed picture until an average pixel value of the region of interest is within a preset set of pixel values and a distance between a center of the region of interest and a center of the notch is within a preset range, and determining that the notch label covers the notch of the wafer includes:
when the distance between the center of the region of interest and the center of the gap is not within a preset range, sending first alarm information;
and sending second alarm information when the average pixel value of the region of interest is not found in the preset pixel value set after the region of interest traverses the wafer circumcircle picture.
In one possible implementation, the moving the region of interest within the wafer-circumscribed picture includes:
dividing the wafer circumscribed circle picture into a plurality of sub-regions;
calculating an average pixel value for each of the sub-regions;
selecting a sub-region with the highest average pixel value from a plurality of sub-regions;
moving the region of interest within the sub-region where the average pixel value is highest.
According to an aspect of the present disclosure, there is provided a system for detecting a gap coverage abnormality, including:
the first determining module is used for determining the position of a notch in the picture of the wafer circumscribed circle;
the construction module is used for constructing an interested area which is proportional to the area of the gap label and can cover the gap;
the judging module is used for judging whether the average pixel value of the interested area is within a preset pixel value set or not;
the second determining module is used for determining that the notch label covers the notch of the wafer when the average pixel value of the region of interest is within a preset pixel value set;
the moving module is used for moving the region of interest in the wafer circumcircle when the average pixel value of the region of interest is not within a preset pixel value set;
and the third determining module is used for determining that the notch label covers the notch of the wafer when the region of interest is moved in the wafer circumscribed circle picture until the average pixel value of the region of interest is within a preset pixel value set and the distance between the center of the region of interest and the center of the notch is within a preset range.
In one possible implementation, the method includes:
the acquisition module is used for acquiring an original picture;
the preprocessing module is used for preprocessing the original picture to form a preprocessed picture;
and the fourth determining module is used for determining whether the notch label exists in the preprocessed picture.
In one possible implementation, the preprocessing module includes:
the gray processing unit is used for processing the original picture in a gray mode to form a gray picture;
and the binarization processing unit is used for binarizing the gray level picture, and denoising the binarized gray level picture to obtain a preprocessed picture.
In one possible implementation manner, the fourth determining module includes:
the detection unit is used for detecting the number of angular points in the preprocessed picture by adopting an edge detection algorithm;
the judging unit is used for judging whether the number of the angular points in the preprocessed picture is larger than the number of the preset angular points or not;
a gap label determining unit, configured to determine that the preprocessed picture with the number of the corner points being greater than or equal to the preset number of the corner points is a gap label;
and the screening unit is used for screening the preprocessed pictures of which the angular points are less than the preset angular points.
In one possible implementation manner, the fourth determining module includes:
and the extraction unit is used for extracting the pixel value set of the notch label from the gray picture as a preset pixel value set.
In one possible implementation manner, the first determining module includes:
the gray processing unit is used for carrying out gray processing on the original picture to form a gray picture;
the forming unit is used for acquiring the outline of the wafer in the gray level picture by utilizing an outline detection algorithm, drawing an circumscribed circle of the outline of the wafer and forming a wafer circumscribed circle picture;
the first calculation unit is used for calculating the circle center and the diameter of the circumscribed circle in the wafer circumscribed circle picture;
the second calculation unit is used for calculating to obtain an image scale according to the diameter of the circumscribed circle and the actual diameter of the wafer;
the third calculating unit is used for calculating the picture radius of the wafer in the wafer circumcircle picture according to the image scale;
and the gap position determining unit is used for moving the wafer gap in the fixed position direction by a distance equal to the radius of the wafer picture by taking the circle center of the circumscribed circle as a starting point, and determining the wafer gap as the gap position in the wafer circumscribed circle picture.
In a possible implementation manner, the center of the region of interest is the position of the notch, and the length and width of the region of interest are equal to a value obtained by subtracting a preset value from the length and width of an actual notch label and then reducing the size according to an image scale.
In a possible implementation manner, the average pixel value of the region of interest includes a vertex pixel value of the region of interest and values of all pixel points in the region of interest.
In one possible implementation, the method includes:
the first warning module is used for sending first warning information when the distance between the center of the region of interest and the center of the gap is not within a preset range;
and the second alarm module is used for sending out second alarm information when the average pixel value of the region of interest is not found in the preset pixel value set when the region of interest traverses the wafer circumscribed circle picture.
In one possible implementation, the moving module includes:
the dividing unit is used for dividing the wafer circumcircle picture into a plurality of sub-areas;
a fourth calculation unit for calculating an average pixel value of each of the sub-regions;
the selecting unit is used for selecting a subarea with the highest average pixel value from a plurality of subareas;
a moving unit for moving the region of interest within the sub-region where the average pixel value is highest.
According to an aspect of the present disclosure, there is provided a detection apparatus of a gap coverage abnormality, including:
a processor and a memory;
the memory is used for storing a computer program, and the processor calls the computer program stored in the memory to execute any one of the above methods for detecting the gap coverage abnormality.
According to an aspect of the present disclosure, there is provided a computer-readable storage medium having a computer program stored therein, which when executed by a processor, enables the processor to execute any one of the above-mentioned methods for detecting a gap coverage anomaly.
Exemplary embodiments of the present disclosure have the following advantageous effects: by utilizing the exemplary embodiment of the disclosure, the picture shot after the wafer is placed inside the machine table is extracted, the relative positions of the Notch (Notch) and the Notch label (Notch Tab) are determined by utilizing contour detection and color tracking, whether the Notch is in the coverage range of the Notch label or not can be detected in advance, the problem of continuous yield loss caused by impurities due to mismatch of the Notch and the Notch label is solved, and the time consumption for troubleshooting reasons after accidents is saved.
The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below. Other features and advantages of the application will be apparent from the description and drawings, and from the claims. It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure. It should be apparent that the drawings in the following description are merely examples of the disclosure and that other drawings may be derived by those of ordinary skill in the art without inventive effort.
Fig. 1 is one of flowcharts of a detection method of a gap coverage abnormality of the present exemplary embodiment;
FIG. 2 is a second flowchart of a method for detecting a gap coverage anomaly according to the present exemplary embodiment;
fig. 3 is a schematic view of a wafer with a notch label of the present exemplary embodiment;
FIG. 4 is a partial enlarged view at A in FIG. 3 of the present exemplary embodiment;
FIG. 5 is a schematic diagram of an original image of the notch label of the present exemplary embodiment normally covering the notch;
FIG. 6 is a schematic diagram of an original image of the notch label not normally covering the notch of the present exemplary embodiment;
fig. 7 is a schematic diagram of a grayscale picture of the present exemplary embodiment;
FIG. 8 is a schematic diagram of a wafer outline picture in accordance with the exemplary embodiment;
fig. 9 is a block diagram of a detection system of a gap coverage abnormality of the present exemplary embodiment.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the subject matter of the present disclosure can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and the like. In other instances, well-known technical solutions have not been shown or described in detail to avoid obscuring aspects of the present disclosure.
Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repetitive description will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in the form of software, or in one or more hardware units or integrated circuits, or in different networks and/or processor means and/or microcontroller means.
The flow charts shown in the drawings are merely illustrative and do not necessarily include all of the steps. For example, some steps may be decomposed, and some steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
The terms "first," "second," and the like in the description and in the claims of the present application and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged under appropriate circumstances such that the embodiments of the application described herein may be implemented, for example, in sequences other than those illustrated or described herein.
Furthermore, the terms "comprise," "include," and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or sub-modules is not necessarily limited to those steps or sub-modules expressly listed, but may include other steps or sub-modules not expressly listed or inherent to such process, method, article, or apparatus.
Fig. 1 is one of flowcharts of a method for detecting a gap coverage abnormality according to the present exemplary embodiment, and as shown in fig. 1, an exemplary embodiment of the present disclosure provides a method for detecting a gap coverage abnormality, including:
s100, determining the position of a notch in the picture of the wafer circumscribed circle, and constructing an interested area which is proportional to the area of a notch label and can cover the notch;
in the present exemplary embodiment, the Notch position is a central position of the Notch (Notch), for example, a center of a circumscribed circle of the Notch and/or a center of an inscribed circle of the Notch;
illustratively, when the orthographic projection shape of the Notch is an equilateral triangle, the center of the circumscribed circle of the Notch coincides with the center of the inscribed circle, so that the region of interest is constructed with the coincident center as the center;
exemplarily, when the orthographic projection shape of the Notch is a triangle other than the equilateral triangle row, the region of interest is constructed by taking the center of the circumscribed circle of the Notch or the center of the inscribed circle of the Notch as the center;
illustratively, when the orthographic projection shape of the Notch is a square, the center of the circumscribed circle of the Notch coincides with the center of the inscribed circle, so that the region of interest is constructed with the coincident center as the center;
illustratively, when the orthographic projection shape of the Notch is a rectangle, the region of interest is constructed by taking the center of a circle circumscribing the Notch as the center;
it should be noted that, in general, the orthographic shape of the Notch is an equilateral triangle.
In the present exemplary embodiment, with respect to the region of interest: the shape of the region of interest is consistent with that of the Notch Tab, and the area of the region of interest is slightly smaller than that of the Notch Tab, so that the accuracy of subsequent judgment (judgment on whether the average pixel value of the region of interest is in the preset pixel value set) is ensured; for example, when the area of the constructed region of interest is smaller than the Notch Tab, if the average pixel value of the region of interest is within the preset pixel value set, it can be indicated that the Notch Tab must normally cover the Notch, and the result of the determination is accurate, whereas, if the area of the constructed region of interest is larger than the Notch Tab, there is a possibility that the Notch Tab does not normally cover the Notch and the average pixel value of the region of interest is within the preset pixel value set, and the result of the determination is inaccurate.
Illustratively, when the Notch Tab is triangular in shape, then a set value R (0.1 mm. Ltoreq. R. Ltoreq.2 mm) is subtracted from each of the three side lengths of the Notch Tab, or a new side length is formed by multiplying each of the three side lengths of the Notch by a set value R '(R' < 1), so as to construct the region of interest; for example, if three side lengths of Notch Tab are X, Y, Z, respectively, then the region of interest is constructed with Notch as the center and (X-R), (Y-R), (Z-R) as the new side length, for example, when R =1mm, then the region of interest is constructed with (X-1), (Y-1), (Z-1) as the new side length, or with Notch as the center, then the region of interest is constructed with (X R '), (Y R '), (Z R ') as the new side length; for example, when R' =0.9, then the region of interest is constructed with (X0.9), (Y0.9), (Z0.9) new edge lengths. In the above, the unit of the set value R coincides with the unit of the side length of the Notch Tab, and in the present exemplary embodiment, the unit of the set value R is millimeters.
Illustratively, when the Notch Tab is rectangular in shape, then N will beThe length and width of otch are both subtracted by a set value R (R) 1 ≤R≤R 2 ) Or multiplying the length and the width of the Notch by a set value R '(R' < 1) to form a new side length so as to construct the region of interest; for example, if three side lengths of Notch Tab are a and b, respectively, then construct the region of interest with Notch as the center and (a-R) and (b-R) as the new side lengths, for example, if R =1, then construct the region of interest with (a-1) and (b-1) as the new side lengths, or if Notch as the center and construct the region of interest with (a × R '), (b × R ') as the new side lengths, for example, if R ' =0.9, then construct the region of interest with (a × 0.9) and (Y × 0.9) as the new side lengths; in the above, the unit of the set value R coincides with the unit of the length and width of the Notch Tab, and in the present exemplary embodiment, the unit of the set value R is millimeters. It is worth mentioning that the region of interest constructed with the new side length as described above needs to cover the Notch, which requires that the settings R and R' cannot be too small.
In the present exemplary embodiment, regarding the notch label: fig. 3 is a schematic diagram of a wafer with a notch label of the present example embodiment; FIG. 4 is a partial enlarged view at A in FIG. 3 of the present exemplary embodiment; as shown in fig. 3 and 4, a Notch label (Notch Tab) is a very important tool in the DRAM manufacturing process, and is usually used to cover the Notch on the wafer to avoid particle contamination in the coating production process.
As described above, notch Tab is generally rectangular in shape.
S200, judging whether the average pixel value of the region of interest is within a preset pixel value set or not;
in the present exemplary embodiment, it is determined whether the notch label normally covers the notch by determining whether the average pixel value of the region of interest is within the preset pixel value set, where the average pixel value of the region of interest exemplarily includes four vertices of the region of interest and the average pixel value in the region of interest;
it should be noted that, in the present exemplary embodiment, the preset pixel value set is set according to the pixel value set of the notch label.
S300, when the average pixel value of the region of interest is within a preset pixel value set, determining that the notch label covers the notch of the wafer; in this embodiment, when the average pixel value of the region of interest is within the preset pixel value set, it is indicated that the notch label normally covers the notch, and thus it is determined that the notch label covers the wafer notch, and in addition, the wafer circumscribed-circle picture of the average pixel value of the region of interest within the preset pixel value set may be filtered.
S400, if not, moving the interested region in the wafer circumcircle picture until the average pixel value of the interested region is in a preset pixel value set and the distance between the center of the interested region and the center of the notch is in a preset range, and determining that the notch label covers the notch of the wafer. In this embodiment, when the average pixel value of the region of interest is not within the preset pixel value set, two situations are included, one is that the position of the notch label relative to the notch is slightly shifted, but the notch label normally covers the notch, and the other is that the notch label does not normally cover the notch, for these two situations, further measures are taken to distinguish, exemplarily, an equation of a circle with conditional restrictions is constructed so that the circle is overlapped with the object to be detected, the position of the region of interest is continuously moved from one end point of the wafer circumscribed circle picture, an area where the average pixel values of the region of interest are all within the preset pixel value set is found, when the region of interest is moved within the wafer circumscribed circle picture until the average pixel value of the region of interest is within the preset pixel value set and the distance between the center of the region of interest and the center of the notch is within a preset range, it is stated that the position of the notch label conforms to the first situation, i.e., the position of the notch label is slightly shifted relative to the notch label, but the notch label still normally covers the notch, at this time, the wafer is determined, and the wafer is filtered, and the first class of the wafer circumscribed circle picture can be referred to the second class of the wafer statistical data. When the interested region is moved in the wafer circumscribed circle picture until the average pixel value of the interested region is within the preset pixel value set and the distance between the center of the interested region and the center of the notch is not within the preset range, the position of the notch label accords with the second condition, namely the notch label does not normally cover the notch, at the moment, abnormal alarm is carried out, and the wafer circumscribed circle pictures which accord with the second condition can be classified into one type, for example, the wafer circumscribed circle pictures which accord with the second condition are classified into abnormal pictures for two-stage detection, so that data processing work such as data statistics at the later stage is facilitated.
Before the region of interest is constructed, the method comprises the following steps:
s10, acquiring an original picture;
in the exemplary embodiment, a camera of the machine station shoots a chamber of the machine station in real time, uploads a picture to a machine station storage system through a network, and reads the shot picture by using a timing task program, so as to obtain an original picture of the installed machine station. FIG. 5 is a schematic diagram of an original image of a notch label of the present exemplary embodiment normally covering a notch; FIG. 6 is a schematic diagram of an original image of the gap label not normally covering the gap in the present exemplary embodiment; there are many situations in the original picture in this exemplary embodiment, for example, one of them is a situation that the gap label normally covers the gap as shown in fig. 5, the gap and the gap label are both located at the bottom of the picture; secondly, as shown in fig. 6, when the Notch label does not normally cover the Notch, in fig. 6, the Notch Tab indicates the Notch label and is located at the top of the wafer, and the Notch indicates the Notch and is located at the bottom of the wafer; third, there is no gap label in the original picture (not shown).
S20, preprocessing the original picture to form a preprocessed picture;
s21, processing the original picture in a gray scale mode to form a gray scale picture; the formed grayscale picture is as shown in fig. 7, and fig. 7 is a schematic view of the grayscale picture of the present exemplary embodiment.
S22, binarizing the gray level picture, and denoising the binarized gray level picture to obtain a preprocessed picture. It is to be noted that the binarization processing is an image processing method, and the binarization can convert a grayscale image into a binary image: the pixel gray scale larger than a certain critical gray scale value is set as a gray scale maximum value, and the pixel gray scale smaller than the value is set as a gray scale minimum value, so that binarization is realized.
S30, determining whether a gap label exists in the preprocessed picture;
s31, detecting the number of angular points in the preprocessed picture by adopting an edge detection algorithm; exemplarily, detecting the number of corner points existing in the binarized picture by using a canny edge detection algorithm;
s32, judging whether the number of the angular points in the preprocessed picture is larger than a preset number of angular points or not; in this exemplary embodiment, the preset corner number is set according to the shape of the Notch Tab, for example, the number of protruding vertices existing in the binarized picture sample with the Notch Tab is taken as the preset corner number in this embodiment, and exemplarily, the preset corner number is set to 4, it should be noted that the value of the preset corner number in this embodiment is only one example, and the value of the preset corner number is not limited, and other values capable of determining whether the Notch Tab exists in the binarized picture should belong to the protection scope of the present invention.
S33, determining the preprocessed pictures with the angular point number more than or equal to the preset angular point number as notched labels; in the exemplary embodiment, the binarized picture with the number of the angular points larger than the preset number of the angular points is retained; in this exemplary embodiment, when the number of corner points existing in the binarized picture is greater than the preset number of corner points, for example, when the number of detected corner points is 8 and the preset number of corner points is set to 7, it is indicated that Notch Tab exists in the binarized picture, and when Notch Tab exists in the binarized picture, it is meaningful to detect whether subsequent Notch Tab normally covers Notch, so that the binarized picture with the number of corner points greater than the preset number of corner points is retained.
S34, screening out the preprocessed pictures of which the number of the corner points is less than the preset number of the corner points. In this exemplary embodiment, the binarized picture with the number of corners smaller than the preset number of corners is filtered. In this embodiment, when the number of the corner points existing in the binarized picture is not greater than the preset number of corner points, for example, when the number of the detected corner points is 6 and the preset number of corner points is set to 7, it is indicated that no Notch Tab exists in the binarized picture, and when no Notch Tab exists in the binarized picture, it is not significant whether the subsequent Notch Tab normally covers the Notch or not, and therefore, the binarized picture with the corner points greater than the preset number of corner points is filtered.
In this embodiment, noise reduction processing is performed on the binarized picture first, because detection by using a canny edge detection algorithm is essentially to obtain all edges in an image by calculating image gradients, and noise is a place with large gray scale change and is easily identified as a false edge, the gaussian filtering noise reduction processing is performed on the binarized picture before detection by using the canny edge detection algorithm; and then, calculating the gradient of the binary image to obtain a possible edge set, and performing non-maximum suppression processing on the possible edge set, wherein the places with the gray changes are concentrated, and the places with the gray changes in the gradient direction in a local range are reserved with the gray changes being the maximum, and the other places are not reserved, so that most points can be eliminated. Changing an edge with a plurality of pixel widths into an edge with a single pixel width, finally, carrying out double-threshold screening processing, after non-maximum value inhibition, still having a plurality of possible edge points, and further setting a double threshold, namely a low threshold (low) and a high threshold (high). And if the gray change is larger than high, setting the gray change as a strong edge pixel, and if the gray change is lower than low, rejecting the strong edge pixel. The setting between low and high is a weak edge. And further judging, if the field has strong edge pixels, reserving the strong edge pixels, and if the field does not have strong edge pixels, removing the strong edge pixels to obtain the edge shape of the picture, and obtaining the angular point number existing in the binary picture according to the edge shape of the picture.
S23, extracting the pixel value set of the notch label from the gray picture as a preset pixel value set. Illustratively, the pixel value set of Notch Tab is artificially extracted as the preset pixel value set for the grayed picture.
S201, acquiring the outline of the wafer in the gray level picture by using an outline detection algorithm, and drawing an outer circle of the outline of the wafer to form a wafer outer circle picture; it should be noted that, when a picture is taken, the situation that the wafer is deformed into an ellipse due to the deviation of the shooting angle and the outline obtained by the outline detection algorithm is not clear exists, and the outline is completed by the circumscribed circle. In this embodiment, the picture of the circle circumscribing the wafer is shown in fig. 8, and fig. 8 is a schematic diagram of the picture of the circle circumscribing the wafer according to the exemplary embodiment. The contour detection refers to a process of extracting the contour of an object by adopting a certain technology and a certain method by neglecting the influence of textures and noise interference in the background and the object in a digital image containing the object and the background.
S202, calculating the circle center and the diameter of the circumscribed circle in the wafer circumscribed circle picture;
s203, calculating according to the diameter of the circumscribed circle and the actual diameter of the wafer to obtain an image scale;
s204, calculating the picture radius of the wafer in the wafer circumcircle picture according to the image scale;
s205, moving the wafer in the direction of the fixed position of the notch by a distance equal to the radius of the wafer picture by taking the center of the circumscribed circle as a starting point, and determining the position of the notch in the wafer circumscribed circle picture. Illustratively, the movement is vertically downward starting from the center of the circumscribed circle. It is worth to be noted that, when wafers are placed, the wafers are placed in the bearing plate according to the notches, the notches of the wafers are fixed at the same position when the wafers are placed every time, and when the wafers are placed, the notches are aligned with the bearing table and then covered by the notch labels.
The center of the region of interest is the position of the notch, and the length and width of the region of interest are equal to the value obtained by subtracting a preset value from the length and width of the actual notch label and then reducing the size according to the image proportion.
The average pixel value of the region of interest comprises a vertex pixel value of the region of interest and values of all pixel points in the region of interest.
Moving the region of interest within the wafer-out wafer illustratively includes the steps of:
s4001, dividing the wafer circumscribed circle picture into a plurality of sub-regions;
s4002, calculating an average pixel value of each sub-area;
s4003 selecting a subarea with the highest average pixel value from the subareas;
s4004 moving the region of interest within the sub-region where the average pixel value is highest.
Since the Notch Tab is white after the original picture is grayed, the average pixel value of the region where the Notch Tab is located is raised, in the exemplary embodiment, the wafer circumscribed circle picture is divided into a plurality of sub-regions, the region of interest is moved from the sub-region with the highest average pixel value, so that the search time can be saved, in an exemplary embodiment, the wafer circumscribed circle picture is equally divided into 4 sub-regions, that is, 4 equal-area fan-shaped regions, and the region with the highest average pixel value in the 4 fan-shaped regions is selected as the object to be detected. It should be noted that, equally dividing the wafer outer circle picture into 4 sub-regions is only an exemplary embodiment, and the dividing manner and the dividing number of the wafer outer circle picture are not limited, and other dividing manners and dividing numbers of the wafer outer circle picture all belong to the protection scope of the present invention.
The method also comprises the following steps after the interested area is moved in the wafer circumcircle picture:
s410, when the distance between the center of the region of interest and the center of the notch is not within a preset range, sending first alarm information; in this embodiment, the region of interest is moved in the wafer circumcircle picture until the average pixel value of the region of interest is within a preset pixel value set, and when the distance between the center of the region of interest and the center of the notch is not within a preset range, it indicates that although the notch label exists in the wafer circumcircle picture, the notch label does not normally cover the notch, and at this time, first alarm information is sent out, and a worker takes corresponding measures in time according to the first alarm information, so as to avoid that the yield is reduced because the notch label does not normally cover the notch.
S420, when the region of interest traverses the wafer circumcircle picture and the average pixel value of the region of interest is not found in the preset pixel value set, second alarm information is sent. In this embodiment, when the region of interest traverses the wafer circumscribed circle picture and the average pixel value of the region of interest is not found within the preset pixel value set, it indicates that there is no gap label in the wafer circumscribed circle picture or there are other abnormal situations in the wafer circumscribed circle picture and the original picture corresponding to the wafer circumscribed circle picture, for example, the acquired original picture is incomplete, and a gap label is blocked by a foreign object, and at this time, the second alarm information is sent, and the staff takes corresponding measures in time according to the first alarm information.
FIG. 2 is a second flowchart of a method for detecting an abnormal gap coverage according to the present exemplary embodiment; as shown in fig. 2, a method for detecting an abnormal coverage of a notch includes:
a camera carried by a machine station shoots a machine station chamber in real time and uploads a picture to an NAS (network attached storage) through a network;
reading a machine storage system by using a timing task program, and selecting a picture of a wafer installing machine as an original picture;
carrying out graying processing on an original picture, carrying out binarization, carrying out denoising by applying Gaussian filtering to finish preprocessing operation of the picture, and extracting a pixel value set A of Notch Tab from the grayed picture;
detecting the number of angular points existing in the preprocessed operation picture by using a Canny edge detection technology, if the number of the angular points is more than 4, proving that the original picture contains Notch Tab, if not, determining that the original picture is wrong, filtering the wrong picture, and not performing subsequent operation;
acquiring the outline of the wafer in the gray level picture by using an outline detection algorithm, drawing an circumscribed circle and storing the circumscribed circle as a picture B, calculating the coordinate of the circle center and the diameter of the circumscribed circle, and dividing the picture diameter of the picture B by the actual diameter of the wafer by using the diameter length of the wafer in the known information to obtain an image scale;
multiplying the actual radius of the wafer by the picture scale to obtain the distance from the circle center to the Notch in the picture B, determining the direction of the Notch in the picture B according to the position of the machine station corresponding to the Notch when the wafer is placed, and moving the position of the circle center in the picture B to the edge of the picture B in the direction of the corresponding Notch to obtain the position of the Notch point; the placing directions are uniformly fixed when the wafer is installed, the wafer installation positions can be positioned and calibrated through the notches and the machine table, so that the notch positions of all wafers are uniformly fixed, the shooting angle of the machine table is fixed, the notch positions of different wafers are the same in an original picture, the notch positions can be obtained only by moving the radius of the picture along the same fixed direction from the circle center position of the picture, wherein the same fixed direction is generally vertical downward movement along the center point position;
constructing an embedded rectangle C which takes the Notch as a center and has the length and the width equal to the length and the width of the Notch Tab minus 1mm respectively according to the position of the Notch point, the width and the height of the Notch Tab and a picture scale; the embedded rectangle C is arranged corresponding to the outer circle of the wafer picture.
Calculating whether the four vertexes of the embedded rectangle C and the average pixel value in the rectangular area are in the set A, if so, judging that the picture is normal, covering the Notch by the Notch Tab, entering a subsequent measurement link, otherwise, continuously searching the position of the Notch Tab in the picture B, and continuously performing the following operations;
equally dividing the picture B into 4 fan-shaped areas with equal areas, and selecting the object to be detected with the highest average pixel value in the 4 fan-shaped areas as the average pixel value of the semicircle where the Notch Tab is white and can be pulled up;
continuously moving the position of the embedded rectangle C from one endpoint of the sector area, searching the area which leads the four vertexes of the embedded rectangle and the average pixel value in the rectangular area to be in the set A, and determining the position of the Notch Tab in the original picture, which is the area of the set A, of the average pixel value;
after the Notch Tab position is determined, calculating the distance between the center of the embedded rectangle C meeting the condition and the Notch, if the distance is within a reasonable range (the distance between the center of the embedded rectangle C meeting the condition and the Notch is less than 1.98 mm), ignoring the distance, and if the distance is not within the reasonable range (the distance between the center of the embedded rectangle C meeting the condition and the Notch is not less than 1.98 mm), sending an alarm;
and after receiving the alarm, stopping and checking the wafer processing machine.
Fig. 9 is a block diagram of a detection system of a gap coverage abnormality of the present exemplary embodiment. As shown in fig. 9, an exemplary embodiment of the present disclosure provides a detection system for a gap coverage abnormality, including:
the first determining module is used for determining the position of a notch in the picture of the wafer circumscribed circle;
the construction module is used for constructing an interested area which is proportional to the area of the gap label and can cover the gap;
the judging module is used for judging whether the average pixel value of the region of interest is within a preset pixel value set or not;
the second determining module is used for determining that the notch label covers the notch of the wafer when the average pixel value of the region of interest is within a preset pixel value set;
the moving module is used for moving the region of interest in the wafer circumcircle when the average pixel value of the region of interest is not within a preset pixel value set;
and the third determining module is used for determining that the notch label covers the notch of the wafer when the region of interest is moved in the wafer circumscribed circle picture until the average pixel value of the region of interest is within a preset pixel value set and the distance between the center of the region of interest and the center of the notch is within a preset range. An exemplary embodiment of the present disclosure provides a detection apparatus of a gap coverage abnormality, including: a processor and a memory; the memory is used for storing a computer program, and the processor calls the computer program stored in the memory to execute the detection method of the gap coverage abnormity.
The acquisition module is used for acquiring an original picture;
the preprocessing module is used for preprocessing the original picture to form a preprocessed picture;
and the fourth determining module is used for determining whether the notch label exists in the preprocessed picture.
The preprocessing module comprises: the gray processing unit is used for processing the original picture in a gray mode to form a gray picture; and the binarization processing unit is used for binarizing the gray level picture, and denoising the binarized gray level picture to obtain a preprocessed picture.
The fourth determining module includes: the detection unit is used for detecting the number of angular points in the preprocessed picture by adopting an edge detection algorithm; the judging unit is used for judging whether the number of the angular points existing in the preprocessed picture is greater than the number of preset angular points or not; a gap label determining unit, configured to determine that the preprocessed picture with the number of the corner points being greater than or equal to the preset number of the corner points is a gap label; and the screening unit is used for screening the preprocessed pictures of which the angular points are less than the preset angular points.
The fourth determining module includes: and the extraction unit is used for extracting the pixel value set of the notch label from the gray picture as a preset pixel value set.
The first determining module includes: the gray processing unit is used for carrying out gray processing on the original picture to form a gray picture; the forming unit is used for acquiring the outline of the wafer in the gray level picture by utilizing an outline detection algorithm, drawing an outer circle of the outline of the wafer and forming a wafer outer circle picture; the first calculation unit is used for calculating the circle center and the diameter of the circumscribed circle in the wafer circumscribed circle picture; the second calculation unit is used for calculating to obtain an image scale according to the diameter of the circumscribed circle and the actual diameter of the wafer; the third calculating unit is used for calculating the picture radius of the wafer in the wafer circumcircle picture according to the image scale; and the gap position determining unit is used for moving the wafer gap fixing position direction by a distance equal to the radius of the wafer picture by taking the circle center of the circumscribed circle as a starting point, and determining the position of the gap in the wafer circumscribed circle picture.
The center of the region of interest is the position of the notch, and the length and width of the region of interest are equal to the value obtained by subtracting a preset value from the length and width of the actual notch label and then reducing the size according to the image proportion.
The average pixel value of the region of interest comprises a vertex pixel value of the region of interest and values of all pixel points in the region of interest.
Further comprising: the first warning module is used for sending first warning information when the distance between the center of the region of interest and the center of the notch is not within a preset range; and the second alarm module is used for sending out second alarm information when the average pixel value of the region of interest is not found in the preset pixel value set when the region of interest traverses the wafer circumscribed circle picture.
The moving module includes: the dividing unit is used for dividing the wafer circumcircle picture into a plurality of sub-areas; a fourth calculation unit for calculating an average pixel value of each of the sub-regions; the selecting unit is used for selecting a subarea with the highest average pixel value from a plurality of subareas; a moving unit for moving the region of interest within the sub-region where the average pixel value is highest.
Exemplary embodiments of the present disclosure provide a computer-readable storage medium having stored therein a computer program, which, when executed by a processor, enables the processor to execute the above-described method of detecting a gap coverage abnormality.
The above is only a preferred embodiment of the present disclosure, and the protection scope of the present disclosure is not limited to the above embodiments, and all technical solutions that belong to the idea of the present disclosure belong to the protection scope of the present disclosure. It should be noted that several modifications and decorations within the scope of the present disclosure may be considered by those skilled in the art without departing from the principle of the present disclosure.
Claims (22)
1. A method for detecting a gap coverage anomaly, comprising:
determining the position of a notch in the picture of the wafer circumscribed circle, and constructing an interested area which is proportional to the area of the notch label and can cover the notch;
judging whether the average pixel value of the region of interest is within a preset pixel value set or not;
when the average pixel value of the region of interest is within a preset pixel value set, determining that the notch label covers a wafer notch;
otherwise, moving the region of interest in the wafer circumcircle picture until the average pixel value of the region of interest is within a preset pixel value set and the distance between the center of the region of interest and the center of the notch is within a preset range, and determining that the notch label covers the notch of the wafer.
2. The method for detecting the abnormal coverage of the notch as claimed in claim 1, wherein the step of determining the position of the notch in the picture of the wafer circumcircle comprises the steps of, before constructing the region of interest which is proportional to the area of the notch label and can cover the notch:
acquiring an original picture;
preprocessing the original picture to form a preprocessed picture;
and determining whether a gap label exists in the preprocessed picture.
3. The method according to claim 2, wherein the preprocessing the original image to form a preprocessed image comprises:
processing the original picture in a gray scale mode to form a gray scale picture;
and binarizing the gray-scale picture, and denoising the binarized gray-scale picture to obtain a preprocessed picture.
4. The method according to claim 2, wherein the determining whether the gap label exists in the preprocessed image includes:
detecting the number of angular points in the preprocessed picture by adopting an edge detection algorithm;
judging whether the number of angular points existing in the preprocessed picture is larger than a preset number of angular points or not;
determining the preprocessed pictures with the angular point number greater than or equal to the preset angular point number as notched labels;
and screening out the preprocessed pictures of which the angular points are smaller than the preset angular points.
5. The method according to claim 3, wherein the preprocessing the original image to form a preprocessed image further comprises:
and extracting a pixel value set of the notch label from the gray picture as a preset pixel value set.
6. The method of claim 2, wherein the determining the position of the notch in the picture of the wafer circumscribed circle comprises:
carrying out gray processing on the original picture to form a gray picture;
acquiring the outline of the wafer in the gray level picture by utilizing an outline detection algorithm, and drawing an outer circle of the outline of the wafer to form a wafer outer circle picture;
calculating the circle center and the diameter of the circumscribed circle in the picture of the circumscribed circle of the wafer;
calculating according to the diameter of the circumscribed circle and the actual diameter of the wafer to obtain an image scale;
calculating the picture radius of the wafer in the wafer circumcircle picture according to the image scale;
and moving the wafer in the direction of the fixed position of the notch by a distance equal to the radius of the wafer picture by taking the circle center of the circumscribed circle as a starting point, and determining the position of the notch in the wafer circumscribed circle picture.
7. The method for detecting a gap coverage abnormality according to claim 1,
the center of the region of interest is the position of the notch, and the length and width of the region of interest are equal to the value obtained by subtracting a preset value from the length and width of the actual notch label and then reducing the size according to the image proportion.
8. The method for detecting a gap coverage abnormality according to claim 1,
the average pixel value of the interested region comprises a vertex pixel value of the interested region and values of all pixel points in the interested region.
9. The method according to any one of claims 1 to 8, wherein the step of moving the region of interest within the wafer circumscribing the wafer until an average pixel value of the region of interest is within a preset set of pixel values and a distance between a center of the region of interest and a center of the notch is within a preset range comprises the step of determining that the notch label covers the notch of the wafer, after:
when the distance between the center of the region of interest and the center of the gap is not within a preset range, sending first alarm information;
and when the region of interest traverses the wafer circumscribed circle picture and does not find that the average pixel value of the region of interest is within the preset pixel value set, sending second alarm information.
10. The method as claimed in claim 1, wherein the moving the region of interest within the wafer outline comprises:
dividing the wafer circumscribed circle picture into a plurality of sub-regions;
calculating an average pixel value for each of the sub-regions;
selecting a sub-region with the highest average pixel value from a plurality of sub-regions;
moving the region of interest within the sub-region where the average pixel value is highest.
11. A system for detecting a gap coverage anomaly, comprising:
the first determining module is used for determining the position of a notch in the picture of the wafer circumscribed circle;
the construction module is used for constructing an interested area which is proportional to the area of the gap label and can cover the gap;
the judging module is used for judging whether the average pixel value of the interested area is within a preset pixel value set or not;
the second determining module is used for determining that the notch label covers the notch of the wafer when the average pixel value of the region of interest is within a preset pixel value set;
the moving module is used for moving the interested region in the wafer circumcircle picture when the average pixel value of the interested region is not in the preset pixel value set;
and the third determining module is used for determining that the notch label covers the notch of the wafer when the region of interest is moved in the wafer circumscribed circle picture until the average pixel value of the region of interest is within a preset pixel value set and the distance between the center of the region of interest and the center of the notch is within a preset range.
12. The system for detecting a gap coverage anomaly of claim 11, comprising:
the acquisition module is used for acquiring an original picture;
the preprocessing module is used for preprocessing the original picture to form a preprocessed picture;
and the fourth determining module is used for determining whether the notch label exists in the preprocessed picture.
13. The system for detecting a gap coverage anomaly of claim 12, wherein said preprocessing module comprises:
the gray processing unit is used for processing the original picture in a gray mode to form a gray picture;
and the binarization processing unit is used for binarizing the gray level picture, and denoising the binarized gray level picture to obtain a preprocessed picture.
14. The system for detecting a gap coverage anomaly of claim 12, wherein said fourth determination module comprises:
the detection unit is used for detecting the number of angular points in the preprocessed picture by adopting an edge detection algorithm;
the judging unit is used for judging whether the number of the angular points existing in the preprocessed picture is greater than the number of preset angular points or not;
a notch label determining unit, configured to determine that a notch label exists in the preprocessed picture whose corner number is greater than or equal to the preset corner number;
and the screening unit is used for screening the preprocessed pictures of which the angular points are less than the preset angular points.
15. The system for detecting a gap coverage anomaly of claim 13, wherein said fourth determination module comprises:
and the extraction unit is used for extracting the pixel value set of the notch label from the gray picture as a preset pixel value set.
16. The system for detecting a gap coverage anomaly of claim 12, wherein said first determining module comprises:
the gray processing unit is used for carrying out gray processing on the original picture to form a gray picture;
the forming unit is used for acquiring the outline of the wafer in the gray level picture by utilizing an outline detection algorithm, drawing an outer circle of the outline of the wafer and forming a wafer outer circle picture;
the first calculation unit is used for calculating the circle center and the diameter of the circumscribed circle in the wafer circumscribed circle picture;
the second calculation unit is used for calculating to obtain an image scale according to the diameter of the circumscribed circle and the actual diameter of the wafer;
the third calculating unit is used for calculating the picture radius of the wafer in the wafer circumcircle picture according to the image scale;
and the gap position determining unit is used for moving the wafer gap in the fixed position direction by a distance equal to the radius of the wafer picture by taking the circle center of the circumscribed circle as a starting point, and determining the wafer gap as the gap position in the wafer circumscribed circle picture.
17. The system for detecting a gap coverage anomaly of claim 11,
the center of the region of interest is the position of the notch, and the length and width of the region of interest are equal to the value obtained by subtracting a preset value from the length and width of the actual notch label and then reducing the size according to the image proportion.
18. System for detection of anomaly in notch coverage according to claim 11,
the average pixel value of the region of interest comprises a vertex pixel value of the region of interest and values of all pixel points in the region of interest.
19. A system for detecting gap coverage anomalies as claimed in any one of claims 11 to 18 including:
the first warning module is used for sending first warning information when the distance between the center of the region of interest and the center of the gap is not within a preset range;
and the second alarm module is used for sending out second alarm information when the average pixel value of the region of interest is not found in the preset pixel value set when the region of interest traverses the wafer circumscribed circle picture.
20. The system for detecting anomaly in notch coverage according to claim 11, wherein said movement module comprises:
the dividing unit is used for dividing the wafer circumcircle picture into a plurality of sub-areas;
a fourth calculation unit configured to calculate an average pixel value for each of the sub-regions;
the selecting unit is used for selecting a subarea with the highest average pixel value from a plurality of subareas;
a moving unit for moving the region of interest within the sub-region where the average pixel value is highest.
21. A detection apparatus for a gap covering abnormality, comprising:
a processor and a memory;
the memory is used for storing a computer program, and the processor calls the computer program stored in the memory to execute the detection method of the gap coverage abnormity of any one of claims 1 to 11.
22. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, enables the processor to carry out the method of detecting a gap coverage anomaly of any one of claims 1 to 11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211370150.2A CN115619761A (en) | 2022-11-03 | 2022-11-03 | Method, system, equipment and storage medium for detecting gap coverage abnormity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211370150.2A CN115619761A (en) | 2022-11-03 | 2022-11-03 | Method, system, equipment and storage medium for detecting gap coverage abnormity |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115619761A true CN115619761A (en) | 2023-01-17 |
Family
ID=84877077
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211370150.2A Pending CN115619761A (en) | 2022-11-03 | 2022-11-03 | Method, system, equipment and storage medium for detecting gap coverage abnormity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115619761A (en) |
-
2022
- 2022-11-03 CN CN202211370150.2A patent/CN115619761A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US6876445B2 (en) | Method for analyzing defect data and inspection apparatus and review system | |
| CN111307727B (en) | Water body water color abnormity identification method and device based on time sequence remote sensing image | |
| CN114140679B (en) | Defect fusion method, device, recognition system and storage medium | |
| JP6598162B2 (en) | Visual identification method of multi-type BGA chip based on linear clustering | |
| US6954550B2 (en) | Image processing method and apparatus | |
| CN113096119B (en) | Method and device for classifying wafer defects, electronic equipment and storage medium | |
| CN104718428A (en) | Pattern inspecting and measuring device and program | |
| CN113646801A (en) | Defect detection method and device for defect image and computer readable storage medium | |
| CN115205223B (en) | Visual inspection method and device for transparent object, computer equipment and medium | |
| CN109285791B (en) | Design layout-based rapid online defect diagnosis, classification and sampling method and system | |
| CN113643276B (en) | Textile texture defect automatic detection method based on statistical analysis | |
| CN110047063B (en) | Material drop detection method, device, equipment and storage medium | |
| US20110164129A1 (en) | Method and a system for creating a reference image using unknown quality patterns | |
| CN113408519B (en) | Method and system for pointer instrument reading based on template rotation matching | |
| US7024031B1 (en) | System and method for inspection using off-angle lighting | |
| US9443165B2 (en) | Blob-encoding | |
| CN112634259A (en) | Automatic modeling and positioning method for keyboard keycaps | |
| CN115619761A (en) | Method, system, equipment and storage medium for detecting gap coverage abnormity | |
| CN113012137B (en) | Panel defect inspection method, system, terminal device and storage medium | |
| CN109978879A (en) | Case angle based on loading goods train video monitor enters slot condition detection method | |
| CN115471650A (en) | Gas pressure instrument reading method, device, equipment and medium | |
| KR101521620B1 (en) | method of segmentation of die image for semiconductor device examination | |
| CN108509845B (en) | Visual inspection method for transformer substation instrument equipment inspection based on feature fitting | |
| CN110874837A (en) | Automatic defect detection method based on local feature distribution | |
| Kim | License plate location method unaffected by variation in size and aspect ratio |
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 |