CN117409435A

CN117409435A - Automatic checking method and equipment for drawing data document

Info

Publication number: CN117409435A
Application number: CN202210804265.1A
Authority: CN
Inventors: 严聪; 金文�; 向威; 黄正雨; 刘刚
Original assignee: Shennan Circuit Co Ltd
Current assignee: Shennan Circuit Co Ltd
Priority date: 2022-07-07
Filing date: 2022-07-07
Publication date: 2024-01-16

Abstract

The application discloses a drawing data document automatic checking method and equipment. The automatic drawing data document checking method comprises the following steps: acquiring a scanning image of the detection substrate; obtaining a marking document of the detection substrate; acquiring a drawing data document; converting the scanned image into a first matrix square chart and carrying out waste identification; converting the marked file into a second matrix square chart and carrying out waste identification; converting the drawing data file into a third matrix check chart; comparing the first matrix check diagram with the third matrix check diagram to identify waste products of the third matrix check diagram; and comparing the second matrix check diagram with the third matrix check diagram to identify the waste of the third matrix check diagram. Compared with the prior art, the method and the device for automatically checking the drawing data document determine the rejection mark of the drawing data document according to the two parts of the scanned image and the marking document, so that the automatic checking of the drawing data document can be realized, and the checking efficiency and the checking accuracy are improved.

Description

Automatic checking method and equipment for drawing data document

Technical Field

The present disclosure relates to the field of substrate detection, and in particular, to a method and apparatus for automatically inspecting a drawing data document.

Background

In the substrate industry, it is necessary to acquire a drawing data document, and to determine the condition of each unit on a substrate by checking the data of the drawing data document. However, at present, the substrate industry typically uses a manual inspection to inspect the data of drawing documents.

However, the inspection is performed by a manual inspection mode, so that a large amount of manpower and material resources are required, and the efficiency is low; on the other hand, the error is easy to occur in the inspection and the error rate is high.

Disclosure of Invention

The technical problem that the application mainly solves is to provide an automatic checking method and equipment for drawing data files, so as to solve the problem that the manual checking of the data of the drawing data files is easy to make mistakes.

In order to solve the technical problems, the technical scheme adopted by the application is as follows: there is provided a drawing data document automatic checking method including: acquiring a scanning image of the detection substrate; obtaining a marking document of the detection substrate; acquiring a drawing data document; converting the scanned image into a first matrix square chart and carrying out waste identification; converting the marked file into a second matrix square chart and carrying out waste identification; converting the drawing data file into a third matrix check chart; comparing the first matrix check diagram with the third matrix check diagram to identify waste products of the third matrix check diagram; and comparing the second matrix check diagram with the third matrix check diagram to identify the waste of the third matrix check diagram.

The step of converting the scanned image into a first matrix square chart and performing waste identification comprises the following steps: identifying the area where the unit is located on the scanned image; positioning each cell on the scanned image to convert the scanned image into a first matrix grid pattern; performing waste identification on the bad units through learning and training; and after the unit comparison is completed, the rejection identification of the first matrix check graph is completed.

Wherein the number of rows and columns of the first matrix checkerboard is obtained through external input.

Wherein the first matrix square chart, the second matrix square chart and the third matrix square chart have the same row and column numbers.

The step of performing reject identification on the bad units through learning training comprises the following steps: acquiring an image of a preset bad unit; comparing the unit in the scanned image with the image of the preset bad unit; and if the waste marks are the same, performing waste mark.

After the step of converting the marked document into the second matrix square chart and performing the waste mark, the method further comprises the following steps: comparing the first matrix square diagram with the second matrix square diagram, and confirming whether coordinates of the waste marks of the first matrix square diagram and the second matrix square diagram are the same; and if the coordinates of the rejection marks of the first matrix square chart and the second matrix square chart are the same, performing the subsequent steps.

If the coordinates of the reject marks of the first matrix square chart and the second matrix square chart are different, the detection substrate is set as the substrate to be processed.

Wherein the step of identifying the area of the unit for the scanned image comprises: selecting a region where a unit in the scanned image is located; obtaining the number of rows and columns to divide the units; the location features of the cells are learning trained to determine the starting location of the selected region.

The step of obtaining the marking document of the detection substrate comprises the following steps: scanning and detecting a two-dimensional code of the substrate; and calling the corresponding marking document according to the scanning result of the two-dimensional code.

In order to solve the technical problems, another technical scheme adopted by the application is as follows: there is provided a drawing data document automatic inspection apparatus including: the conveying device is similar to the conveying detection substrate, and the specific position of the conveying device is a scanning position; the light source group comprises three groups of light sources, namely a red light source, a first blue light source and a second blue light source in sequence; the line scanning camera is arranged corresponding to the scanning position; an information processing apparatus connecting the line scan camera and performing the drawing data document automatic inspection method as described in any one of the above.

The beneficial effects of this application are: compared with the prior art, the method and the device for automatically checking the drawing data document are provided, and the rejection mark of the drawing data document is determined according to the two parts of the scanned image and the marked document, so that the automatic checking of the drawing data document can be realized, and the checking efficiency and the checking accuracy are improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. Wherein:

FIG. 1 is a flow chart of an embodiment of a method for automatically inspecting a drawing data document according to the present application;

FIG. 2 is a schematic diagram of the first matrix grid of FIG. 1;

FIG. 3 is a sub-flowchart of S14 in FIG. 1;

FIG. 4 is a sub-flowchart of S141 in FIG. 3;

fig. 5 is a schematic diagram of a second matrix square chart in S15 in fig. 1;

fig. 6 is a schematic diagram of a third matrix square diagram in S18 in fig. 1;

FIG. 7 is a block diagram schematically illustrating a structure of an embodiment of the automatic inspection apparatus for drawing data documents of the present application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.

The terminology used in the embodiments of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise, the "plurality" generally includes at least two, but does not exclude the case of at least one.

It should be understood that the term "and/or" as used herein is merely one relationship describing the association of the associated objects, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.

It should be understood that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.

A method of packaging provided herein is described in detail below with reference to the accompanying drawings and examples.

Referring to fig. 1, fig. 1 is a flowchart illustrating an embodiment of a method for automatically checking a drawing data document according to the present application. As shown in fig. 1, in the present embodiment, the method includes:

in S11, a scan image of the detection substrate is acquired. The scan image of the detection substrate may be obtained by scanning the detection substrate with a line scan camera. And, in order to ensure the definition and recognition of the image, it is optimally accomplished using an 8K black and white line scan camera.

In S12, a marking document of the detection substrate is acquired. The marking document is a scc defect coordinate document, and can be obtained when defect detection is performed on the detection substrate. In the method, the detection of drawing data documents is concerned, the order of which is after the defect detection, so that the marking document of the detection substrate can be directly called. Each detection substrate has its unique identification two-dimensional code, and thus, the step of obtaining the marking document of the detection substrate may include: scanning and detecting a two-dimensional code of the substrate; and calling the corresponding marking document according to the scanning result of the two-dimensional code.

In S13, a drawing data document is acquired. In this step, the drawing data document may be converted by the markup document. Because the marking document is not easy to read, the marking document needs to be converted into a drawing data document, so that the defect data of the detection substrate can be more clearly and conveniently checked.

In S14, the scanned image is converted into a first matrix grid pattern, and the reject identification is performed. Referring to fig. 2, fig. 2 is a schematic diagram of the first matrix square chart in fig. 1. As shown in fig. 2, the scanned image is converted into a first matrix grid pattern, so that the first matrix grid pattern becomes an image in a row-column matrix arrangement, like a table. Each cell represents a cell on the test substrate. And carrying out rejection identification on the unit in which the defect is detected at the corresponding position of the first matrix square. For example, if the fourth cell in the second row of the scanned image is detected as a defective cell, it is identified as a defective cell and distinguished from other cells.

Referring to fig. 3, fig. 3 is a sub-flowchart of S14 in fig. 1.

In S141, the scan image is identified as the area where the unit is located. In this step, the region where the scanning image processing unit is located can be directly identified by training the model. Alternatively, referring to fig. 4, fig. 4 is a sub-flowchart of S141 in fig. 3. In this embodiment, the step of identifying the area where the scanning image processing unit is located includes:

in S411, an area where a cell in the scanned image is located is selected. The selection may be performed by reading the positions in each cell set to select the region where the cell in the scanned image is located, or may be performed directly by the search box. There may be one region or a plurality of regions on one detection substrate.

In S412, the number of rows and columns are acquired to divide the cells. The manner of acquiring the number of rows and columns may be acquired by analyzing the arrangement of the units on the scanned image, or may be acquired by an external input, or may be acquired by other means, which is not limited herein.

In S413, the location feature of the cell is learning trained to determine the starting location of the selected region. There are various ways to learn and train the positioning features of the units, for example, to provide preset positioning features of the units for comparison; or by analyzing the cells in the region, for example, the cell at the intersection of the first row and the first column is the starting cell, or the cell at the intersection of the last row and the last column is the starting cell, or the cell at the intersection of the first row and the last column is the starting cell. The position of the starting unit is the starting position. The starting position is determined, coordinates can be created to divide the matrix so that the scanned image can be converted into a first matrix grid and the reject identification can be performed.

In S142, each cell on the scanned image is positioned to convert the scanned image into a first matrix grid pattern.

In S143, defective units are identified as defective products by learning training. In a preferred embodiment, this step comprises:

acquiring an image of a preset bad unit;

comparing the unit in the scanned image with the image of the preset bad unit. If the two types of the waste marks are the same, waste marks are carried out; if the mark is different, the mark of the waste is not carried out or the mark is good.

In S144, after the cell comparison is completed, the rejection identification of the first matrix square is completed.

In S15, the marked document is converted into a second matrix square, and the reject identification is performed. Because the marking document itself is a defective coordinate document, the teaching is easily converted into a second matrix grid pattern. And the defect coordinate position is recorded, so that the rejection mark can be performed. Referring to fig. 5, fig. 5 is a schematic diagram of a second matrix square chart in S15 in fig. 1. For example, in fig. 5, the marking document records that the third cell of the fourth row right number and the third cell of the sixth row right number have defects, and the corresponding position of the second matrix grid chart is identified as defective, so as to be distinguished from the positions of other good cells.

In S16, the drawing data document is converted into a third matrix square chart. The drawing data document is a document which accommodates all defect information of the detection substrate by means of a binary data array, and is therefore the most easily converted into a matrix checkerboard. After the drawing data document is converted into the third matrix square chart, the unification of the scanning image, the standard document and the drawing data document in the format is realized. It should be noted that, the number of rows and columns of the first matrix square, the second matrix square and the third matrix square is the same optimally, so that the accuracy can be improved maximally.

In S17, the first matrix grid pattern and the third matrix grid pattern are compared to identify rejects for the third matrix grid pattern.

In S18, the second matrix grid pattern and the third matrix grid pattern are compared to identify rejects for the third matrix grid pattern. Referring to fig. 6, fig. 6 is a schematic diagram of a third matrix square chart in S18 in fig. 1. In the first matrix square chart, the second row of right number fourth square lattice is provided with a waste mark, so that the same square lattice is subjected to waste mark in the third matrix square chart; in the second matrix square chart, the third square lattice of the fourth row right number and the third square lattice of the sixth row right number are provided with the waste marks, and the same square lattice is subjected to the waste marks in the third matrix square chart. After the identification is finished, the examination of the drawing data document is finished.

In the above steps, the order of S11, S12, and S13 is not limited, and S14 may be after S11, S15 may be after S12, and S16 may be after S13. The order of S17 and S18 may be changed, and the final result is not affected.

In other embodiments, after the step of converting the marked-up document into the second matrix grid and performing the step of identifying the reject, the method further comprises: and comparing the first matrix square diagram with the second matrix square diagram, and confirming whether the coordinates of the waste marks of the first matrix square diagram and the second matrix square diagram are the same. And if the coordinates of the rejection marks of the first matrix square chart and the second matrix square chart are the same, performing the subsequent steps. If the coordinates of the reject marks of the first matrix square chart and the second matrix square chart are different, the detection substrate is set to be the substrate to be processed. The substrate to be processed may be inspected again to determine whether a missed inspection condition exists.

By the method, the rejection mark of the drawing data document can be determined according to the two parts of the scanned image and the marked document, so that automatic inspection of the drawing data document can be realized, and the inspection efficiency and the inspection accuracy are improved.

Referring to fig. 7, fig. 7 is a schematic block diagram showing the structure of an embodiment of the drawing data document automatic inspection apparatus of the present application. The drawing data document automatic inspection apparatus includes: a conveying device 21, a light source group 22, a line scanning camera 23, and an information processing device (not shown).

The conveyor 21 is used for transporting the detection substrate 29, and its specific position is a scanning position. The conveying device 21 can be a conveying belt, or a conveying device formed by matching a screw rod, a sliding block and a motor, and can also be other common conveying devices for conveying objects. In the present embodiment, the loading tray 211 is further mounted on the conveyor 21. The loading tray 211 is used for accommodating the detection substrate 29, and the conveying device 21 drives the loading tray 211 to move to the scanning position, so that the detection substrate 29 is scanned. The loading tray 211 is preferably provided with a vacuum generator for sucking the detection substrate 29 to ensure stability of the detection substrate 29, that the detection substrate 29 does not move when the conveyor 21 is not moving, and that the detection substrate 29 does not drop out of the loading tray 211 when the conveyor 21 is moving.

The light source group 22 is disposed corresponding to the scanning position, and includes three groups of light sources, namely a red light source 221, a first blue light source 222 and a second blue light source 223. The red light source 221, the first blue light source 222 and the second blue light source 223 are all illuminated to the scanning position to provide the necessary illumination and color for the line scan camera 23. Since the red light source 221 and the second blue light source 223 are respectively located twice of the first blue light source 222, the red light source 221 and the second blue light source 223 are both inclined to the first blue light source 222 to enable the red light source 221, the first blue light source 222 and the second blue light source 223 to irradiate the scanning position.

The line scanning camera 23 is fixed by a support 24 and is disposed corresponding to the scanning position. The line scanning camera 23 is provided so as to be able to acquire a scanned image of the detection substrate, thereby performing detection of the drawing data document. In addition, the light source group 22 may be fixed by the supporting member 24.

The information processing apparatus connects the line scan camera 23 and performs the drawing data document automatic checking method as described in any one of the above. Preferably, the information processing apparatus includes a processor, a display, and an input-output component, and is capable of running preset software, displaying, and accepting input information.

By the automatic drawing data document checking device, automatic drawing data document checking can be realized, and checking efficiency and checking accuracy are improved.

The foregoing description is only of embodiments of the present application, and is not intended to limit the scope of the patent application, and all equivalent structures or equivalent principle changes made by the specification and the drawings of the present application, or direct or indirect application in other related technical fields, are included in the scope of the patent protection of the present application.

Claims

1. An automatic drawing data document inspection method, characterized in that the automatic drawing data document inspection method comprises:

acquiring a scanning image of the detection substrate;

obtaining a marking document of the detection substrate;

acquiring a drawing data document;

converting the scanned image into a first matrix square chart and carrying out waste identification;

converting the marked file into a second matrix square chart and carrying out waste identification;

converting the drawing data file into a third matrix check chart;

comparing the first matrix square diagram with the third matrix square diagram to perform waste identification on the third matrix square diagram;

and comparing the second matrix square diagram with the third matrix square diagram to perform waste identification on the third matrix square diagram.

2. The automatic inspection method of drawing data documents according to claim 1, wherein the step of converting the scanned image into a first matrix grid and performing reject identification includes:

identifying the area where the unit is located on the scanned image;

positioning each of the cells on the scanned image to convert the scanned image into the first matrix grid;

performing waste identification on the bad units through learning and training;

and after the unit comparison is completed, completing the rejection identification of the first matrix check.

3. The automatic drawing data document inspection method according to claim 2, wherein the number of rows and columns of the first matrix checkerboard is obtained by an external input.

4. The automatic drawing data document inspection method according to claim 3, wherein the first matrix pattern, the second matrix pattern, and the third matrix pattern have the same number of rows and columns.

5. The automatic inspection method of drawing data documents according to claim 2, wherein the step of reject-marking the defective unit by learning training comprises:

acquiring an image of a preset bad unit;

comparing the unit in the scanned image with the image of the preset bad unit;

and if the waste marks are the same, performing waste mark.

6. The automatic inspection method of drawing data documents according to claim 2, further comprising, after the step of converting the marked-up document into a second matrix grid and performing reject identification:

comparing the first matrix check diagram with the second matrix check diagram, and confirming whether coordinates of waste marks of the first matrix check diagram and the second matrix check diagram are the same;

and if the coordinates of the rejection marks of the first matrix check chart and the second matrix check chart are the same, performing the subsequent steps.

7. The automatic inspection method of drawing data documents according to claim 6, wherein if the coordinates of the reject marks of the first matrix square and the second matrix square are different, the inspection substrate is set as the substrate to be processed.

8. The automatic inspection method of drawing data documents according to claim 2, wherein the step of recognizing the area where the unit is located for the scanned image includes:

selecting an area in which the unit in the scanned image is located;

obtaining the number of rows and columns to divide the units;

learning the location features of the unit to determine the starting location of the selected region.

9. The automatic drawing data document inspection method according to claim 1, wherein the step of acquiring the marked document of the detection substrate includes:

scanning the two-dimensional code of the detection substrate;

and calling the corresponding marking document according to the scanning result of the two-dimensional code.

10. An automatic drawing data document inspection apparatus, characterized in that the automatic drawing data document inspection apparatus comprises:

a transport device for transporting the detection substrate, wherein a specific position of the transport device is a scanning position;

the light source group comprises three groups of light sources, namely a red light source, a first blue light source and a second blue light source in sequence,

the line scanning camera is arranged corresponding to the scanning position;

an information processing apparatus which is connected to the line scan camera and performs the drawing data document automatic checking method according to any one of claims 1 to 9.