An automated optical inspection method and system
By preprocessing, channelizing, and differentiating the scanning data of the membrane material, the range of defect judgment is expanded, solving the problem of omission caused by the deviation between the automatic optical inspection device and the actual position, and realizing efficient and accurate defect detection.
Patent Information
- Application Number
- CN202311866995.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-12-31
- Publication Date
- 2026-11-10
- Estimated Expiration
- 2043-12-31
AI Technical Summary
During the film cutting process, the automatic optical inspection device deviates from the actual position, which may lead to the risk of missing defective products. In addition, manual inspection is inefficient and it is difficult to detect defects in a timely manner.
The camera acquisition module acquires scanned data of the material, performs preprocessing, channelization, difference processing, and classification processing, obtains multiple sets of defect information, expands the scope of defect judgment, and avoids omissions.
This improved the accuracy of testing, avoided the risk of material omissions during quality assessment, and ensured the accuracy and efficiency of testing.
Smart Images

Figure CN117825385B_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of optical inspection technology, and specifically relates to an automatic optical inspection method and system. Background Technology
[0002] The capacity for manual full inspection of polarizer film cutting is limited. Compared with manual inspection, automated optical inspection (AOI) machine vision inspection is more reliable. Manual inspection is inefficient for products with many defects or large polarizer film sizes. Moreover, long-term inspection can cause eye fatigue and lead to missed inspections. Therefore, replacing manual inspection with machines is an inevitable development trend in the film material industry in the future.
[0003] Currently, in the membrane material industry, oscillating wheels are added to cutting devices to improve the quality of the cut edges of finished products. During the cutting process, the roll material is stretched under tension to ensure a smooth cut edge. However, this indirectly leads to a deviation between the actual position of defects and the position recorded by the automatic optical inspection device during the stretching process of the oscillating wheel, resulting in the risk of missing defects in the sheet quality assessment. Furthermore, the tension of the roll material itself varies, and the oscillation amplitude of the oscillating wheel is random in order to maintain a constant tension, thus the deviation caused by stretching is also random. In actual mass production, it is impossible for humans to guarantee the timely detection of missed sheets, resulting in defective products reaching the customer. Summary of the Invention
[0004] To address the aforementioned problems, this invention proposes an automated optical inspection method and system that can be used for defect quality inspection of membrane materials, thereby avoiding the risk of omissions during material quality assessment.
[0005] To achieve the above-mentioned technical objectives and effects, the present invention is implemented through the following technical solution: On one hand, the present invention provides an automatic optical detection method, comprising: The material area is scanned using a camera acquisition module to obtain the target defect range, and multiple scan data are recorded based on the target defect range. The data processing module receives the multiple scan data and preprocesses them to obtain multiple sets of scan images; The multiple sets of scanned images are channelized, and the channelized images are then subjected to differential processing to obtain multiple sets of defect information. Multiple sets of defect information are classified and processed according to the control requirements to detect material quality.
[0006] Optionally, the method for obtaining the target defect range includes: Based on the camera acquisition module, the grayscale values of the material defect area are obtained; A detection threshold is obtained, which is set based on negligible defects on the material surface; The grayscale value of the material defect area is compared with the detection threshold. The material defect area that exceeds the detection threshold is identified as the target defect area.
[0007] Optionally, the preprocessing of multiple scan data to obtain multiple sets of scan images includes: The multiple scan data are periodically combined based on the scan frequency to obtain scan marker information; Based on the scanning marker information, the multiple scan data are periodically arranged and combined to obtain multiple sets of scan images.
[0008] Optionally, the channelized images are subjected to differential processing to obtain multiple sets of defect information, including: The maximum deviation value is obtained, and the maximum deviation value is set based on actual production data collection. Based on the maximum deviation value, the scanning record coordinates of the channelized image are deviated to obtain multiple sets of defect information.
[0009] Optionally, the deviation of the scan recording coordinates of the channelized image includes: Among the scan coordinates of multiple sets of images, one set is determined as the reference coordinates; Centered on the reference coordinates, along the X-axis or Y-axis, the maximum deviation value is increased or decreased by multiples to serve as the scanning coordinates for the remaining groups.
[0010] Optionally, the process of classifying and processing multiple sets of defect information according to control requirements to detect material quality includes: When the defect information meets the defect control criteria for good products, the material is detected as a good product; When the defect information meets the defect control criteria for defective products, the material is detected as a defective product. The defect control for good products and defective products are set according to product requirements.
[0011] In one aspect, the present invention provides an automated optical inspection system applied to the automated optical inspection method described in the first aspect, comprising: A camera acquisition module is used to scan the material area based on the camera acquisition module to obtain the target defect range, and record multiple scan data according to the target defect range; The data processing module is used to receive and process multiple scan data obtained from the camera acquisition module to detect the quality of the material.
[0012] Optionally, the data processing module includes a preprocessing unit, a channel processing unit, a deviation processing unit, and a classification processing unit; The preprocessing unit is used to preprocess multiple scan data to obtain multiple sets of scan images; The channel processing unit is used to process multiple sets of scanned images into channels; The deviation processing unit is used to perform differential processing on the channelized image to obtain multiple sets of defect information; The classification and processing unit is used to classify and process multiple sets of defect information according to the control requirements to detect material quality. Compared with the prior art, the beneficial effects of the present invention are as follows: This invention proposes an automatic optical inspection method and system. The system acquires multiple scan data through a camera acquisition module and performs preprocessing, channelization, difference processing, and classification processing on the multiple scan data in sequence to obtain material quality inspection results. The detection accuracy is higher, and the risk of omission in the material quality judgment is avoided. Attached Figure Description
[0013] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly described below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort, wherein: Figure 1 This is a flowchart of an automatic optical detection method in one embodiment of the present invention; Figure 2 This is a framework diagram of an automatic optical inspection system in one embodiment of the present invention; Figure 3 This is a schematic diagram comparing automatic optical detection and ordinary optical detection in one embodiment of the present invention; Figure 4 This is a schematic diagram comparing automatic optical detection and ordinary optical detection in a second scenario of one embodiment of the present invention; Figure 5 This is a schematic diagram comparing automatic optical detection and ordinary optical detection in a third case according to one embodiment of the present invention; Figure 6 This is a schematic diagram comparing the fourth case of automatic optical detection and ordinary optical detection in one embodiment of the present invention; Figure 7 This is a schematic diagram comparing the fifth case of automatic optical detection and ordinary optical detection in one embodiment of the present invention. Implementation
[0014] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the present invention or its application or use. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0015] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are used only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined with "first," "second," etc., may explicitly or implicitly include one or more of that feature. In the description of this invention, unless otherwise stated, "a plurality of" means two or more.
[0016] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances. In the description of this invention, "several" means one or more, "multiple" means two or more, and "greater than," "less than," and "exceeding" are understood to exclude the stated number, while "above," "below," and "within" are understood to include the stated number. Where "first" and "second" are used, they are only for distinguishing technical features and should not be construed as indicating or implying relative importance or implicitly indicating the number of indicated technical features or the order of the indicated technical features.
[0017] In the description of this invention, the terms "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.
[0018] The application principle of the present invention will be described in detail below with reference to the accompanying drawings. Example
[0019] like Figure 1 As shown, this invention provides an automatic optical detection method, comprising the following steps: Step S01: Scan the material area using the camera acquisition module to obtain the target defect range, and record multiple scan data based on the target defect range; Step S02: The data processing module receives the multiple scan data and preprocesses the multiple scan data to obtain multiple sets of scan images; Step S03: Channelize the multiple sets of scanned images and perform differential processing on the channelized images to obtain multiple sets of defect information; Step S04: Classify and process multiple sets of defect information according to the control requirements to detect material quality.
[0020] Based on the automatic optical inspection method in this embodiment of the invention, multiple scan data can be acquired through a camera acquisition module, and the multiple scan data can be preprocessed, channelized, differentiated, and classified sequentially to obtain material quality inspection results. The detection accuracy is higher, and the risk of omission in material quality judgment is avoided. In one specific embodiment of the present invention, step S01 specifically includes: The camera acquisition module scans the material area to obtain the range of the target defect; Based on the target defect range, the grayscale value of the material defect area is obtained; A detection threshold is obtained, which is set based on negligible defects on the material surface; The grayscale value of the material defect area is compared with the detection threshold. The material defect area that exceeds the detection threshold is identified as the target area; The target defect area is scanned multiple times per unit time at the same scanning frequency to obtain multiple scan data; Specifically, the material is illuminated by a light source in the camera acquisition module. The material defects cause changes in the camera's light intensity due to their unevenness, thereby obtaining the grayscale value of the material defect area. A detection threshold is set based on negligible defects on the material surface, and the portion of the grayscale value exceeding the detection threshold is determined as the target range.
[0021] In one specific embodiment of the present invention, step S02, which involves preprocessing multiple scan data to obtain multiple sets of scan images, includes: The multiple scan data are periodically combined based on the scan frequency to obtain scan marker information; Based on the scanning marker information, the multiple scan data are periodically arranged and combined to obtain multiple sets of scan images.
[0022] Specifically, in this embodiment, the existing fixed scanning frequency is split, and the defects (defects in the material) are recorded three times. For example, if the material is scanned at a frequency of 12000 Hz, it means that the material is scanned 12000 times per second. In the scanning record of the camera acquisition module, the 12000 scans are marked and recorded in three groups: A, B, and C. The scanning marking order is A1, B1, C1, A2, B2, C2, A3, B3, C3, A4, B4, C4...A4000, B4000, C4000, resulting in 12000 scan data. Then, by filtering the scanning marking information, multiple sets of scan images and their accompanying information can be obtained, such as A(A1,A2,A3,A4,A5,...A4000), B(B1,B2,B3,B4,B5,...B4000), and C(C1,C2,C3,C4,C5,...C4000). The resolution in the machine direction = material speed / camera scanning frequency, meaning the resolution in the machine direction after three scans will become one-third of the resolution in normal mode. The resolution in the horizontal direction = material width / (number of cameras * number of pixels per line scan camera), meaning the resolution in the horizontal direction after three scans is consistent with the resolution in normal mode. The detected data from the three sets of scan images show little difference and all conform to the characteristics of the defect data, so they can all be used as the basis for judging the defect.
[0023] In one specific embodiment of the present invention, step S03 specifically includes: Multiple sets of scanned images are channelized; The maximum deviation value S is obtained, and the maximum deviation value S is set based on actual production data collection. Based on the maximum deviation value S, the scan record coordinates of the channelized image are deviated to obtain multiple sets of defect information (multiple sets of defect scan record coordinates); the deviation of the scan record coordinates of the channelized image includes: Among the scan coordinates of multiple sets of images, one set is determined as the reference coordinates; Centered on the reference coordinates, along the X-axis or Y-axis, the maximum deviation value is increased or decreased by multiples to serve as the scanning coordinates for the remaining groups.
[0024] In this embodiment, the three sets of scanned images are processed separately and treated as multiple channels of scanning imaging. They are named and parameter controlled, such as TD, TDA, and TDB. This means that multiple channels with the same camera settings and light source configuration are used to detect defects, and the defect detection data tends to be consistent with small fluctuation errors.
[0025] To address the error issue in the mechanical direction, a specific coordinate deviation is applied to the channel, i.e., the actual coordinates Q(X,Y) of the original defect. This invention scans and records coordinates A(M,NS), B(M,N), and C(M,N+S). The actual coordinate error of the original defect is within the defect range of three imaging operations, i.e., it satisfies NS... <Y<N+S。
[0026] For differential processing, the three sets of channel cameras without deviation have the same scanning mechanical position, resulting in identical target defect imaging and an inability to expand the judgment range. By deviating the mechanical direction position of the scanning lines in the three sets of channel modules, the defect recording position is changed, achieving misalignment of the three sets of defects and expanding the judgment range, thereby improving the situation of defect omission. For example, if the defect itself has a length L, the defect judgment machine direction range in normal mode is L, while the defect judgment area in this invention is S+S+L, expanding the judgment range by 2S.
[0027] In this embodiment, classifying and processing multiple sets of defect information according to control requirements to detect material quality includes: When the defect information meets the defect control criteria for good products, the material is detected as a good product; When the defect information meets the defect control criteria for defective products, the material is detected as a defective product. The defect control for good products and defective products are set according to product requirements. Example
[0028] like Figure 2 As shown, this invention provides an automated optical inspection system applied to the automated optical inspection method described in Example 1, comprising: A camera acquisition module is used to scan the material area to obtain the target defect range and record multiple scan data based on the target defect range. The data processing module is used to receive and process multiple scan data obtained from the camera acquisition module to detect the quality of the material.
[0029] In one specific embodiment of the present invention, the data processing module includes a preprocessing unit, a channel processing unit, a deviation processing unit, and a classification processing unit. The preprocessing unit is used to preprocess multiple scan data to obtain multiple sets of scan images; The channel processing unit is used to process multiple sets of scanned images into channels; The deviation processing unit is used to perform differential processing on the channelized image to obtain multiple sets of defect information; The classification and processing unit is used to classify and process multiple sets of defect information according to the control requirements to detect material quality.
[0030] In one specific embodiment of the present invention, optical detection is based on the automatic cutting and sorting device, wherein the automatic cutting and sorting device is equipped with a cutting device, mainly configured as a long strip cutting knife, which cuts the roll material at a fixed length during machine operation, and the first piece, the second piece, and the third piece are cut within the cutting range set by the material.
[0031] The following are six comparisons between general optical inspection and the optical inspection of this invention: A. The first case, such as Figure 3 As shown: The actual product defect is at the back cut of the first piece, and the general optical inspection record position is at the back cut of the first piece, with no defect omission; the optical inspection record of the present invention records three defects on the first and second pieces, which results in one more defective product than the actual product, with no defect omission.
[0032] B. The second scenario, such as Figure 4 As shown: The actual product defect is at the back cut of the first wafer, while the optical inspection record is usually located at the front cut of the second wafer, resulting in defect omission; the optical inspection record of this invention records three defects on the first and second wafers, resulting in one more defective product than the actual product, with no omissions.
[0033] C. The third scenario, such as Figure 5 As shown: The actual product defect is at the back cut of the first piece, while the general optical inspection record is located at the back cut of the first piece and the front cut of the second piece. This results in one more defective product being identified than the actual product, with no defect omissions. The optical inspection record of this invention shows three defects on the first and second pieces, resulting in one more defective product being identified than the actual product, with no defect omissions.
[0034] D. The fourth case, such as Figure 6 As shown: The actual product defects are at the rear cutter of slice one and the front cutter of slice two. The optical inspection record is usually located at the front cutter of slice two. The actual product is split in two, resulting in defect omission. The optical inspection record of this invention records three defects on slice one and slice two, which is consistent with the actual product judgment, and there is no defect omission.
[0035] E. The fifth case, such as Figure 7 As shown: The actual product defects are at the rear cut of wafer 1 and the front cut of wafer 2. The optical inspection record is usually located at the rear cut of wafer 1. The actual product is split in two, resulting in the omission of defects. The optical inspection record of this invention records three defects on wafer 1 and wafer 2, which is consistent with the judgment of the actual product, and there is no omission of defects.
[0036] In summary, the invention effectively avoids the risk of missing defects in the second, fourth, fifth, and sixth scenarios where defects are near the cutting edge. For the first and third scenarios, where general optical inspection does not typically result in missed defects, further measures are taken to ensure no risk of omission. Defects not located near the cutting edge do not pose a risk of omission. Specifically, the optical inspection method of this invention, based on multiple scanning imaging, expands the original defect judgment area, increasing the judgment range for individual defects. This effectively avoids omission problems caused by errors between the automatic optical inspection device and the actual product due to the oscillating wheel.
[0037] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.
Claims
1. An automatic optical inspection method, characterized in that, include: The material area is scanned using a camera acquisition module to obtain the target defect range, and multiple scan data are recorded based on the target defect range. The data processing module receives the multiple scan data and preprocesses them to obtain multiple sets of scan images; The multiple sets of scanned images are channelized, and the channelized images are then subjected to differential processing to obtain multiple sets of defect information. Multiple sets of defect information are classified and processed according to control requirements to detect material quality; The process of preprocessing multiple scan data to obtain multiple sets of scan images includes: The multiple scan data are periodically combined based on the scan frequency to obtain scan marker information; Based on the scanning marker information, the multiple scanning data are periodically arranged and combined to obtain multiple sets of scanning images; The channelized images are then subjected to differential processing to obtain multiple sets of defect information, including: The maximum deviation value is obtained, and the maximum deviation value is set based on actual production data collection. Based on the maximum deviation value, the scanning record coordinates of the channelized image are deviated to obtain multiple sets of defect information; The deviation of the scan recording coordinates of the channelized image includes: Among the scan coordinates of multiple sets of images, one set is determined as the reference coordinates; Centered on the reference coordinates, along the X-axis or Y-axis, the maximum deviation value is increased or decreased by multiples to serve as the scanning coordinates for the remaining groups.
2. The automatic optical inspection method according to claim 1, characterized in that, The method for obtaining the target defect range includes: Based on the camera acquisition module, the grayscale values of the material defect area are obtained; A detection threshold is obtained, which is set based on negligible defects on the material surface; The grayscale value of the material defect area is compared with the detection threshold. The material defect area that exceeds the detection threshold is identified as the target defect area.
3. The automatic optical inspection method according to claim 1, characterized in that, The process of classifying and processing multiple sets of defect information according to control requirements to detect material quality includes: When the defect information meets the defect control criteria for good products, the material is detected as a good product; When the defect information meets the defect control criteria for defective products, the material is detected as a defective product. The defect control for good products and defective products are set according to product requirements.
4. An automated optical inspection system, applied to the automated optical inspection method according to any one of claims 1-3, characterized in that, include: A camera acquisition module is used to scan the material area to obtain the target defect range and record multiple scan data based on the target defect range. The data processing module is used to receive and process multiple scan data obtained from the camera acquisition module to detect the quality of the material.
5. The automatic optical inspection system according to claim 4, characterized in that, The data processing module includes a preprocessing unit, a channel processing unit, a deviation processing unit, and a classification processing unit. The preprocessing unit is used to preprocess multiple scan data to obtain multiple sets of scan images; The channel processing unit is used to process multiple sets of scanned images into channels. The deviation processing unit is used to perform differential processing on the channelized image to obtain multiple sets of defect information; The classification and processing unit is used to classify and process multiple sets of defect information according to the control requirements to detect material quality.
Citation Information
Patent Citations
Camellia oleifera pest model training method and recognition method based on image analysis
CN110544237A
Additive manufacturing defect detection system based on double channels
CN111999254A
