Automatic optical detection method and device, storage medium and electronic terminal

Abstract

The invention discloses an automatic optical detection method and device, a storage medium and an electronic terminal.The automatic optical detection method comprises the steps that a material is scanned based on preset detection conditions of a camera and a light source, first defect information is obtained, and the first defect information comprises the area, the gray scale, the length, the width, the X position and the Y position of a defect; generating first defect labels according to feature classification, and integrating a first single defect information base; establishing a two-dimensional plane with the detection starting point, and generating a first defect distribution diagram according to the defect position and the first defect label; setting a screening condition from the single-defect information base according to a first defect label, calculating defect density and obtaining feature information; and resetting a detection condition and a classification condition according to the feature information, processing to obtain second defect information, establishing a second single defect information library, and generating a second defect distribution diagram. According to the method, the problems of low-contrast defect missing detection and non-key line over-detection are effectively solved, the classification error rate is obviously reduced, and the detection precision is greatly improved.

Description

Technical Field

[0001] This invention relates to the field of optical inspection technology, and specifically to an automatic optical inspection method, apparatus, storage medium, and electronic terminal. Background Technology

[0002] In the film material manufacturing industry, surface defect detection of materials such as polarizing film rolls is crucial; however, traditional manual inspection methods have significant limitations. Manual inspection can only sample the core and end of the roll, failing to achieve full roll inspection and making it difficult to assess the overall material quality. This leads to difficulties in timely feedback of anomalies during production, easily causing batch quality problems. Furthermore, film material defects are diverse, and some special defects require subsequent sampling or product delivery to the customer for confirmation of compliance. These defects are also not reproducible, and given the high pressure of roll production, rewinding and re-inspection are not applicable in the production environment. It's impossible to determine whether the defect can be specifically controlled subsequently, leading to continued undetected defects. Existing automated optical inspection equipment also has significant shortcomings. It lacks the function of resetting and processing detection conditions such as thresholds, gain, and filtering information for stored data of inspected products. Moreover, the organization of information on similar defects is too scattered, making it difficult to quickly summarize information, define defect characteristics, and classify and warn, inevitably causing economic losses. In addition, subsequent manual sheet sampling is unpredictable, and without warning labels, it is easy to miss defects, allowing defective products to reach the customer.

[0003] Therefore, how to solve problems such as detection omissions, over-detection, and classification errors through effective detection methods has become an urgent technical challenge. Summary of the Invention

[0004] The purpose of this invention is to address the above-mentioned problems by providing an automatic optical inspection method, apparatus, storage medium, and electronic terminal.

[0005] The technical solution of the present invention is as follows: an automatic optical inspection method, comprising the following steps: scanning material based on preset detection conditions of a camera and a light source to obtain first defect information, the first defect information including the area, grayscale, length, width, X position, and Y position of the defect; generating first defect labels according to feature classification and integrating a first single defect information database; establishing a two-dimensional plane with the detection starting point and generating a first defect distribution map according to the defect position and the first defect label; calculating the defect density and obtaining feature information from the single defect information database by setting screening conditions according to the first defect label; The detection and classification conditions are reset based on the feature information, and the second defect information is obtained. A second single defect information database is established and a second defect distribution map is generated.

[0006] As an improvement of this invention, a defect image is acquired based on preset detection conditions of the camera and light source, the gray value of the defect area is obtained from the defect image, the gray value is compared with a detection threshold, the area where the gray value exceeds the detection threshold is the target defect range, and the defect information within the target defect range is the first defect information.

[0007] As an improvement to an embodiment of the present invention, the "generating defect labels by feature classification and integrating a single defect information library" specifically includes: classifying the first defect information by feature of the area, gray level, length, width, X position and Y position to generate defect labels; and integrating the first defect information with the defect image to form a first single defect information library with defect labels as units.

[0008] As an improvement to an embodiment of the present invention, the step of “establishing a two-dimensional plane with the detection starting point and generating a first defect distribution map based on the defect location and the first defect label” specifically includes: establishing an XY two-dimensional plane with the material detection starting point, distributing the defects on the XY two-dimensional plane based on the X and Y positions of the defects and the first defect label, and generating a first defect distribution map with the surface of the detected material as the background.

[0009] As an improvement to an embodiment of the present invention, the step of "setting screening conditions according to the first defect label from the single defect information database, calculating defect density and obtaining feature information" specifically includes: screening according to the first defect label from the first single defect information database, using area or grayscale value as conditions, statistically analyzing the number of defects or the distribution density of feature parameters within a unit detection area, and obtaining feature information for each first defect label.

[0010] As an improvement to this embodiment of the invention, the step of "resetting the detection conditions and classification conditions based on the feature information, processing to obtain the second defect information, establishing a second single defect information database and generating a second defect distribution map" specifically includes: adjusting the detection threshold, gain parameter and defect filtering rules based on the feature information to reset the detection conditions and classification conditions, rescanning the material according to the reset detection conditions to obtain the second defect information, establishing a second single defect information database, and generating a second distribution map according to the defect location and second defect label in the second defect information.

[0011] As an improvement of this embodiment of the invention, the second single defect information database is independent of the first single defect information database.

[0012] To achieve one of the aforementioned objectives, one embodiment of the present invention provides an automatic optical inspection device, comprising the following modules: an information acquisition module, used to scan materials based on preset detection conditions of a camera and a light source, and acquire first defect information, the first defect information including the area, grayscale, length, width, X position, and Y position of the defect; an information database generation module, used to generate first defect labels according to feature classification, and integrate a first single defect information database; a first defect distribution map generation module, used to establish a two-dimensional plane with the detection starting point, and generate a first defect distribution map according to the defect location and the first defect label; a data processing module, used to set screening conditions according to the first defect label from the single defect information database, calculate the defect density, and obtain feature information; and a second defect distribution map generation module, used to reset the detection conditions and classification conditions according to the feature information, process to obtain second defect information, establish a second single defect information database, and generate a second defect distribution map.

[0013] To achieve one of the above-mentioned objectives, one embodiment of the present invention provides a storage medium storing program instructions, which, when executed, implement the automatic optical detection method as described in any of the preceding claims.

[0014] To achieve one of the above-mentioned objectives, one embodiment of the present invention provides an electronic terminal, including a processor and a memory, wherein the memory stores program instructions, and the processor executes the program instructions to implement the automatic optical detection method as described in any of the preceding claims.

[0015] The automatic optical inspection method, device, storage medium, and electronic terminal provided in this invention have the following advantages: This invention effectively solves the problems of missed detection of low-contrast defects and over-detection of non-critical textures by re-processing the initial inspection data by resetting parameters such as thresholds and gain; based on the classification of multi-dimensional features such as defect area, gray level, and aspect ratio, combined with defect density calculation, the classification error rate is significantly reduced; in terms of data, an independent second single defect information database is compared with the original data, supporting intuitive evaluation of the optimization effect of inspection conditions. Attached Figure Description

[0016] Figure 1 This is a schematic flowchart of the automatic optical detection method described in this invention; Figure 2 This is a distribution range diagram of defect information in the automatic optical inspection method described in this invention; Figure 3 It is the defect image described in this invention; Figure 4 This is a schematic diagram of the actual target defect range when the preset detection condition is A as described in this invention; Figure 5 This is a schematic diagram of the actual target defect range when the preset detection condition is B as described in this invention; Figure 6 This is a schematic diagram of the target defect range when the preset detection condition is A, as described in this invention. Figure 7 This is a schematic diagram of the target defect range when the preset detection condition is B, as described in this invention. Figure 8 This is a schematic diagram of the structure of the automatic optical inspection device described in this invention; Figure 9 This is a schematic diagram of the structure of the electronic terminal described in this invention. Detailed Implementation

[0017] The present invention will now be described in detail with reference to the specific embodiments shown in the accompanying drawings. However, these embodiments do not limit the present invention, and any structural, methodological, or functional modifications made by those skilled in the art based on these embodiments are included within the scope of protection of the present invention.

[0018] If the present invention involves orientation (e.g., up, down, left, right, front, back, outside, inside, etc.) when described, then the orientations involved need to be defined.

[0019] The scope of the embodiments described herein includes the entire scope of the claims and all available equivalents thereof. Throughout this document, the terms “first,” “second,” etc., are used only to distinguish one element from another without requiring or implying any actual relationship or order between the elements. Indeed, a first element can also be referred to as a second element, and vice versa. Furthermore, the terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that a structure, apparatus, or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a structure, apparatus, or device. Without further limitations, an element defined by the phrase “comprising one…” does not exclude the presence of other identical elements in the structure, apparatus, or device that includes said element. The various embodiments described herein are presented in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably.

[0020] The terms "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer" used in this document to indicate orientation or positional relationships are based on the orientation or positional relationships shown in the accompanying drawings and are used only for the convenience of describing this document and simplifying the description. They 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 limiting the invention. In the description herein, unless otherwise specified and limited, the terms "installed," "connected," and "linked" should be interpreted broadly. For example, they can refer to mechanical or electrical connections, or internal connections between two elements, or direct connections or indirect connections through an intermediate medium. Those skilled in the art can understand the specific meaning of the above terms according to the specific circumstances.

[0021] Embodiment 1 of the present invention provides an automatic optical detection method, such as... Figure 1 As shown, it includes the following steps: Step 101: Scan the material based on the preset detection conditions of the camera and light source to obtain the first defect information, which includes the area, gray level, length, width, X position and Y position of the defect; In practice, the area to be inspected of target materials such as films can be scanned based on preset detection conditions such as light source intensity, camera exposure parameters, and imaging resolution. During the scanning process, the camera captures optical signals from the material surface, and combined with the light-dark contrast formed by the illumination source, identifies defective areas with abnormalities and extracts key feature parameters of these areas. These parameters include the physical size information of the defect: area is the total pixel coverage of the defect area, length is the dimension along the longest axis of the defect, and width is the dimension along the shortest axis of the defect; the grayscale in the optical feature information represents the brightness difference between the defect area and the background; and the position information is determined by establishing an XY two-dimensional coordinate system based on the material surface to determine the X and Y position coordinates of the defect. The area, grayscale, length, width, X position, and Y position information of the defect form the initial first defect information, providing basic data for subsequent database construction and defect distribution image generation.

[0022] Step 102: Generate the first defect label according to feature classification and integrate the first single defect information database; Here, after obtaining the first defect information in step 101, the defects are classified according to their various characteristics, such as area, grayscale, length, and width. A corresponding first defect label is generated for each defect, and the label content matches the feature information of the defect. Then, all the information of these labeled individual defects is processed as follows: Figure 2The distribution ranges shown are integrated to form a first single-defect information database with each individual defect as an independent unit. This first single-defect information database can provide a complete description of each defect and can retrieve its corresponding overall features and classification labels based on the defect image information.

[0023] Step 103: Establish a two-dimensional plane with the detection starting point, and generate a first defect distribution map based on the defect location and the first defect label; In practice, firstly, an XY two-dimensional plane map is established based on the detection starting point of the target material. This plane map uses the surface of the object being detected as the background and corresponds to the actual physical area of ​​the material. Next, the X and Y position information of each defect, along with its corresponding first defect label, is extracted from a first single defect information database. All defects are then distributed according to their specific coordinates within the aforementioned XY two-dimensional plane, thus obtaining a first defect distribution map with the surface of the object being detected as the background. In this first defect distribution map, the defects can be presented as the defect image itself or as the first defect classification information corresponding to the defect image. Furthermore, through interactive operations, the complete descriptive information of the defects in the first single defect information database can be directly viewed.

[0024] Step 104: Calculate the defect density and obtain the feature information from the single defect information database by setting the filtering conditions according to the first defect label; Here, individual defect information is extracted from the first defect information database according to the first defect label. Then, using single features such as area, grayscale, length, and width as filtering conditions, the information density of different defect categories under the corresponding filtering conditions is calculated, thereby collecting and identifying the information features of different defects. During this process, the original information of the defect images is extracted from the first defect information database. This original information retains the original defect grayscale distribution and is the closest to the defect entity image detected by the automatic inspection machine. It can be used as initial data to perform multiple data processing operations such as thresholding and background filtering on the image, improving the overall detection and classification effect of defects. Figure 4 The image shows the actual detection area of ​​a defect under detection condition A. Figure 5 The image shows the actual detection area of ​​the same defect under detection condition B. By comparing the image processing effects of detection condition B and the original detection condition A, it can be seen that the detection under detection condition B is more complete and can better meet the actual needs of defect detection. It is understandable that by calculating the defect density and feature information under different conditions, data can be provided for the optimization of detection conditions.

[0025] Step 105: Reset the detection and classification conditions based on the feature information, process to obtain the second defect information, establish the second single defect information database, and generate the second defect distribution map.

[0026] In practice, based on the feature information of different defects collected in step 104, the detection conditions of the camera acquisition module and the light source module are readjusted, including threshold, gain, and filtering parameters, while the defect classification conditions are optimized. Based on the new detection and classification conditions, the original defect image is processed a second time to extract updated information such as defect area, grayscale, length, width, X position, and Y position, forming second defect information. Then, this second defect information is integrated into a second single-defect information database, with each defect as a unit. Preferably, the second single-defect database is independent of the first single-defect information database, enabling independent storage and retrieval of defect information. Following a similar approach to step 103, based on the XY two-dimensional plane established at the detection starting point, a second defect distribution map is generated according to the position information in the second defect information and the new classification labels. The second defect distribution map can present the defect distribution and classification after the second processing.

[0027] In this embodiment, a defect image is acquired based on preset detection conditions of the camera and light source. The gray value of the defect area is obtained from the defect image. The gray value is compared with a detection threshold. The area where the gray value exceeds the detection threshold is the target defect range. The defect information within the target defect range is the first defect information.

[0028] Here, the material is illuminated by a light source in the camera acquisition module. When defects exist on the material surface, the unevenness of the defective areas and the resulting differences in brightness will cause changes in the light intensity received by the camera, resulting in... Figure 3 The defect image shown is used to obtain different grayscale values ​​of the material defect area. Then, a detection threshold is set based on negligible defects on the material surface. The grayscale values ​​obtained after grayscale processing of the acquired defect image are compared with this detection threshold. If the grayscale value of a certain area exceeds the detection threshold, that area is determined to be the target defect range. Next, the defect information within the target defect range is extracted as the first defect information.

[0029] In this embodiment, the "generating defect labels by feature classification and integrating a single defect information library" specifically includes: classifying the first defect information by feature (area, grayscale, length, width, X position, and Y position) to generate defect labels; and integrating the first defect information with the defect image to form a first single defect information library based on defect labels.

[0030] In practice, the area, grayscale, length, width, X-defect location, and Y-defect location in the first defect information are used as feature parameters. A preset classification algorithm is used to classify the first defect information through threshold-based segmentation, cluster analysis, or machine learning models, generating a corresponding defect label for each defect. The parameters in the first defect information are associated and integrated with the corresponding original defect image that retains the grayscale distribution information to form a first single defect information library with defect labels as the index unit. The first single defect information library can realize a complete description and fast retrieval of each defect, and supports filtering and statistical analysis of defects by label.

[0031] In this embodiment, the step of "establishing a two-dimensional plane based on the detection starting point and generating a first defect distribution map based on the defect location and the first defect label" specifically includes: establishing an XY two-dimensional plane based on the material detection starting point, distributing the defects on the XY two-dimensional plane based on the X and Y positions of the defects and the first defect label, and generating a first defect distribution map with the surface of the detected material as the background.

[0032] Here, a two-dimensional XY plane coordinate system for defects is established with the starting point of material inspection as the origin, and the material surface is mapped onto this coordinate system. The X and Y position coordinates of each defect, along with its corresponding first defect label, are extracted from the first single-defect information database. Each defect is precisely located on the XY plane according to its coordinate values, and different visual identifiers are used based on the defect labels. These visual identifiers can be colors, shapes, or symbols, thereby generating a first defect distribution map that visually displays the distribution and classification of defects against the background of the inspected material surface. Preferably, the visual identifiers are colors, such as... Figure 6 As shown, in the defect information under detection condition A, the pink markings represent negligible background defects, while the blue markings represent target defects. Figure 6 A total of 15 defects were detected, including 8 actual defects in blue and 7 defects in pink background, with two of the background defects being defects. Understandably, the first defect distribution map visually presents the location and classification of the defects, completing the visualization of the initial detection results.

[0033] In this embodiment, the step of "setting filtering conditions according to the first defect label from the single defect information database, calculating defect density and obtaining feature information" specifically includes: filtering according to the first defect label from the first single defect information database, using area or grayscale value as conditions, statistically analyzing the number of defects or the distribution density of feature parameters within a unit detection area, and obtaining feature information for each first defect label.

[0034] Here, from the first defect information database, defect information of different label categories is extracted by filtering according to the first defect label; for each label category, the area or grayscale value is used as the filtering condition to map the filtered defects to a preset grid-like unit detection area; the number of defects that meet the conditions in each unit area is counted, or the distribution density of feature parameters is calculated, so as to obtain the feature information of each first defect label under specific filtering conditions.

[0035] In this embodiment, the step of "resetting the detection and classification conditions based on the feature information, processing to obtain the second defect information, establishing a second single defect information database and generating a second defect distribution map" specifically includes: adjusting the detection threshold, gain parameter and defect filtering rules based on the feature information to reset the detection and classification conditions, rescanning the material according to the reset detection conditions to obtain the second defect information, establishing a second single defect information database, and generating a second distribution map according to the defect location and second defect label in the second defect information.

[0036] In practice, such as Figure 7 As shown, in the defect information under detection condition B, there are a total of 10 defects. Those marked in blue and red are actual defects (10 in total), and those marked in orange are defects that were reclassified as actual defects from background defects. This is compared with... Figure 6 The cross-comparison of the first defect distribution map shows that two background defects were reclassified as actual defects. If the product is remanufactured, defect omissions can be effectively avoided, improving classification accuracy. Simultaneously, the second defect distribution map reduces the density of background defects, simplifies the interface, and helps increase personnel's awareness of problematic defects. Through secondary processing and result presentation, problems such as omissions, over-detection, and classification errors that may exist in the initial inspection can be effectively solved, further improving the accuracy of inspection. While ensuring complete defect detection, the intuitiveness of the interface is maintained, avoiding subsequent defect omissions due to the inability to re-inspect rolls and defect reproduction issues.

[0037] Embodiment 2 of the present invention provides an automatic optical inspection device, such as Figure 8 As shown, it includes the following modules: The information acquisition module 201 is used to scan the material based on the preset detection conditions of the camera and the light source to obtain the first defect information, which includes the area, gray level, length, width, X position and Y position of the defect. The information database generation module 202 is used to generate the first defect label according to feature classification and integrate the first single defect information database. The first defect distribution map generation module 203 is used to establish a two-dimensional plane with the detection starting point and generate a first defect distribution map based on the defect location and the first defect label. Data processing module 204 is used to calculate defect density and obtain feature information from the single defect information database according to the first defect label and set the filtering conditions; The second defect distribution map generation module 205 is used to reset the detection conditions and classification conditions based on the feature information, process the information to obtain the second defect information, establish the second single defect information database, and generate the second defect distribution map.

[0038] Embodiment 3 of the present invention provides a storage medium storing program instructions, which, when executed, implement the automatic optical detection method as described in any of the preceding embodiments.

[0039] Embodiment 4 of the present invention provides an electronic terminal, such as Figure 9 As shown, it includes a processor and a memory, the memory storing program instructions, and the processor executing the program instructions to implement the automatic optical detection method as described in any of the preceding claims.

[0040] This invention can be an apparatus, method, and / or computer program product. A computer program product may include a readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of the invention.

[0041] Storage media can be tangible devices that hold and store instructions for use by instruction execution devices. Storage media can include, but are not limited to, electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination thereof.

[0042] It should be understood that although this specification describes embodiments, not every embodiment contains only one independent technical solution. This way of describing the specification is only for clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art.

[0043] The detailed descriptions listed above are merely specific descriptions of feasible embodiments of the present invention, and are not intended to limit the scope of protection of the present invention. All equivalent embodiments or modifications made without departing from the spirit of the present invention should be included within the scope of protection of the present invention.

Claims

1. An automatic optical inspection method, characterized in that, Includes the following steps: The material is scanned based on preset detection conditions of the camera and light source to obtain first defect information, which includes the area, gray level, length, width, X position and Y position of the defect. Generate the first defect label based on feature classification and integrate the first single defect information database; A two-dimensional plane is established based on the detection starting point, and a first defect distribution map is generated based on the defect location and the first defect label. Based on the single defect information database, filter conditions are set according to the first defect label, and defect density is calculated to obtain feature information; The detection and classification conditions are reset based on the feature information, and the second defect information is obtained. A second single defect information database is established and a second defect distribution map is generated.

2. The automatic optical inspection method according to claim 1, characterized in that, Defect images are acquired based on preset detection conditions of the camera and light source. The grayscale value of the defect area is obtained from the defect image. The grayscale value is compared with a detection threshold. The area where the grayscale value exceeds the detection threshold is the target defect range. The defect information within the target defect range is the first defect information.

3. The automatic optical inspection method according to claim 2, characterized in that, The "generating defect labels by feature classification and integrating a single defect information database" specifically includes: classifying the first defect information by using the area, grayscale, length, width, X position, and Y position of the first defect information as features to generate defect labels; and integrating the first defect information with the defect image to form a first single defect information database based on defect labels.

4. The automatic optical inspection method according to claim 1, characterized in that, The phrase "establishing a two-dimensional plane based on the detection starting point and generating a first defect distribution map based on the defect location and the first defect label" specifically includes: establishing an XY two-dimensional plane based on the material detection starting point, distributing the defects on the XY two-dimensional plane based on the X and Y positions of the defects and the first defect label, and generating a first defect distribution map with the surface of the detected material as the background.

5. The automatic optical inspection method according to claim 1, characterized in that, The phrase "setting filtering conditions according to the first defect label from the single defect information database, calculating defect density and obtaining feature information" specifically includes: filtering according to the first defect label from the first single defect information database, using area or grayscale value as conditions, statistically analyzing the number of defects or the distribution density of feature parameters within a unit detection area, and obtaining feature information for each first defect label.

6. The automatic optical inspection method according to claim 1, characterized in that, The phrase "resetting detection and classification conditions based on feature information, processing to obtain second defect information, establishing a second single defect information database, and generating a second defect distribution map" specifically includes: adjusting the detection threshold, gain parameter, and defect filtering rules based on the feature information to reset the detection and classification conditions; rescanning the material according to the reset detection conditions to obtain second defect information; establishing a second single defect information database; and generating a second distribution map according to the defect location and second defect label in the second defect information.

7. The automatic optical inspection method according to claim 1, characterized in that, The second single defect information database is independent of the first single defect information database.

8. An automatic optical inspection device, applied to the automatic optical inspection method according to any one of claims 1-6, characterized in that, include: The information acquisition module is used to scan the material based on preset detection conditions of the camera and light source to obtain first defect information, which includes the area, gray level, length, width, X position and Y position of the defect. The information database generation module is used to generate the first defect label according to feature classification and integrate the first single defect information database. The first defect distribution map generation module is used to establish a two-dimensional plane with the detection starting point and generate a first defect distribution map based on the defect location and the first defect label. The data processing module is used to calculate the defect density and obtain feature information from the single defect information database according to the first defect label and the set filtering conditions. The second defect distribution map generation module is used to reset the detection and classification conditions based on the feature information, process the information to obtain the second defect information, establish the second single defect information database, and generate the second defect distribution map.

9. A storage medium storing program instructions, characterized in that, When the program instructions are executed, the automatic optical detection method as described in any one of claims 1 to 7 is implemented.

10. An electronic terminal, characterized in that, It includes a processor and a memory, the memory storing program instructions, and the processor executing the program instructions to implement the automatic optical detection method as described in any one of claims 1 to 7.

Images