Electronic component defect detection method and system based on machine vision

Abstract

The invention belongs to the technical field of image analysis, and particularly relates to an electronic component defect detection method and system based on machine vision, and the method comprises the following steps: S1, obtaining visible light, X-ray and three-dimensional structured light images of an electronic component to be detected, and generating respective multi-scale feature pyramids through independent feature extraction networks; s2, generating a multi-modal fusion feature pyramid; s3, applying a candidate region generation network to propose a candidate defect region; s4, processing the spatial topological relation graph through a graph neural network, and embedding spatial context information into candidate defect region features; and S5, if the minimum distance between the candidate region features and all the pre-stored prototypes is greater than a set discrimination threshold, determining that the candidate region is a potential defect of an unknown type. According to the method, the detection range is widened, the robustness of feature expression is improved, the limitation of insufficient information of a single data source is overcome, and the accuracy, comprehensiveness and perspectiveness of detection are improved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of image analysis, and particularly relates to a machine vision-based electronic component defect detection method and system. BACKGROUND

[0002] In the field of modern electronic manufacturing, with the increasing integration and complexity of components, the detection requirements for product quality are becoming increasingly stringent. Traditional defect detection mainly relies on manual visual inspection, which is inefficient, costly, and the detection results are easily affected by subjective factors, making it difficult to meet the needs of large-scale, high-precision automated production lines. Therefore, automatic optical inspection (AOI) technology based on machine vision has emerged and been applied. Early automatic optical inspection technology mostly uses traditional image processing algorithms such as template matching, edge detection, and threshold segmentation. Although these methods achieve a certain degree of automation, they have poor robustness to problems such as light changes, background noise, and defect morphology diversity, and require a large number of manual rule settings, with limited generalization ability. In recent years, deep learning technology represented by convolutional neural networks (CNN) has made breakthroughs in image recognition and has been introduced into electronic component defect detection, significantly improving the accuracy and automation level of detection. However, most existing deep learning detection schemes still have limitations. They usually rely only on a single visible light two-dimensional image, and cannot effectively detect internal solder defects (such as BGA virtual soldering, bubbles) or abnormalities on three-dimensional structures (such as component warping, poor coplanarity of pins).

[0003] To overcome the shortcomings of single modal information, some studies have begun to explore multi-modal data fusion detection methods. For example, visible light and X-ray images are combined to cover both surface and internal defects. However, existing fusion strategies are relatively primitive, mostly using simple feature concatenation or pixel-by-pixel addition, which cannot fully exploit and utilize the deep correlations and complementary information between different modal data, resulting in poor fusion results. In addition, in the defect positioning and identification process, existing methods also have some bottlenecks: first, general object detection networks do not optimize for the elongated and irregular shape characteristics of electronic defects when generating candidate boxes, resulting in low positioning accuracy; second, detection models usually analyze each candidate region as an independent individual, ignoring the spatial topological relationship between the defect and the key functional unit (such as chip pins, pads) it is in, which is crucial for judging the actual harmfulness of the defect; third, classifiers are mostly trained to identify a predefined, closed set of defect categories. When new, unknown types of defects appear on the production line, the system often misjudges them as known categories or directly misses them, lacking the ability to discover and warn new patterns, which poses a challenge to ensuring product quality stability throughout the life cycle. SUMMARY

[0004] The present invention provides a method and system for electronic component defect detection based on machine vision to solve the technical problems of modal limitations and identification defects in deep learning detection methods in the prior art.

[0005] In a first aspect, the present invention provides a method for detecting electronic component defects based on machine vision, comprising the following steps: S1, obtains visible light, X-ray and 3D structured light images of the electronic component to be tested, and generates their own multi-scale feature pyramids through independent feature extraction networks; S2, between the corresponding levels of the multi-scale feature pyramid, the correlation weights between the three image features of visible light, X-ray and 3D structured light are calculated through the cross-modal self-attention module, and the image features are weighted fused accordingly to generate a multi-modal fusion feature pyramid; S3, at each level of the multimodal fusion feature pyramid, a candidate region generation network is applied to propose candidate defect regions. The loss function of the candidate region generation network includes shape prior loss to constrain the geometric features of the candidate box to prioritize matching typical defect shapes; S4: Construct a spatial topological relationship graph based on the coordinates of all candidate defect regions and preset key functional units, where all candidate defect regions and preset key functional units are nodes and their spatial proximity relationships are edges. The spatial topological relationship graph is processed through a graph neural network to embed spatial context information into the features of the candidate defect regions. S5, input the candidate region features embedded with spatial context information into the prototype network classifier, and complete the classification by calculating the distance between the candidate region features and the pre-stored prototypes of each known defect category and the normal region prototype; if the minimum distance between the candidate region features and all pre-stored prototypes is greater than the set discrimination threshold, the candidate region will be judged as a potential defect of unknown type.

[0006] Furthermore, S1 includes the following steps: For each image type of visible light, X-ray, and three-dimensional structured light, an encoder with ResNet as the backbone network is independently used for feature extraction, and feature maps are extracted from the output of different stages of the backbone network to construct a multi-scale feature pyramid under each image type.

[0007] Furthermore, S2 includes the following steps: At any corresponding level of the multi-scale feature pyramid, the feature maps of visible light, X-ray and 3D structured light images are spliced ​​along the channel dimension to form a combined feature map; The combined feature map is input into the cross-modal self-attention module, which adaptively calculates the attention weights in the spatial dimension and channel dimension, and recalibrates the combined feature map to enhance key information and suppress redundant information, thereby generating the fusion features of this level.

[0008] Furthermore, S3 includes the following steps: Predefine a set of prior anchor box aspect ratios representing typical defect morphologies; During the training process, for each candidate box output by the candidate region generation network, the generalized intersection-union (GIU) of the candidate box and all prior anchor boxes is calculated; the maximum GIU value is selected, and 1 minus the maximum GIU value is used as the shape prior loss, which is then added to the total loss function of the candidate region generation network.

[0009] Furthermore, the total loss function is the sum of classification loss, bounding box regression loss, and shape prior loss.

[0010] Furthermore, S4 includes the following steps: Each candidate defect region and its feature vector are defined as a defect node; The location and category information of each preset key functional unit is defined as a key functional unit node; When the Euclidean distance between the center points of the entities represented by the defective node and the key functional unit node is less than a preset threshold, an edge is established between the defective node and the key functional unit node to represent their spatial proximity relationship.

[0011] Furthermore, the key functional unit includes a chip and a capacitor.

[0012] Furthermore, in S5, classification by the prototype network classifier includes the following steps: in the training phase, for each known category, the mean of the feature vectors output by the graph neural network of all training samples in the category is taken as the central prototype of the category; In the inference phase, the Euclidean distance between the feature vector of the candidate region and each central prototype is calculated, and the candidate region is classified into the category corresponding to the central prototype with the smallest distance.

[0013] Furthermore, determining the candidate region as a potential defect of unknown type includes the following steps: Calculate the minimum distance D between the candidate region features and all pre-stored prototypes min ; D min Compare with the set discrimination threshold T, where the discrimination threshold T is determined based on the distance distribution between all correctly classified samples in the validation set and their corresponding category prototypes; If D minIf greater than T, mark the candidate region as a ''potential defect of unknown type''.

[0014] In a second aspect, the present application provides a machine vision-based electronic component defect detection system, comprising a memory and a processor, wherein the memory stores computer program instructions which, when executed by the processor, implement the machine vision-based electronic component defect detection method described above.

[0015] The beneficial effects are: the present application can comprehensively detect the surface, internal and three-dimensional topography defects of electronic components by fusing the data of three modalities of visible light, X-ray and three-dimensional structured light, and using cross-modal self-attention mechanism for feature fusion, which widens the detection range and improves the robustness of feature expression, and overcomes the limitations of insufficient information of a single data source. By introducing shape prior loss in the candidate region generation network, the defects of special shapes such as elongated and irregular can be more accurately located. The spatial topological relationship between the defects and the key functional units is analyzed by using the graph neural network, and the spatial context information is integrated into the classification decision, reducing the misjudgment caused by isolated analysis. The prototype network classifier is used, which not only improves the classification accuracy of known defects, but also gives the system the ability to identify and warn potential defects of unknown types, enhances the ability to find new problems in complex and variable production environments, and improves the accuracy, comprehensiveness and forward-looking of the detection. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 Flowchart of the machine vision-based electronic component defect detection method; Figure 2 Schematic diagram of feature extraction; Figure 3 Structural block diagram of the machine vision-based electronic component defect detection system. DETAILED DESCRIPTION

[0017] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present application, and those skilled in the art should know that the embodiments described below are part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of the present application.

[0018] Embodiments of the machine vision-based electronic component defect detection method provided by the present application: As shown in Figure 1 and Figure 2 The machine vision-based electronic component defect detection method comprises the following steps: S1, acquiring visible light, X-ray and three-dimensional structured light images of the electronic component to be tested, and generating respective multi-scale feature pyramids through independent feature extraction networks.

[0019] In an optional embodiment, S1 includes the following steps: for each image type of visible light, X-ray and three-dimensional structured light, independently using an encoder with a ResNet backbone network for feature extraction, and extracting feature maps from the output of different stages of the backbone network to construct a multi-scale feature pyramid for the image type.

[0020] Specifically, taking a printed circuit board assembly to be tested as an example, a visible light color image with a resolution of 1024x1024 pixels is collected, which is used to identify surface color abnormalities (such as blackened solder joints); an X-ray grayscale image with the same resolution is collected, which is used to detect internal structural defects (such as air bubbles); a three-dimensional structured light image with the same resolution generated by structured light scanning is collected, which is used to measure the height or flatness of the component. The three images are respectively input into three independent feature extraction networks based on the ResNet-50 architecture.

[0021] Within each ResNet-50 network, the feature extraction process goes through multiple convolution stages. Feature maps are extracted from the output of the second, third, fourth, and fifth residual block groups, i.e., C2, C3, C4, and C5 stages. For example, for the visible light color image, the feature map output by the C2 stage has a high resolution, retaining fine texture details, which is suitable for detecting small scratches; while the feature map output by the C5 stage has a lower resolution, but has a larger receptive field and more semantic information, which is suitable for identifying the absence of the entire printed circuit board assembly. The four feature maps of different scales together form a feature pyramid for the visible light image. The same process is applied to the X-ray grayscale image and the three-dimensional structured light image, ultimately generating three independent multi-scale feature pyramids that can represent information from details to the global.

[0022] S2, through the cross-modal self-attention module, the correlation weights between the features of the visible light, X-ray and three-dimensional structured light images are calculated at the corresponding levels of the multi-scale feature pyramids, and the image features are weighted and fused accordingly to generate a multi-modal fusion feature pyramid.

[0023] In an optional embodiment, in S2, at any corresponding level of the multi-scale feature pyramid, the feature maps of the visible light, X-ray and three-dimensional structured light images are concatenated along the channel dimension to form a combined feature map; the combined feature map is input into the cross-modal self-attention module, which adaptively calculates the attention weights in the spatial and channel dimensions, and recalibrates the combined feature map to enhance key information and suppress redundant information, thereby generating the fusion feature at this level.

[0024] Specifically, assuming that in the third level of the multi-scale feature pyramid, the feature map size of visible light, X-ray and three-dimensional structured light images are all 64x64 pixels, and the number of channels are all 256. The three feature maps are spliced along the channel dimension to form a combined feature map with a size of 64x64 pixels and a channel number of 768. The combined feature map is sent to the cross-modal self-attention module, which contains two branches of spatial attention and channel attention.

[0025] For example, when detecting an internal cavity of a blocked BGA solder joint, the channel attention branch will learn to give higher weights to the channels corresponding to the X-ray image, i.e., channels 257 to 512, while reducing the weight of the visible light image channel because its surface information is irrelevant. At the same time, the spatial attention branch will locate to the spatial region where the BGA is located and increase the attention score of all pixel points in this spatial region. By multiplying the attention weights in these two dimensions with the original combined feature map, the cross-modal self-attention module finally outputs a re-scaled fusion feature map, in which the multi-modal information most relevant to BGA cavity detection is significantly enhanced, while irrelevant background or noise information is effectively suppressed.

[0026] S3, in each level of the multi-modal fusion feature pyramid, a candidate region generation network is applied to propose candidate defect regions, and a shape prior loss is included in the loss function of the candidate region generation network to constrain the geometric features of the candidate box to preferentially match the typical defect morphology.

[0027] In an optional embodiment, in S3, a set of prior anchor box aspect ratios representing typical defect morphologies (such as bars, circles, squares) are predefined; during training, for each candidate box output by the candidate region generation network, the generalized intersection over union (GIoU) of the candidate box and all prior anchor boxes is calculated; the maximum GIoU value is selected, and 1 minus the maximum GIoU value is taken as the shape prior loss, which is added to the total loss function of the candidate region generation network, i.e., in addition to the standard classification loss and bounding box regression loss, the shape prior loss is additionally added to the total loss function.

[0028] Specifically, according to statistical analysis of historical defect data, a set of prior anchor box aspect ratios are predefined, for example, 1:5 and 5:1 represent elongated scratches or solder bridges, 1:1 represents pinholes or the offset of square patch elements, and 2:3 and 3:2 represent common rectangular capacitors or resistors. The aspect ratios of this set of prior anchor boxes are fixed as guidance information.

[0029] In network training, assuming that the candidate region generation network predicts a candidate box with a width of 20 pixels and a height of 25 pixels for a real existing bar scratch defect. The aspect ratio of the candidate box is close to 1:1, and the generalized intersection over union calculated with the 1:5 aspect ratio of the prior anchor box can only be 0.3, while the generalized intersection over union calculated with the 1:1 prior anchor box is 0.8. At this time, the maximum generalized intersection over union value selected is 0.8, and the shape prior loss is 1-0.8=0.2. This loss value will punish the candidate region generation network through back propagation, prompting the candidate region generation network to adjust the parameters in subsequent iterations to generate a candidate box closer to the 1:5 aspect ratio to match the real shape of the bar scratch. By adding the shape prior loss term to the total loss function, the model is guided to generate a prediction box with a geometric shape closer to the actual defect shape.

[0030] S4, a spatial topology relationship graph is constructed with all candidate defect regions and preset key functional unit coordinates as nodes, and their spatial proximity as edges; the spatial context information is embedded into the candidate defect region features by processing the spatial topology relationship graph through a graph neural network.

[0031] In an optional embodiment, in S4, each candidate defect region and its feature vector are defined as a defect node; the position and category information of each preset key functional unit (such as a chip or a capacitor) are defined as a key functional unit node; when the Euclidean distance between the center points of the entities represented by the defect node and the key functional unit node is less than a preset threshold, an edge is established between the defect node and the key functional unit node to represent their spatial proximity.

[0032] Specifically, assuming that a candidate defect region D1 is detected on a circuit board, with a center coordinate of (150, 200), and a 128-dimensional feature vector is extracted. At the same time, it is known from the design file of the circuit board that the center coordinate of a key chip IC1 is (160, 210) and the center coordinate of a capacitor C1 is (300, 400). D1, IC1 and C1 are all defined as nodes in the spatial topology relationship graph. The preset threshold for judging spatial proximity is 50 pixels.

[0033] The Euclidean distance between the center points of D1 and IC1 is calculated as Pixels. Since 14.14 is less than the threshold 50, an edge is established between the D1 node and the IC1 node. Then the distance between D1 and the center of C1 is calculated, which is much larger than 50 pixels, so no connection is established between D1 and C1. Through this process, the spatial topological graph encodes the important spatial context information that the defect D1 is close to the chip IC1, and is irrelevant to the distant capacitor C1. This graph is then input into the graph neural network to learn the relevance of the defect and its surrounding environment.

[0034] S5, input the candidate region feature embedded with spatial context information into the prototype network classifier, and complete classification by calculating the distance between the candidate region feature and the pre-stored center prototype of each known defect category and the normal region prototype; if the minimum distance between the candidate region feature and all pre-stored prototypes is greater than the set discrimination threshold, it is determined that the candidate region is a potential defect of unknown type.

[0035] In an optional embodiment, in S1, the classification by the prototype network classifier includes the following steps: in the training stage, for each known category (including the normal category and N known defect categories), the mean of the feature vectors output by the graph neural network for all training samples of the category is taken as the center prototype of the category; in the inference stage, the Euclidean distance between the feature vector of the candidate region and each center prototype is calculated, and the candidate region is classified into the category corresponding to the center prototype with the smallest distance.

[0036] Specifically, in the training stage, it is assumed that there are three known categories: normal, tin bead defect, and element offset defect. For the tin bead defect category, 1000 samples of this category are processed, and each sample is processed by the graph neural network to obtain a 256-dimensional feature vector. The 1000 256-dimensional feature vectors are averaged element by element to obtain a single 256-dimensional vector, which becomes the center prototype representing the tin bead defect category. Similarly, the center prototypes of the normal category and the element offset defect category are also calculated. The three prototype vectors belonging to different categories are stored for later use.

[0037] In the inference stage, a candidate region to be tested is processed through the entire network to generate a 256-dimensional feature vector. At this time, the Euclidean distances between the to-be-tested feature vector and the three stored center prototypes need to be calculated. For example, the calculated distances are: the distance to the normal category prototype is 8.2, the distance to the tin bead defect category prototype is 1.5, and the distance to the element offset defect category prototype is 6.7. Since 1.5 is the smallest of the three distances, the candidate region is finally classified as a tin bead defect.

[0038] In an optional embodiment, the steps of determining a candidate region as an unknown type potential defect include: calculating the minimum distance D between the feature of the candidate region and all pre-stored prototypes (including the normal category prototype and the known defect category prototypes) min ; comparing D min with a set of discrimination threshold T, wherein the discrimination threshold T is determined according to the distance distribution of all correctly classified samples and their corresponding category prototypes on the validation set (for example, taking the 95th percentile of the distribution); if D min is greater than T, the candidate region is marked as an “unknown type potential defect”.

[0039] Specifically, the determination process of the discrimination threshold T is as follows: using an independent validation data set (containing samples of all known categories), for each sample correctly classified by the model in the validation set, calculate the Euclidean distance between its feature vector and the prototype of the category it belongs to. For example, a sample correctly identified as a tin bead defect has a distance of 1.3 between its feature vector and the tin bead defect category prototype. Collect the distance values of all these correctly classified samples to form a distance distribution, and take the 95th percentile of the distance distribution as the threshold (assuming that the calculated T is equal to 4.5).

[0040] In actual detection, if a previously unseen defect type (such as circuit board substrate delamination) is encountered, the defect will generate a corresponding feature vector after being processed by the graph neural network. Calculate the Euclidean distance between the feature vector and all known category prototypes (including the normal category prototype, the tin bead defect category prototype, and the component offset defect category prototype). The minimum distance D min = 5.8 is calculated, which is the distance between it and the most similar known category, such as the component offset defect type prototype. Because 5.8 is greater than the preset threshold T = 4.5, it indicates that the sample is far away from all known category centers in the feature space. Therefore, it will not be misclassified as any known defect, but will be marked as an “unknown type potential defect” and reported to the engineer for manual analysis and confirmation.

[0041] Embodiments of the electronic component defect detection system based on machine vision provided by the present application: As Figure 3 shown, the electronic component defect detection system based on machine vision includes a processor and a memory, the memory stores computer program instructions, when the computer program instructions are executed by the processor, the above-mentioned electronic component defect detection method based on machine vision is realized.

[0042] The electronic component defect detection system based on machine vision also includes a communication interface and other components familiar to those skilled in the art, the settings and functions of which are known in the art, and therefore will not be described here.

[0043] In the present invention, the aforementioned memory can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, the computer-readable storage medium can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc., or any other medium that can be used to store the required information and can be accessed by an application, module, or both. Any such computer storage medium can be part of, accessible to, or connectable to a device. Any application or module described in the present invention can be implemented using computer-readable / executable instructions stored or otherwise maintained by such a computer-readable medium.

[0044] In addition, in the description of this specification, “a plurality of” means at least two, for example, two, three or more, etc., unless otherwise clearly and specifically defined.

Claims

1. A method for detecting defects in electronic components based on machine vision, characterized in that: The following steps are involved: S1, obtains visible light, X-ray and 3D structured light images of the electronic component to be tested, and generates their own multi-scale feature pyramids through independent feature extraction networks; S2, between the corresponding levels of the multi-scale feature pyramid, the correlation weights between the three image features of visible light, X-ray and 3D structured light are calculated through the cross-modal self-attention module, and the image features are weighted fused accordingly to generate a multi-modal fusion feature pyramid; S3, at each level of the multimodal fusion feature pyramid, a candidate region generation network is applied to propose candidate defect regions. The loss function of the candidate region generation network includes shape prior loss to constrain the geometric features of the candidate box to prioritize matching typical defect shapes; S4: Construct a spatial topological relationship graph based on the coordinates of all candidate defect regions and preset key functional units, where all candidate defect regions and preset key functional units are nodes and their spatial proximity relationships are edges. The spatial topological relationship graph is processed through a graph neural network to embed spatial context information into the features of the candidate defect regions. S5, input the candidate region features embedded with spatial context information into the prototype network classifier, and complete the classification by calculating the distance between the candidate region features and the pre-stored prototypes of each known defect category and the normal region prototype; if the minimum distance between the candidate region features and all pre-stored prototypes is greater than the set discrimination threshold, the candidate region will be judged as a potential defect of unknown type.

2. The method for detecting electronic component defects based on machine vision according to claim 1, wherein: S1 includes the following steps: For each image type of visible light, X-ray, and three-dimensional structured light, an encoder with ResNet as the backbone network is independently used for feature extraction, and feature maps are extracted from the output of different stages of the backbone network to construct a multi-scale feature pyramid under each image type.

3. The electronic component defect detection method based on machine vision according to claim 1, characterized in that: S2 includes the following steps: At any corresponding level of the multi-scale feature pyramid, the feature maps of visible light, X-ray, and 3D structured light images are spliced ​​along the channel dimension to form a combined feature map; The combined feature map is input into the cross-modal self-attention module, which adaptively calculates the attention weights in the spatial dimension and channel dimension, and recalibrates the combined feature map to enhance key information and suppress redundant information, thereby generating the fusion features of this level.

4. The method for detecting electronic component defects based on machine vision according to claim 1, wherein: S3 includes the following steps: Predefine a set of prior anchor box aspect ratios representing typical defect morphologies; During the training process, for each candidate box output by the candidate region generation network, the generalized intersection-union (GIU) of the candidate box and all prior anchor boxes is calculated; the maximum GIU value is selected, and 1 minus the maximum GIU value is used as the shape prior loss, which is then added to the total loss function of the candidate region generation network.

5. The method for detecting electronic component defects based on machine vision according to claim 4, characterized in that: The total loss function is the sum of classification loss, bounding box regression loss, and shape prior loss.

6. The method for detecting electronic component defects based on machine vision according to claim 1, wherein: S4 includes the following steps: Each candidate defect region and its feature vector are defined as a defect node; The location and category information of each preset key functional unit is defined as a key functional unit node; When the Euclidean distance between the center points of the entities represented by the defective node and the key functional unit node is less than a preset threshold, an edge is established between the defective node and the key functional unit node to represent their spatial proximity relationship.

7. The method for detecting electronic component defects based on machine vision according to claim 6, wherein: The key functional units include chips and capacitors.

8. The method for detecting electronic component defects based on machine vision according to any one of claims 1 to 7, characterized in that: In S5, classification by the prototype network classifier includes the following steps: During the training phase, for each known category, the mean of the feature vectors output by the graph neural network of all training samples in that category is taken as the central prototype of that category; In the inference phase, the Euclidean distance between the feature vector of the candidate region and each central prototype is calculated, and the candidate region is classified into the category corresponding to the central prototype with the smallest distance.

9. The method for detecting electronic component defects based on machine vision according to claim 8, characterized in that: The following steps are involved in determining a candidate area as a potential defect of unknown type: Calculate the minimum distance D between the candidate region features and all pre-stored prototypes min ; D min Compare with the set discrimination threshold T, where the discrimination threshold T is determined based on the distance distribution between all correctly classified samples in the validation set and their corresponding category prototypes; If D min If it is greater than T, the candidate region is marked as a “potential defect of unknown type”.

10. An electronic component defect detection system based on machine vision, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the method for detecting electronic component defects based on machine vision according to any one of claims 1 to 9 is implemented.

Images