CN112950560A - Electronic component defect detection method, device and system - Google Patents
Electronic component defect detection method, device and system Download PDFInfo
- Publication number
- CN112950560A CN112950560A CN202110195319.4A CN202110195319A CN112950560A CN 112950560 A CN112950560 A CN 112950560A CN 202110195319 A CN202110195319 A CN 202110195319A CN 112950560 A CN112950560 A CN 112950560A
- Authority
- CN
- China
- Prior art keywords
- defect
- electronic component
- image
- detected
- defect detection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000007547 defect Effects 0.000 title claims abstract description 360
- 238000001514 detection method Methods 0.000 title claims abstract description 126
- 238000000034 method Methods 0.000 claims abstract description 61
- 238000004364 calculation method Methods 0.000 claims abstract description 58
- 238000012549 training Methods 0.000 claims description 64
- 229910000679 solder Inorganic materials 0.000 claims description 39
- 239000011800 void material Substances 0.000 claims description 22
- 238000012360 testing method Methods 0.000 claims description 21
- 238000010586 diagram Methods 0.000 claims description 13
- 238000003860 storage Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 230000002950 deficient Effects 0.000 claims description 6
- 238000002372 labelling Methods 0.000 claims description 6
- 238000004806 packaging method and process Methods 0.000 claims description 6
- 229910052710 silicon Inorganic materials 0.000 claims description 4
- 239000010703 silicon Substances 0.000 claims description 4
- 239000000126 substance Substances 0.000 claims description 4
- 238000003384 imaging method Methods 0.000 claims description 3
- 238000003475 lamination Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 238000007689 inspection Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 239000013598 vector Substances 0.000 description 6
- 238000013527 convolutional neural network Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000011796 hollow space material Substances 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012536 packaging technology Methods 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 230000000750 progressive effect Effects 0.000 description 2
- 108010001267 Protein Subunits Proteins 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005670 electromagnetic radiation Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
- 238000003466 welding Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Library & Information Science (AREA)
- Databases & Information Systems (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The disclosure relates to a method, a device and a system for detecting defects of electronic components. In one embodiment of the method, the defects of the electronic components can be automatically detected, the defect detection result is output, and the defect detection speed of the electronic components can be improved. In addition, in the disclosed embodiment, different defect types are identified by adopting a defect detection model during defect detection, and a more matched defect size calculation mode is selected for different defect types, so that the defect size calculation can realize quantitative calculation of a defect area, the misjudgment can be reduced, and the detection accuracy of the defects of the electronic components can be improved.
Description
Technical Field
The present disclosure relates to the field of electronic component detection technologies, and in particular, to a method, an apparatus, and a system for detecting defects of an electronic component.
Background
The defect detection of electronic components is a necessary production process for ensuring the quality of the components, but along with the continuous development of the processing and manufacturing level of the electronic components, the packaging forms of the electronic components are more and more, the packaging density is higher and more, and the types and the number of the detected electronic components are increased increasingly.
In the related art, electronic component defect detection usually relies on manual detection. However, manual detection has strong subjectivity and high cost, and the accuracy and speed of manual detection cannot meet the industrial requirements. Therefore, a technical scheme for efficiently and accurately detecting the defects of the electronic components is needed.
Disclosure of Invention
In view of the above, it is necessary to provide a method, an apparatus and a system for detecting defects of electronic components.
A method for detecting defects of electronic components, the method comprising:
acquiring an image of an electronic component to be detected;
inputting the image into a defect detection model obtained by training to obtain the defect type of the electronic component to be detected; the defect detection model is obtained based on the constructed good product gallery and the defect gallery through training;
determining a defect size calculation mode of the electronic component to be detected according to the defect type;
and performing defect calculation on the image by using the defect size calculation mode, and determining a defect detection result of the electronic component to be detected according to the calculation result.
In one embodiment, when it is determined that the defect area calculation is required according to the defect type, performing defect calculation on the image by using the defect size calculation method, and determining the defect detection result of the electronic component to be detected according to the calculation result includes:
extracting a defect area in the image and calculating the defect area;
and when the defect area is larger than a preset defect threshold value, determining that the electronic component to be detected is an unqualified product.
In one embodiment, the defect type includes at least one of the following defects: redundancy, silicon through hole cavities, lamination packaging cavities, solder ball cavities and bonding cavities.
In one embodiment, when the defect type is a solder ball void defect, if the electronic component has at least one solder ball void area, the proportion is greater than a preset defect threshold, and the electronic component is determined to be an unqualified product.
In one embodiment, the proportion of the solder ball void area comprises: the ratio of the sum of all the hollow areas on a single solder ball to the area of the solder ball.
In one embodiment, when it is determined that the defect length calculation is required according to the defect type, the defect calculation is performed on the image by using the defect size calculation method, and the defect detection result of the electronic component to be detected is determined according to the calculation result, including:
extracting a defect area in the image and calculating the defect length;
and when the defect length is larger than a preset defect threshold value, determining that the electronic component to be detected is an unqualified product.
In one embodiment, the defect type includes at least one of the following defects: chip cracks and overlong leads.
In one embodiment, the defect detection result includes: the electronic component to be detected has defect category, defect position and defect size.
In one embodiment, the defect detection model is determined as follows:
constructing a good product diagram library and a defect diagram library of the electronic components, and labeling labels;
dividing the gallery into a training set and a test set;
training to obtain a plurality of defect detection models by taking the training images in the training set as input and taking the defect types corresponding to the input training images as output;
taking the test images in the test set as input, taking defect types corresponding to the input test images as output, and testing the plurality of defect detection models;
and selecting a defect detection model with the test accuracy rate meeting the detection condition as the defect detection model.
In one embodiment, the method further comprises the following steps:
adding the image of the electronic component to be detected and the detected defect type and position into a training set to obtain an updated training set;
and training the defect detection model by using the updated training set to obtain an updated defect detection model.
In one embodiment, the acquiring the image of the electronic component to be detected includes:
transmitting energy waves to the electronic component to be detected, wherein the energy waves comprise at least one of electromagnetic waves, mechanical waves and substance waves;
receiving a feedback signal transmitted or reflected from the electronic component to be tested;
and calculating to obtain the image of the electronic component to be detected according to the feedback signal.
An electronic component defect detection apparatus, the apparatus comprising:
the acquisition module is used for acquiring an image of the electronic component to be detected;
the detection module is used for inputting the image into a defect detection model obtained by training for defect detection to obtain the defect type of the image; wherein the training set and the test set of the defect detection model comprise a plurality of images, and the defect position and type of the defect region in each image;
the calculation module is used for determining a defect size calculation mode of the electronic component to be detected according to the defect type, performing defect calculation on the image by using the defect size calculation mode, and determining a defect detection result of the electronic component to be detected according to a calculation result; the defect detection result comprises the defect type, the defect position and the defect size of the electronic component to be detected;
the model updating module is used for adding the image of the electronic component to be detected and the detected defect type and position into a training set to obtain an updated training set, training a defect detection model by using the updated training set to obtain an updated defect detection model, and inputting the image into the defect detection model obtained by training for defect detection comprises the following steps: and determining the defect type of the electronic component to be detected through the updated defect detection model.
In one embodiment, the obtaining module further includes:
the transmitting module is used for transmitting energy waves to the electronic component to be detected, and the energy waves comprise at least one of electromagnetic waves, mechanical waves and substance waves;
the receiving module is used for receiving a feedback signal transmitted or reflected from the electronic component to be tested;
and the imaging module is used for calculating to obtain the image of the electronic component to be detected according to the feedback signal.
An electronic component defect detecting apparatus comprising:
at least one processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the method of any embodiment of the present disclosure.
A computer readable storage medium, wherein instructions, when executed by a processor of a server, enable the server to perform a method according to any one of the embodiments of the present disclosure.
A computer program product comprising a computer program enabling, when executed by a processor, the implementation of the method according to any one of the embodiments of the present disclosure.
An electronic component defect detection system, comprising:
at least one processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the method of any embodiment of the present disclosure.
The embodiment scheme provided by the disclosure can automatically detect the defects of the electronic components, output the detection result and improve the defect detection speed. In addition, in the embodiment of the disclosure, different defect types are identified by using a defect detection model during defect detection, and a more matched defect size calculation mode is selected for different defect types, so that the defect size calculation can realize quantitative calculation of a defect area, and the accuracy of a defect detection result is improved.
Drawings
FIG. 1 is a diagram of an exemplary embodiment of a method for detecting defects in an electronic device;
FIG. 2 is a schematic flow chart of a method for detecting defects in an electronic device according to an embodiment;
FIG. 3 is a schematic flow chart illustrating a method for detecting defects in an electronic device according to another embodiment;
FIG. 4 is a schematic diagram of an electronic device defect image in accordance with one embodiment;
FIG. 5 is a schematic diagram of an electronic device defect image in accordance with one embodiment;
FIG. 6 is a schematic flow chart illustrating a method for detecting defects in an electronic device according to another embodiment;
FIG. 7 is a schematic flow chart illustrating a method for detecting defects in an electronic device according to an embodiment;
FIG. 8 is a schematic flow chart diagram illustrating a method for detecting defects in an electronic device, according to an embodiment;
FIG. 9 is a schematic diagram showing a configuration of a defect detection apparatus for an electronic component according to an embodiment;
FIG. 10 is a schematic structural view of a defect detection apparatus for an electronic component according to another embodiment;
fig. 11 is a schematic structural diagram of a defect inspection apparatus for an electronic component in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present disclosure more clearly understood, the present disclosure is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the disclosure and are not intended to limit the disclosure.
It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, the presence of additional identical or equivalent elements in a process, method, article, or apparatus that comprises the recited elements is not excluded. For example, if the terms first, second, etc. are used to denote names, they do not denote any particular order.
The method for detecting the defects of the electronic component provided by the embodiment of the disclosure can be applied to the application environment shown in fig. 1. The acquiring device 110 acquires an image of the electronic component 120. The image may be input to the inspection apparatus 130 so that the inspection apparatus 130 may perform defect inspection on the image of the electronic component 120.
In the present embodiment, an electronic component defect detection method is provided, which can be applied to the detection apparatus 130. As shown in fig. 2, the method includes:
s202, obtaining an image of the electronic component to be detected.
Before the defect detection is performed on the electronic component to be detected, the obtaining device 110 may first obtain an image of the electronic component to be detected. For example, the electronic component may be directly photographed by a camera to obtain an image. Ultrasonic signals can also be emitted by the ultrasonic sensor, and received ultrasonic reflection signals can be converted into images.
S204, inputting the images into a defect detection model obtained by training to obtain the defect types of the electronic components to be detected; and the defect detection model is obtained based on the constructed good product gallery and the defect gallery.
And inputting the images into a defect detection model obtained by training, and if the defects are detected, outputting the defect types and position labels of the components to be detected. If the defect is not detected, the electronic component to be detected is a qualified product, and the electronic component to be detected can be set as an output qualified label.
The defect detection model can be obtained based on the constructed good product gallery and the defect gallery. The good product gallery can include qualified electronic component images and qualified labels. The defect library may include images of defective electronic components and defect type and location labels.
And S206, determining a defect size calculation mode of the electronic component to be detected according to the defect type.
In the embodiment of the present disclosure, the defect size may be calculated in different manners. For example, the defect may be classified into a point defect, a line defect, and a plane defect according to a defect shape, and accordingly, the defect size calculation method of the image may be classified according to the defect shape, and may include: defect area calculation, defect length calculation, etc. The specific calculation method may include design according to a corresponding defect size calculation manner through median filtering and original image subtraction, morphological operation, shape fitting, and the like.
And S208, performing defect calculation on the image by using the defect size calculation mode, and determining a defect detection result of the electronic component to be detected according to the calculation result.
In the embodiment provided by the disclosure, the defect type of the electronic component to be detected is obtained by using the defect detection model, so that the defect detection speed can be increased. The defect size calculation mode of the electronic component to be detected can be confirmed according to the defect type, and the defect detection is carried out on the image according to different defect size calculation modes to obtain a defect detection result. In some application scenes, the defect size calculation mode can be adopted to realize quantitative calculation of the defect area, the defect identification is more accurate than that only the model is adopted to extract the image characteristics, and the accuracy of the defect detection of the electronic component is improved.
Fig. 3 is a schematic flow chart of a defect detection method for an electronic component in another embodiment, some embodiments of the present disclosure provide an implementation manner of calculating a defect size by using a detection apparatus, and specifically, the step S208 may include:
s302, extracting a defect region in the image and calculating the defect area;
on the basis of the above embodiment, after determining that the defect area needs to be calculated according to the defect type, the defect area may be extracted based on the color grayscale information of the image, and the defect area may be calculated by using an image processing technique.
S304, when the defect area is larger than a preset defect threshold value, determining that the electronic component to be detected is a defective product.
In this embodiment, the calculated defect area may be compared with a preset threshold interval, and whether the electronic component has a defect or not may be determined. Specifically, the defect area can be matched with a preset threshold interval, and when the defect area exceeds a certain preset threshold interval, the defect can be considered to exist, and the disqualification of the electronic component can be determined. And when the defect area is smaller than the defect threshold value, the electronic component is qualified.
In the scheme of the embodiment of the disclosure, the defect area of the image can be extracted, the defect area is calculated, and the comparison with the preset defect threshold value is carried out to judge whether the electronic component to be detected is qualified, so that the accuracy of the surface defect detection can be further improved.
In one embodiment, when it is determined that the defect area calculation is required according to the defect type, the defect type may include at least one of the following defects: redundancy, silicon through hole cavities, lamination packaging cavities, solder ball cavities and bonding cavities.
In one embodiment, when the defect type is a solder ball void defect, as shown in fig. 4, if the electronic component has at least one solder ball void area, and the proportion of the solder ball void area is greater than a preset defect threshold, it is determined that the electronic component is a defective product.
In which, due to design, process, manufacturing, and the like, void defects are formed on the solder balls, as shown in fig. 4, a circular area characterized by a darker gray level on the image is a solder ball area 10, and a circular area with a relatively lighter gray level inside the solder ball is a void defect area 20. The detection method of void defects can be based on the ratio of the area of the void region 20 to the area of the solder ball region 10.
Specifically, a solder ball region and a void region may be extracted according to a set empirical threshold of image characteristics, and the ratio of the areas of the void region 502 and the solder ball region 504 may be calculated as shown in fig. 5 for the extracted solder ball region 502 and the void region 504. And when the ratio exceeds a preset defect threshold value, determining that the electronic component has the solder ball hole defect. Therefore, the ratio of the area of the cavity region to the area of the solder ball region is calculated, the defect of the solder ball cavity can be further judged, the misjudgment can be avoided, and the defect detection accuracy is improved.
In one embodiment, the proportion of the solder ball void region includes: the ratio of the sum of all the hollow areas on a single solder ball to the area of the solder ball.
As shown in fig. 4, one or more voids 20 may appear in a single solder ball 10. Generally, when the total area of the plurality of voids exceeds a certain ratio of the area of the solder balls, the voids can also be considered as a defect.
Fig. 6 is a schematic flow chart of a defect detection method for an electronic component in another embodiment, some embodiments of the present disclosure provide an implementation manner of calculating a defect size by using a detection apparatus, and specifically, the step S208 may include:
s602, extracting a defect area in the image and calculating the defect length;
after determining the defect type as a line defect, a defect length calculation may be performed. For example, in one embodiment, the linear structure of the defect region may be extracted based on the color grayscale information of the image, and the length of the defect region may be calculated by using an image processing technique.
S604, when the defect length is larger than a preset defect threshold value, determining that the electronic component to be detected is a defective product.
In this embodiment, the calculated defect length may be compared with a preset threshold interval, so as to determine whether the electronic component has a defect. Specifically, the defect length can be matched with a preset threshold interval, and when the defect length exceeds the preset threshold interval, the defect can be considered to exist, and the disqualification of the electronic component can be determined. And when the defect length is smaller than the defect threshold value, the electronic component is qualified.
According to the scheme of the embodiment of the invention, the defect area in the image can be extracted, the defect length can be calculated, and the defect area is compared with the preset defect threshold value, so that whether the electronic component to be detected is qualified or not can be judged, and the accuracy of linear defect detection can be further improved.
In one embodiment, when it is determined that the defect length calculation is required according to the defect type, the defect type may include at least one of the following defects: chip cracks and overlong leads.
In one embodiment, the defect detection result may include: the electronic component to be detected has the defect types, defect positions, defect sizes and the like.
Wherein the defect size may further include: length, width, area, aspect ratio, area ratio of the defect.
Specifically, whether the corresponding electronic component is qualified or not can be determined according to the defect threshold value range preset by different defect types and other conditions. Other conditions may also include defect location, defect number, etc. For example, the void defect of the solder ball can be judged according to the ratio of the void to the area of the solder ball and the number of voids on the solder ball. For example, in one embodiment, when a single void defect occurs on a single solder ball of an electronic component, the electronic component with the corresponding single void area exceeding that of the solder ball by more than or equal to 25% can be regarded as a defective product. The electronic component with a single hollow space occupying 10-25% of the area of the solder ball has acceptable welding quality and can be regarded as qualified products, but the hollow space is reduced by improving the process. The electronic component with the area of the single hollow hole occupying less than or equal to 10 percent of the area of the solder ball can be regarded as a qualified product. When a plurality of void defects appear on a single solder ball of the electronic component, the defect size of the electronic component can be determined and whether the defect size is qualified or not can be determined according to the corresponding preset defect threshold value.
In one embodiment, the defect detection model is determined by the following method, as shown in fig. 7, including:
s702, constructing a good product diagram library and a defect diagram library of the electronic component, and labeling;
specifically, the labeling label may be different according to image sources, for example, the image source may be labeled according to a camera, X-ray, ultrasonic waves, and the like. The packaging technology of electronic components can be labeled according to the packaging form, such as through silicon via technology, stacked packaging technology, and the like. The defect type and defect location may be labeled according to image characteristics. The labeling label may be one or a combination of several of the labeling methods.
S704, dividing the gallery into a training set and a test set;
and S706, training to obtain a plurality of defect detection models by taking the training images in the training set as input and taking the defect types corresponding to the input training images as output.
Taking a convolutional neural network as an example, the specific training process is as follows:
acquiring initial model parameters of a convolutional neural network model to be trained, wherein the initial model parameters comprise initial convolutional kernels of each convolutional layer, initial bias matrixes of each convolutional layer, initial weight matrixes of all-connected layers and initial bias vectors of all-connected layers;
on each level of convolutional layer, using the initial convolutional kernels and the initial bias matrixes on each level of convolutional layer to respectively perform convolution operation and maximum pooling operation on each training image to obtain a first characteristic image of each training image on each level of convolutional layer;
performing horizontal pooling operation on the first characteristic image of each training image on at least one level of convolution layer to obtain a second characteristic image of each training image on each level of convolution layer;
determining a feature vector of each training image according to a second feature image of each training image on each convolutional layer;
processing each feature vector according to the initial weight matrix and the initial bias vector to obtain a category probability vector of each training image;
calculating a class error according to the class probability vector of each training image and the initial class of each training image;
adjusting model parameters of the convolutional neural network model to be trained based on the category errors;
continuing the process of adjusting the model parameters based on the adjusted model parameters and the plurality of training images until the iteration times reach the preset times;
and taking the model parameters obtained when the iteration times reach the preset times as the model parameters of the trained convolutional neural network model.
S708, taking the test images in the test set as input, taking the defect types corresponding to the input test images as output, and testing the plurality of defect detection models;
s710, selecting a defect detection model with the test accuracy rate meeting the detection condition as the defect detection model.
In one embodiment, to further improve the efficiency and accuracy of detection, the method may further include:
adding the image of the electronic component to be detected and the detected defect type and position into a training set to obtain an updated training set;
and training the defect detection model by using the updated training set to obtain an updated defect detection model.
In one embodiment, as shown in fig. 8, the acquiring the image of the electronic component to be detected may include:
s802, transmitting energy waves to the electronic component to be detected, wherein the energy waves comprise at least one of electromagnetic waves, mechanical waves and matter waves.
The energy wave may include energy propagating in the form of wave, and may include electromagnetic wave, mechanical wave, and matter wave. Specifically, the electromagnetic wave generally refers to a wave having electromagnetic radiation characteristics, such as radio waves, microwaves, infrared rays, visible light, ultraviolet rays, X-rays, gamma rays, and the like. Mechanical waves are typically formed by the propagation of mechanical vibrations in a medium. For example, the mechanical waves may include acoustic waves, water waves, and the like. The material wave is a probability wave, and the mode direction of the probability wave refers to the probability density which can occur at a certain point in space at any time, wherein the size of the probability density is governed by the fluctuation rule.
S804, receiving a feedback signal transmitted or reflected from the electronic component to be tested;
specifically, the energy wave-based sensor receives a feedback signal transmitted or reflected from the electronic component to be measured. The sensor of the energy wave may include an ultrasonic sensor, an infrared sensor, a radiation sensor (such as X-ray), and the like.
And S806, calculating to obtain the image of the electronic component to be detected according to the feedback signal.
It is understood that the embodiments of the method described above are described in a progressive manner, and the same/similar parts of the embodiments are referred to each other, and each embodiment focuses on differences from the other embodiments. Reference may be made to the description of other method embodiments for relevant points.
It should be understood that although the steps in the flowcharts shown in fig. 2, 3, and 6-8 are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2, 3, and 6-8 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or at least partially with other steps or other steps.
Based on the description of the embodiment of the electronic component defect detection method, the disclosure also provides a device for detecting the defects of the electronic component. The apparatus may include systems (including distributed systems), software (applications), modules, components, servers, clients, etc. that use the methods described in embodiments of the present specification in conjunction with any necessary apparatus to implement the hardware. Based on the same innovative concept, the embodiments of the present disclosure provide an apparatus in one or more embodiments as described in the following embodiments. Since the implementation scheme of the apparatus for solving the problem is similar to that of the method, the specific implementation of the apparatus in the embodiment of the present specification may refer to the implementation of the foregoing method, and repeated details are not repeated. As used hereinafter, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
In one embodiment, as shown in fig. 9, there is provided an electronic component defect detecting apparatus 200, including: an obtaining module 902, a detecting module 904, a calculating module 906, and a model updating module 908, wherein:
an obtaining module 902, configured to obtain an image of an electronic component to be detected;
a detection module 904, configured to input the image into a defect detection model obtained through training for defect detection, so as to obtain a defect type of the image; wherein the training set and the test set of the defect detection model comprise a plurality of images, and the defect position and type of the defect region in each image;
a calculating module 906, configured to determine a defect size calculating mode of the electronic component to be detected according to the defect type, perform defect calculation on the image by using the defect size calculating mode, and determine a defect detection result of the electronic component to be detected according to a calculation result; and the defect detection result comprises the defect type, the defect position and the defect size of the electronic component to be detected.
A model updating module 908, configured to add the image of the electronic component to be detected and the detected defect type and position to a training set to obtain an updated training set, train a defect detection model by using the updated training set to obtain an updated defect detection model, where inputting the image into the defect detection model obtained through training for defect detection includes: and determining the defect type of the electronic component to be detected through the updated defect detection model.
In one embodiment, as shown in fig. 10, the obtaining module further includes:
the emitting module 1002 is configured to emit an energy wave to the electronic component to be detected, where the energy wave includes at least one of an electromagnetic wave, a mechanical wave, and a material wave;
the receiving module 1004 is configured to receive a feedback signal transmitted or reflected from the electronic component to be tested;
and the imaging module 1006 is configured to calculate to obtain an image of the electronic component to be detected according to the feedback signal.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
In one embodiment, a computer program product is also provided, which includes a computer program that, when executed by a processor, implements the electronic component defect detection method described in any one of the present descriptions.
In one embodiment, an electronic component defect inspection apparatus 130 is provided, as shown in fig. 11. The detection device 130 may be a computer, personal digital assistant, server, cellular phone, smart phone, wearable device, in-vehicle device, and the like. The components shown in this specification, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
Fig. 11 is a schematic diagram illustrating an electronic component defect inspection apparatus 130 according to an exemplary embodiment, the inspection apparatus 130 including a processing component 1302, which further includes one or more processors, and memory resources, represented by memory 1304, for storing instructions, such as applications, executable by the processing component 1302. The application programs stored in memory 1304 may include one or more modules that each correspond to a set of instructions. Further, the processing component 1302 is configured to execute instructions to perform the above-described methods that may be implemented on the proxy server side. The memory 1304 may be implemented by any type or combination of volatile or non-volatile storage devices such as static random access memory (12RAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.
The device 130 may also include a power component 1306 configured to perform power management for the device 130, a wired or wireless network interface 1308 configured to connect the device 130 to a network, and an input-output (I/O) interface 1310. The power supply component 1306 provides power to the various components of the device 130. The power components 1306 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the device 130. I/O interface 1310 provides an interface between processing component 1302 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a start button, a return button, and a lock button. The device 130 may operate based on an operating system stored in the memory 1304, such as Window 1212 erver, Mac O12X, Unix, Linux, FreeB12D, or the like.
In one embodiment, a computer-readable storage medium, such as the memory 1304, is also provided that includes instructions executable by the processor 1302 of the detection device 130 to perform the above-described method. The storage medium may be a computer-readable storage medium, which may be, for example, a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
In one embodiment, an electronic component defect detection system is also provided and may include one or more processors and memory for storing processor-executable instructions, such as an application program. The application program stored in the memory may include one or more modules that each correspond to a set of instructions. Further, the processor is configured to execute the instructions to perform the above-described method that may be implemented on the proxy server side.
With respect to the defect detection system in the above embodiment, the respective module components and functions thereof have been described in detail in the embodiment related to the method, and will not be described in detail here.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the hardware + program class embodiment, since it is substantially similar to the method embodiment, the description is simple, and the relevant points can be referred to the partial description of the method embodiment.
It should be noted that, the descriptions of the above-mentioned apparatuses, devices, storage media, systems, etc. according to the method embodiments may also include other embodiments, and specific implementations may refer to the descriptions of the related method embodiments. Meanwhile, the new embodiment formed by the mutual combination of the features of the methods, the devices, the equipment and the server embodiments still belongs to the implementation range covered by the present disclosure, and the details are not repeated herein.
For convenience of description, the above devices are described as being divided into various modules by functions, and are described separately. Of course, when implementing one or more of the present description, the functions of each module may be implemented in one or more software and/or hardware, or a module implementing the same function may be implemented by a combination of multiple sub-modules or sub-units, etc. The above-described embodiments of the apparatus are merely illustrative, and for example, a module or a unit may be divided into only one logical function, and may be implemented in other ways, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted or not executed. In addition, the coupling, communication connection, etc. between the devices or units shown or described may be realized by direct and/or indirect coupling/connection, and may be realized by some standard or customized interfaces, protocols, etc., in an electrical, mechanical or other form.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof.
Claims (17)
1. A method for detecting defects of electronic components is characterized by comprising the following steps:
acquiring an image of an electronic component to be detected;
inputting the image into a defect detection model obtained by training to obtain the defect type of the electronic component to be detected; the defect detection model is obtained based on the constructed good product gallery and the defect gallery through training;
determining a defect size calculation mode of the electronic component to be detected according to the defect type;
and performing defect calculation on the image by using the defect size calculation mode, and determining a defect detection result of the electronic component to be detected according to the calculation result.
2. The method according to claim 1, wherein when it is determined that the defect area calculation is required according to the defect type, performing defect calculation on the image by using the defect size calculation method, and determining the defect detection result of the electronic component to be detected according to the calculation result comprises:
extracting a defect area in the image and calculating the defect area;
and when the defect area is larger than a preset defect threshold value, determining that the electronic component to be detected is an unqualified product.
3. The method of claim 2, wherein the defect type comprises at least one defect of:
redundancy, silicon through hole cavities, lamination packaging cavities, solder ball cavities and bonding cavities.
4. The method according to claim 3, wherein when the defect type is a solder ball void defect, if the electronic component has at least one solder ball void area with a ratio larger than a preset defect threshold, the electronic component is determined to be a defective product.
5. The method of claim 4, wherein the percentage of the solder ball void area comprises:
the ratio of the sum of all the hollow areas on a single solder ball to the area of the solder ball.
6. The method according to claim 1, wherein when it is determined that the defect length calculation is required according to the defect type, performing defect calculation on the image by using the defect size calculation method, and determining the defect detection result of the electronic component to be detected according to the calculation result comprises:
extracting a defect area in the image and calculating the defect length;
and when the defect length is larger than a preset defect threshold value, determining that the electronic component to be detected is an unqualified product.
7. The method of claim 6, wherein the defect type comprises at least one defect of: chip cracks and overlong leads.
8. The method of claim 1, wherein the defect detection result comprises: the electronic component to be detected has defect category, defect position and defect size.
9. The method of claim 1, wherein the defect detection model is determined by:
constructing a good product diagram library and a defect diagram library of the electronic components, and labeling labels;
dividing the gallery into a training set and a test set;
training to obtain a plurality of defect detection models by taking the training images in the training set as input and taking the defect types corresponding to the input training images as output;
taking the test images in the test set as input, taking defect types corresponding to the input test images as output, and testing the plurality of defect detection models;
and selecting a defect detection model with the test accuracy rate meeting the detection condition as the defect detection model.
10. The method of claim 1, further comprising:
adding the image of the electronic component to be detected and the detected defect type and position into a training set to obtain an updated training set;
and training the defect detection model by using the updated training set to obtain an updated defect detection model.
11. The method according to claim 1, wherein the acquiring the image of the electronic component to be tested comprises:
transmitting energy waves to the electronic component to be detected, wherein the energy waves comprise at least one of electromagnetic waves, mechanical waves and substance waves;
receiving a feedback signal transmitted or reflected from the electronic component to be tested;
and calculating to obtain the image of the electronic component to be detected according to the feedback signal.
12. An electronic component defect detection apparatus, the apparatus comprising:
the acquisition module is used for acquiring an image of the electronic component to be detected;
the detection module is used for inputting the image into a defect detection model obtained by training for defect detection to obtain the defect type of the image; wherein the training set and the test set of the defect detection model comprise a plurality of images, and the defect position and type of the defect region in each image;
the calculation module is used for determining a defect size calculation mode of the electronic component to be detected according to the defect type, performing defect calculation on the image by using the defect size calculation mode, and determining a defect detection result of the electronic component to be detected according to a calculation result; the defect detection result comprises the defect type, the defect position and the defect size of the electronic component to be detected;
the model updating module is used for adding the image of the electronic component to be detected and the detected defect type and position into a training set to obtain an updated training set, training a defect detection model by using the updated training set to obtain an updated defect detection model, and inputting the image into the defect detection model obtained by training for defect detection comprises the following steps: and determining the defect type of the electronic component to be detected through the updated defect detection model.
13. The apparatus of claim 12, wherein the obtaining module further comprises:
the transmitting module is used for transmitting energy waves to the electronic component to be detected, and the energy waves comprise at least one of electromagnetic waves, mechanical waves and substance waves;
the receiving module is used for receiving a feedback signal transmitted or reflected from the electronic component to be tested;
and the imaging module is used for calculating to obtain the image of the electronic component to be detected according to the feedback signal.
14. An electronic component defect detecting apparatus, comprising:
at least one processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the electronic component defect detection method according to any one of claims 1 to 10.
15. A computer-readable storage medium, wherein instructions in the computer-readable storage medium, when executed by a processor of a server, enable the server to perform the electronic component defect detection method of any one of claims 1 to 10.
16. A computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the method for electronic component defect detection of any of claims 1 to 10.
17. An electronic component defect detection system, comprising:
at least one processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the electronic component defect detection method according to any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110195319.4A CN112950560B (en) | 2021-02-20 | 2021-02-20 | Electronic component defect detection method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110195319.4A CN112950560B (en) | 2021-02-20 | 2021-02-20 | Electronic component defect detection method, device and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112950560A true CN112950560A (en) | 2021-06-11 |
| CN112950560B CN112950560B (en) | 2024-06-21 |
Family
ID=76244967
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110195319.4A Active CN112950560B (en) | 2021-02-20 | 2021-02-20 | Electronic component defect detection method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112950560B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113409315A (en) * | 2021-08-19 | 2021-09-17 | 深圳市信润富联数字科技有限公司 | Workpiece defect detection method, electronic device, device and readable storage medium |
| CN113510234A (en) * | 2021-09-14 | 2021-10-19 | 深圳市信润富联数字科技有限公司 | Quality monitoring method and device for low-pressure casting of hub and electronic equipment |
| CN113916127A (en) * | 2021-09-28 | 2022-01-11 | 安庆帝伯粉末冶金有限公司 | Visual inspection system and method for appearance of valve guide pipe finished product |
| CN114035013A (en) * | 2021-10-19 | 2022-02-11 | 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） | Defect diagnosis method and defect diagnosis device |
| CN114240920A (en) * | 2021-12-24 | 2022-03-25 | 苏州凌云视界智能设备有限责任公司 | Appearance defect detection method |
| CN114240947A (en) * | 2022-02-28 | 2022-03-25 | 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） | Construction method and device of sweep image database and computer equipment |
| CN115631362A (en) * | 2022-09-26 | 2023-01-20 | 北京霍里思特科技有限公司 | Ironware identification method and ironware identification device |
| CN116739980A (en) * | 2023-05-04 | 2023-09-12 | 鲸朵(上海)智能科技有限公司 | Detection capability assessment method and device of anomaly detection model |
| CN116934745A (en) * | 2023-09-14 | 2023-10-24 | 创新奇智(浙江)科技有限公司 | Quality detection method and detection system for electronic component plugging clip |
| CN117152141A (en) * | 2023-10-30 | 2023-12-01 | 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） | Defect detection method, defect detection device, computer equipment, storage medium and product |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101576508A (en) * | 2009-05-27 | 2009-11-11 | 华南理工大学 | Device and method for automatically detecting chip appearance defects |
| CN108509958A (en) * | 2018-03-30 | 2018-09-07 | 北京金山安全软件有限公司 | Defect type detection method, defect type detection device, electronic equipment and medium |
| CN109886950A (en) * | 2019-02-22 | 2019-06-14 | 北京百度网讯科技有限公司 | The defect inspection method and device of circuit board |
| CN109961433A (en) * | 2019-03-29 | 2019-07-02 | 北京百度网讯科技有限公司 | Product defects detection method, device and computer equipment |
| CN110349145A (en) * | 2019-07-09 | 2019-10-18 | 京东方科技集团股份有限公司 | Defect inspection method, device, electronic equipment and storage medium |
| CN110599484A (en) * | 2019-09-19 | 2019-12-20 | 京东方科技集团股份有限公司 | Defect detection method, device and storage medium |
| WO2020048119A1 (en) * | 2018-09-04 | 2020-03-12 | Boe Technology Group Co., Ltd. | Method and apparatus for training a convolutional neural network to detect defects |
| CN111145164A (en) * | 2019-12-30 | 2020-05-12 | 上海感图网络科技有限公司 | IC chip defect detection method based on artificial intelligence |
| CN111179261A (en) * | 2019-12-31 | 2020-05-19 | 深圳市太赫兹科技创新研究院 | Defect detection method, system, terminal device and storage medium |
| WO2020137222A1 (en) * | 2018-12-28 | 2020-07-02 | オムロン株式会社 | Defect inspecting device, defect inspecting method, and program for same |
| CN111640091A (en) * | 2020-05-14 | 2020-09-08 | 阿丘机器人科技(苏州)有限公司 | Method for detecting product defects and computer storage medium |
| CN111696095A (en) * | 2020-06-12 | 2020-09-22 | 北京百度网讯科技有限公司 | Method and device for detecting surface defects of object |
| CN111833303A (en) * | 2020-06-05 | 2020-10-27 | 北京百度网讯科技有限公司 | Product detection method and device, electronic equipment and storage medium |
| CN112365491A (en) * | 2020-11-27 | 2021-02-12 | 上海市计算技术研究所 | Method for detecting welding seam of container, electronic equipment and storage medium |
-
2021
- 2021-02-20 CN CN202110195319.4A patent/CN112950560B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101576508A (en) * | 2009-05-27 | 2009-11-11 | 华南理工大学 | Device and method for automatically detecting chip appearance defects |
| CN108509958A (en) * | 2018-03-30 | 2018-09-07 | 北京金山安全软件有限公司 | Defect type detection method, defect type detection device, electronic equipment and medium |
| WO2020048119A1 (en) * | 2018-09-04 | 2020-03-12 | Boe Technology Group Co., Ltd. | Method and apparatus for training a convolutional neural network to detect defects |
| WO2020137222A1 (en) * | 2018-12-28 | 2020-07-02 | オムロン株式会社 | Defect inspecting device, defect inspecting method, and program for same |
| CN109886950A (en) * | 2019-02-22 | 2019-06-14 | 北京百度网讯科技有限公司 | The defect inspection method and device of circuit board |
| CN109961433A (en) * | 2019-03-29 | 2019-07-02 | 北京百度网讯科技有限公司 | Product defects detection method, device and computer equipment |
| CN110349145A (en) * | 2019-07-09 | 2019-10-18 | 京东方科技集团股份有限公司 | Defect inspection method, device, electronic equipment and storage medium |
| CN110599484A (en) * | 2019-09-19 | 2019-12-20 | 京东方科技集团股份有限公司 | Defect detection method, device and storage medium |
| CN111145164A (en) * | 2019-12-30 | 2020-05-12 | 上海感图网络科技有限公司 | IC chip defect detection method based on artificial intelligence |
| CN111179261A (en) * | 2019-12-31 | 2020-05-19 | 深圳市太赫兹科技创新研究院 | Defect detection method, system, terminal device and storage medium |
| CN111640091A (en) * | 2020-05-14 | 2020-09-08 | 阿丘机器人科技(苏州)有限公司 | Method for detecting product defects and computer storage medium |
| CN111833303A (en) * | 2020-06-05 | 2020-10-27 | 北京百度网讯科技有限公司 | Product detection method and device, electronic equipment and storage medium |
| CN111696095A (en) * | 2020-06-12 | 2020-09-22 | 北京百度网讯科技有限公司 | Method and device for detecting surface defects of object |
| CN112365491A (en) * | 2020-11-27 | 2021-02-12 | 上海市计算技术研究所 | Method for detecting welding seam of container, electronic equipment and storage medium |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113409315A (en) * | 2021-08-19 | 2021-09-17 | 深圳市信润富联数字科技有限公司 | Workpiece defect detection method, electronic device, device and readable storage medium |
| CN113510234A (en) * | 2021-09-14 | 2021-10-19 | 深圳市信润富联数字科技有限公司 | Quality monitoring method and device for low-pressure casting of hub and electronic equipment |
| CN113510234B (en) * | 2021-09-14 | 2022-01-07 | 深圳市信润富联数字科技有限公司 | Quality monitoring method and device for low-pressure casting of hub and electronic equipment |
| CN113916127A (en) * | 2021-09-28 | 2022-01-11 | 安庆帝伯粉末冶金有限公司 | Visual inspection system and method for appearance of valve guide pipe finished product |
| CN114035013A (en) * | 2021-10-19 | 2022-02-11 | 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） | Defect diagnosis method and defect diagnosis device |
| CN114240920A (en) * | 2021-12-24 | 2022-03-25 | 苏州凌云视界智能设备有限责任公司 | Appearance defect detection method |
| CN114240947A (en) * | 2022-02-28 | 2022-03-25 | 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） | Construction method and device of sweep image database and computer equipment |
| CN114240947B (en) * | 2022-02-28 | 2022-06-14 | 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） | Construction method and device of sweep image database and computer equipment |
| CN115631362A (en) * | 2022-09-26 | 2023-01-20 | 北京霍里思特科技有限公司 | Ironware identification method and ironware identification device |
| CN116739980A (en) * | 2023-05-04 | 2023-09-12 | 鲸朵(上海)智能科技有限公司 | Detection capability assessment method and device of anomaly detection model |
| CN116739980B (en) * | 2023-05-04 | 2024-07-26 | 鲸朵(上海)智能科技有限公司 | Detection capability assessment method and device of anomaly detection model |
| CN116934745A (en) * | 2023-09-14 | 2023-10-24 | 创新奇智(浙江)科技有限公司 | Quality detection method and detection system for electronic component plugging clip |
| CN116934745B (en) * | 2023-09-14 | 2023-12-19 | 创新奇智(浙江)科技有限公司 | Quality detection method and detection system for electronic component plugging clip |
| CN117152141A (en) * | 2023-10-30 | 2023-12-01 | 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） | Defect detection method, defect detection device, computer equipment, storage medium and product |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112950560B (en) | 2024-06-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112950560B (en) | Electronic component defect detection method, device and system | |
| US11222234B2 (en) | Method and apparatus for training a convolutional neural network to detect defects | |
| CN108986085B (en) | CT image pulmonary nodule detection method, device and equipment and readable storage medium | |
| Hao et al. | Solder joint inspection based on neural network combined with genetic algorithm | |
| TWI748242B (en) | Method and system for scanning wafer | |
| CN111699499A (en) | Inspection system, image recognition system, recognizer generation system, and learning data generation device | |
| CN111557665A (en) | Dense body marker estimation from camera data for patient positioning in medical imaging | |
| CN108564102A (en) | Image clustering evaluation of result method and apparatus | |
| US20220005214A1 (en) | Method and apparatus for depth-map estimation of a scene | |
| CN110717881A (en) | Wafer defect identification method and device, storage medium and terminal equipment | |
| JP2022501681A (en) | Depth image complement method and device, computer readable storage medium | |
| WO2019176990A1 (en) | Inspection device, image discriminating device, discriminating device, inspection method, and inspection program | |
| CN114862832A (en) | Method, device and equipment for optimizing defect detection model and storage medium | |
| KR102269741B1 (en) | X-ray inspection method for overlap pattern using machine learning | |
| US20230053878A1 (en) | Systems and methods for predicting a quality of a printed circuit board assembly | |
| WO2019176988A1 (en) | Inspection system, identification system, and device for evaluating identification apparatus | |
| US11880432B2 (en) | Confidence measure for a deployed machine learning model | |
| JP2021177541A (en) | Automatic selection of algorithmic modules for examination of a specimen | |
| CN117147561A (en) | Surface quality detection method and system for metal zipper | |
| KR102174424B1 (en) | Method for Inspecting Component basesd Server and system and apparatus therefor | |
| JP7059889B2 (en) | Learning device, image generator, learning method, and learning program | |
| CN114863201A (en) | Training method and device of three-dimensional detection model, computer equipment and storage medium | |
| US11188792B2 (en) | Defect detection using multiple models | |
| CN114120311A (en) | Control method and device for food baking | |
| CN113128516A (en) | Edge extraction method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |