CN113609897A - Defect detection method and defect detection system - Google Patents
Defect detection method and defect detection system Download PDFInfo
- Publication number
- CN113609897A CN113609897A CN202110699282.9A CN202110699282A CN113609897A CN 113609897 A CN113609897 A CN 113609897A CN 202110699282 A CN202110699282 A CN 202110699282A CN 113609897 A CN113609897 A CN 113609897A
- Authority
- CN
- China
- Prior art keywords
- defect
- image
- template
- suspected
- suspected defect
- 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.)
- Pending
Links
- 230000007547 defect Effects 0.000 title claims abstract description 426
- 238000001514 detection method Methods 0.000 title claims abstract description 87
- 238000000034 method Methods 0.000 claims abstract description 58
- 230000011218 segmentation Effects 0.000 claims description 39
- 238000002372 labelling Methods 0.000 claims description 17
- 238000002360 preparation method Methods 0.000 claims description 11
- 238000005520 cutting process Methods 0.000 claims description 9
- 239000000976 ink Substances 0.000 description 23
- 230000015654 memory Effects 0.000 description 12
- 238000012545 processing Methods 0.000 description 12
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 11
- 229910052802 copper Inorganic materials 0.000 description 11
- 239000010949 copper Substances 0.000 description 11
- 230000008569 process Effects 0.000 description 10
- 238000003860 storage Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 6
- 229910052737 gold Inorganic materials 0.000 description 6
- 239000010931 gold Substances 0.000 description 6
- 238000007689 inspection Methods 0.000 description 6
- 238000012549 training Methods 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 150000003071 polychlorinated biphenyls Chemical class 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 238000007639 printing Methods 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 238000010309 melting process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Manufacturing & Machinery (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a defect detection method and a defect detection system. Wherein, the method comprises the following steps: acquiring a suspected defect image of a target object, a template image and position information of the suspected defect image in the template image; according to the suspected defect image, the template image and the position information, acquiring a template part corresponding to the suspected defect image in the template image; and detecting whether the suspected defect image has target defects or not according to the template part and the suspected defect image. The scheme can automatically detect whether the suspected defect image has the target defect or not without manual detection, so that the detection efficiency is higher.
Description
Technical Field
The invention relates to the field of defect detection, in particular to a defect detection method and a defect detection system.
Background
In the production and manufacturing process of electronic products, the PCB is an important component. In the production and manufacturing process of the PCB, because of factors such as manufacturing procedure errors, artificial collisions, foreign impurity pollution and the like, some appearance defects such as printing errors of components, ink stains, copper leakage and the like are inevitably generated.
The defective PCB board is introduced into the market, which may affect the functions of the electronic product using the PCB board and may have a serious negative effect on the product reputation of the PCB manufacturer. Therefore, for a PCB manufacturer, the detection of the appearance defects of the PCB is an important link, a PCB manufacturer can hire a special staff to perform quality inspection on each produced PCB, the quality inspection mode mainly includes that the AOI equipment is used for shooting the PCB into a high-definition picture, the AOI equipment can circle out the place where the defects are likely to exist, and then the quality inspection worker confirms whether the defects are really existed one by one, and a lot of time is consumed for the manual confirmation one by one due to the fact that the number of the PCBs produced by the factory every day is large.
A large number of false reports exist in places (AOI equipment alarm diagrams) which are reported by AOI equipment and possibly have defects, so that the work task of PCB quality inspection is heavy, workers need to be careful, the requirement on the quality of the workers is very high, and the faults are very easy to miss if the workers are lacked;
in the actual operation process, people inevitably have negligence, and defective PCB boards are caused to flow into the market.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the invention provides a defect detection method and a defect detection system, which at least solve the technical problem of low defect detection efficiency caused by manual detection.
According to an aspect of the embodiments of the present invention, there is provided a defect detection method, including: acquiring a suspected defect image, a template image and position information of the suspected defect image in the template image of a target object; according to the suspected defect image, the template image and the position information, acquiring a template part corresponding to the suspected defect image in the template image; and detecting whether the suspected defect image has target defects or not according to the template part and the suspected defect image.
Optionally, the obtaining, according to the suspected defect image, the template image, and the position information, a template portion corresponding to the suspected defect image in the template image includes: determining a preliminary template part in the template image according to the position information, wherein the area of the preliminary template part is larger than that of the suspected defect image, and the preliminary template part comprises a region corresponding to the position information; and intercepting the template part in the preparation template part according to the suspected defect image.
Optionally, the cutting out the template part of the preliminary template part according to the suspected defect image includes: aligning the suspected defect image with a corresponding part in the preparation template part by adopting a sliding window template matching method; and cutting out the part aligned with the suspected defect image from the preparation template part to obtain the template part.
Optionally, the detecting whether the suspected defect image has a target defect according to the template portion and the suspected defect image includes: detecting the defects in the suspected defect image according to the template part to obtain the types of the defects and the labeling graphs of the defects, wherein the types comprise linear types and bulk types; and determining whether the corresponding defect is the target defect or not according to the dimension information of the marked graph.
Optionally, detecting a defect in the suspected defect image according to the template portion to obtain a type of the defect and a label graph of the defect, including: splicing the suspected defect image and the template part into a six-channel image; and inputting the six-channel image into an FCOS network detector to obtain the type of the defect and the labeling graph of the defect.
Optionally, the label graph is a label detection box.
Optionally, the determining, according to the size information of the labeled graph, whether the corresponding defect is a target defect includes: determining whether the length of a diagonal line of the marking detection frame is greater than a predetermined length when the type of the defect is the linear type; and under the condition that the length of the diagonal line of the mark detection frame is greater than a preset length, determining the corresponding defect as the target defect.
Optionally, the determining, according to the size information of the labeled graph, whether the corresponding defect is a target defect includes: under the condition that the defect type is the blob type, intercepting a region to be detected in the suspected defect image by taking the center of the mark detection frame corresponding to the blob type as the center, wherein the region to be detected comprises the corresponding mark detection frame; performing semantic segmentation on the region to be detected to obtain a segmentation result; calculating the area of the corresponding defect according to the segmentation result; determining the defect as the target defect if the area is greater than a predetermined area.
Optionally, the performing semantic segmentation on the region to be detected to obtain a segmentation result includes: and performing semantic segmentation on the to-be-detected region by using a full convolution network based on Unet to obtain the segmentation result.
Optionally, the obtaining a suspected defect image of a target object, a template image, and position information of the suspected defect image in the template image includes: and receiving the suspected defect image, the template image and the position information which are sent by the AOI equipment.
Optionally, the target object is a PCB board.
According to another aspect of the embodiments of the present invention, there is also provided a system for detecting a defect, including: the AOI equipment is used for acquiring a suspected defect image of a PCB, a template image and position information of the suspected defect image in the template image; defect detection means, communicatively connected to said AOI device, for performing any of said detection methods.
According to another aspect of the embodiments of the present invention, there is also provided a method for detecting a defect, including: the method comprises the steps that a cloud server obtains a suspected defect image, a template image and position information of the suspected defect image in the template image of a target object; the cloud server acquires a template part corresponding to the suspected defect image in the template image according to the suspected defect image, the template image and the position information; and the cloud server detects whether the suspected defect image has a target defect according to the template part and the suspected defect image.
In the embodiment of the invention, a suspected defect image, a template image and position information of the suspected defect image in the template image of a target object are obtained; according to the suspected defect image, the template image and the position information, acquiring a template part corresponding to the suspected defect image in the template image; detecting whether the suspected defect image has a target defect or not according to the template part and the suspected defect image; according to the scheme, whether the target defect exists in the suspected defect image can be automatically detected, manual detection is not needed, the detection efficiency is higher, and the technical problem that the defect detection efficiency is lower due to manual detection is solved. In addition, the scheme greatly improves the accuracy and stability of detecting the target defects.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
fig. 1 is a block diagram of a hardware configuration of a computer terminal for implementing a defect detection method according to an embodiment of the present invention;
FIG. 2 is a flowchart of a defect detection method according to embodiment 1 of the present invention;
FIG. 3(a) is a schematic illustration of a defect;
FIG. 3(b) is a schematic illustration of another defect;
FIG. 3(c) is a schematic illustration of another defect;
FIG. 4(a) is a schematic illustration of a template image;
FIG. 4(b) is a schematic view of a template portion;
FIG. 4(c) is a schematic diagram of a suspected defect image;
FIG. 4(d) is a schematic diagram of the alignment of a suspected defect image with a portion of a preparation template using sliding window template matching;
FIG. 5(a) is a schematic illustration of a detected defect using an embodiment of the present invention;
FIG. 5(b) is a schematic illustration of another defect detected using an embodiment of the present invention;
FIG. 6 is a block diagram showing a system for detecting defects according to embodiment 2 of the present invention;
fig. 7 is a flowchart of another defect detection method according to embodiment 3 of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above 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 invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
There is also provided, in accordance with an embodiment of the present invention, a method embodiment for defect detection, it being noted that the steps illustrated in the flowchart of the figure may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than that presented herein.
The method provided by the first embodiment of the present application may be executed in a mobile terminal, a computer terminal, or a similar computing device. Fig. 1 shows a block diagram of a hardware structure of a computer terminal (or mobile device) for implementing a defect detection method. As shown in fig. 1, the computer terminal 10 (or mobile device 10) may include one or more (shown as 102a, 102b, … …, 102 n) processors 102 (the processors 102 may include, but are not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA), and memory 104 for storing data. Besides, the method can also comprise the following steps: a transmission module, a display, an input/output interface (I/O interface), a universal serial BUS (BUS) port (which may be included as one of the ports of the I/O interface), a network interface, a power source, and/or a camera. It will be understood by those skilled in the art that the structure shown in fig. 1 is only an illustration and is not intended to limit the structure of the electronic device. For example, the computer terminal 10 may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.
It should be noted that the one or more processors 102 and/or other data processing circuitry described above may be referred to generally herein as "data processing circuitry". The data processing circuitry may be embodied in whole or in part in software, hardware, firmware, or any combination thereof. Further, the data processing circuit may be a single stand-alone processing module, or incorporated in whole or in part into any of the other elements in the computer terminal 10 (or mobile device). As referred to in the embodiments of the application, the data processing circuit acts as a processor control (e.g. selection of a variable resistance termination path connected to the interface).
The memory 104 may be used to store software programs and modules of application software, such as program instructions/data storage devices corresponding to the detection method in the embodiment of the present invention, and the processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, implementing the vulnerability detection method of the application program. The memory 104 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory located remotely from the processor 102, which may be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission module is used for receiving or sending data through a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission module includes a Network adapter (NIC) that can be connected to other Network devices through a base station to communicate with the internet. In one example, the transmission module may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
The display may be, for example, a touch screen type Liquid Crystal Display (LCD) that may enable a user to interact with a user interface of the computer terminal 10 (or mobile device).
It should be noted here that, in some embodiments, the computer device (or mobile device) shown in fig. 1 has a touch display (also referred to as a "touch screen" or "touch display screen"). In some embodiments, the computer device (or mobile device) of FIG. 1 described above has a Graphical User Interface (GUI) with which a user can interact by touching finger contacts and/or gestures on a touch-sensitive surface, where the human interaction functionality optionally includes the following interactions: executable instructions for creating web pages, drawing, word processing, making electronic documents, games, video conferencing, instant messaging, emailing, call interfacing, playing digital video, playing digital music, and/or web browsing, etc., for performing the above-described human-computer interaction functions, are configured/stored in one or more processor-executable computer program products or readable storage media.
Under the operating environment, the application provides a method for detecting the defects as shown in fig. 2. Fig. 2 is a flowchart of a defect detection method according to embodiment 1 of the present invention. As shown in fig. 2, the process includes the following steps:
step S102, acquiring a suspected defect image of a target object, a template image and position information of the suspected defect image in the template image, wherein the suspected defect image is an image suspected of having a defect, generally speaking, the suspected defect image is an image of a part of a certain surface of the target object, and the template image is a complete and defect-free image of at least one surface of the target object;
as an optional embodiment, the acquiring a suspected defect image of a target object, a template image, and position information of the suspected defect image in the template image includes: and receiving the suspected defect image, the template image and the position information which are sent by the AOI equipment. The template image may be an image taken in advance by the AOI device. In the method, the contents sent by the AOI equipment in the prior art are directly received, and the efficiency of the method is further improved.
Specifically, there are many cases of defects, and the defects on the PCB board may be: the ink covered on the circuit drops due to external factors to expose the color of copper, as shown in fig. 3(a), the portion circled by white circle in fig. 3(a) is the corresponding defect; the printing ink on the circuit or the copper surface falls off to cause copper leakage, and then a layer of gold is formed on the copper surface through a gold melting process; foreign matters exist above the ink or below the ink, so that the ink is uneven or different in color; ink drops on the ink layer, so that the ink is not flat, such as accumulation and the like; the ink is stuck on the bonding pad to cause the color of the bonding pad to be different; originally, the ink-covered area is stripped due to external factors, and as shown in fig. 3(b), the part circled by a white circle in fig. 3(b) is a corresponding defect; the white characters are stuck on the bonding pads to cause the bonding pads to show different colors; a narrow green oil area between two gold surfaces is called a green oil bridge, green oil falling of the green oil bridge is called a green-breaking oil bridge, and as shown in fig. 3(c), a part circled by a white circle in fig. 3(c) is a corresponding defect; the character frame is printed on the pad in an offset manner and is in contact with the pad; the characters are unclear or fall; the periphery of the bonding pad is heterochromatic and generally light black, and the defect is caused by the fact that ink in the bonding pad area is not completely removed.
Step S104, according to the suspected defect image, the template image and the position information, obtaining a template part corresponding to the suspected defect image in the template image;
as an alternative embodiment, the acquiring, according to the suspected defect image, the template image, and the position information, a template portion corresponding to the suspected defect image in the template image includes: determining a preliminary template portion in the template image according to the position information, wherein the preliminary template portion has an area larger than that of the suspected defect image (for example, the suspected defect image has a resolution of 200 × 200, and the preliminary template portion has a resolution of 600 × 600), and the preliminary template portion includes a region corresponding to the position information; and cutting out the template part in the preliminary template part according to the suspected defect image. Because the acquired position information may have deviation, in the scheme, a part with a larger area than the preparation template is selected first, and the part contains complete suspected defect images as much as possible, so that the subsequent detection result is further ensured to be more accurate.
As an alternative embodiment, the cutting out the template portion of the preliminary template portion according to the suspected defect image includes: aligning the suspected defect image with a corresponding portion of the preliminary template portion by a sliding window template matching method; and cutting out a part aligned with the suspected defect image from the preliminary template part to obtain the template part. In the scheme, the template part can be obtained more accurately by adopting a sliding window template matching method, so that the accuracy of the subsequent detection result is further ensured.
Specifically, the suspected defect image and the template part image are shot by the same device in a similar environment, only horizontal and vertical translation exists between the suspected defect image and the template part, rotation and scaling change does not exist, a sliding window template matching method is adopted, the corresponding parts in the suspected defect image and the prepared template part can be aligned more accurately, the suspected defect image moves horizontally and vertically one by one with pixel points in the image of the prepared template part, the mean square error of the overlapped part of the two images is calculated, when the mean square error reaches the minimum, the two images are determined to be aligned, the part aligned with the suspected defect image is intercepted, and the more accurate and aligned template part can be obtained.
Specifically, the template image is extracted as shown in fig. 4(a) to obtain a preliminary template portion, as shown in fig. 4(b), in which a portion framed by a rectangular frame is a portion of the preliminary template portion aligned with the suspected defect image, which is actually a template portion, and the suspected defect image is extracted as shown in fig. 4(c), and the template portion obtained by extracting the portion framed by the rectangular frame in fig. 4(b) is shown in fig. 4 (d).
And step S106, detecting whether the suspected defect image has target defects or not according to the template part and the suspected defect image.
According to the scheme, a suspected defect image of a target object, a template image and position information of the suspected defect image in the template image are obtained; acquiring a template part corresponding to the suspected defect image in the template image according to the suspected defect image, the template image and the position information; detecting whether the suspected defect image has a target defect or not according to the template part and the suspected defect image; according to the scheme, whether the target defect exists in the suspected defect image can be automatically detected, manual detection is not needed, the detection efficiency is higher, and the technical problem that the defect detection efficiency is lower due to manual detection is solved. In addition, the scheme greatly improves the accuracy and stability of detecting the target defects.
As an alternative embodiment, the detecting whether the suspected defect image has the target defect according to the template portion and the suspected defect image includes: detecting the defects in the suspected defect image according to the template part to obtain the types of the defects and the labeling graphs of the defects, wherein the types comprise linear types and bulk types; and determining whether the corresponding defect is the target defect according to the dimension information of the marked graph. According to the scheme, whether the defect in the suspected defect image is the target defect or not can be determined more accurately through the dimension information of the marked graph.
Specifically, the types of defects mainly include two major types, a line type including at least scratches and cracks, and a bulk type including at least inks and copper leaks.
As an optional embodiment, the detecting the defect in the suspected-defect image according to the template portion to obtain the type of the defect and the label graph of the defect includes: splicing the suspected defect image and the template part into a six-channel image; inputting the six-channel image into an FCOS network detector to obtain the type of the defect and the labeling graph of the defect. In the scheme, the suspected defect image and the template part are spliced to form a six-channel image, and then the image is input into the detector, so that the detection result is more accurate.
Of course, in a specific implementation process, the splicing and fusing process may also be performed in an input detector, that is, the suspected defect image and the template portion are input to the detector, and then the detector fuses features of the suspected defect image and the template portion, so as to perform detection and judgment, and obtain a corresponding result.
In addition, the network detector of the present application is not limited to the above-mentioned FCOS network detector, and may be other feasible network detectors, and those skilled in the art may select a suitable network detector according to the actual situation.
In addition, in the model training process of training the network detector, the defects of the training images can be marked with masks, so that the length and the area can be calculated according to the masks. However, the cost of mask labeling is too high, and we label the linear defects with the detection box and label the bulk defects with the mask.
As an optional embodiment, the label graph is a label detection box. The labeling graph is simpler and easier to realize, so that the detection efficiency of the detection method is higher, and of course, other graphs can be used for labeling in practical application.
As an optional embodiment, the determining whether the corresponding defect is the target defect according to the size information of the label graph includes: determining whether a length of a diagonal line of the mark detection frame is greater than a predetermined length in a case where the type of the defect is the line type; and determining the corresponding defect as the target defect when the length of the diagonal line of the mark detection frame is greater than a predetermined length.
Specifically, the linear type defect is determined whether the linear type defect is a target defect by judging whether the length of the diagonal line of the marking detection frame is greater than a predetermined length, and when the length of the diagonal line is greater than the predetermined length, the current linear type defect can be more accurately determined to be the target defect.
As an optional embodiment, the determining whether the corresponding defect is the target defect according to the size information of the label graph includes: when the defect type is the blob type, intercepting a region to be detected in the suspected defect image by taking the center of the mark detection frame corresponding to the blob type as the center, wherein the region to be detected comprises the corresponding mark detection frame; performing semantic segmentation on the to-be-detected region to obtain a segmentation result; calculating the area of the corresponding defect according to the segmentation result; and determining the defect as the target defect when the area is larger than a predetermined area.
Specifically, the blob type defect is determined whether the blob type defect is a target defect by judging whether the area of the defect is larger than a predetermined area, and when the area of the defect is larger than the predetermined area, the current blob type defect can be more accurately determined to be the target defect.
In an alternative embodiment, after determining the defect as the target defect, the target defect may be reported to the manufacturer, and the manufacturer may perform subsequent processing.
As an optional embodiment, the performing semantic segmentation on the region to be detected to obtain a segmentation result includes: and performing semantic segmentation on the to-be-detected region by using a full convolution network based on Unet to obtain the segmentation result.
Specifically, the full convolution network of the Unet is adopted to perform semantic segmentation on the region to be detected, so that an accurate segmentation result can be obtained, and the obtained detection result is further ensured to be accurate.
As an alternative embodiment, the target object is a PCB board. Of course, the method of the present application can also be applied to other objects with defects.
Specifically, the target defect detected by the scheme of the present application is shown in fig. 5(a), a portion framed by a white rectangular frame in the figure is the target defect, the further detected target defect is shown in fig. 5(b), and a portion framed by a white rectangular frame in the figure is another target defect.
It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the invention. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required by the invention.
Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
Example 2
An embodiment of the present invention further provides a defect detection system, as shown in fig. 6, the system includes an AOI device 100 and a defect detection apparatus 200, where the AOI device 100 is configured to obtain a suspected defect image of a PCB, a template image, and position information of the suspected defect image in the template image; the defect inspection apparatus 200 is communicatively connected to the AOI device 100 described above for performing the inspection method of embodiment 1.
Optionally, in this embodiment, the detecting device is configured to perform: acquiring a suspected defect image of a target object, a template image and position information of the suspected defect image in the template image; acquiring a template part corresponding to the suspected defect image in the template image according to the suspected defect image, the template image and the position information; and detecting whether the suspected defect image has a target defect or not according to the template part and the suspected defect image.
Optionally, in this embodiment, the detecting device is configured to perform: the acquiring a template portion corresponding to the suspected defect image in the template image according to the suspected defect image, the template image and the position information includes: determining a preliminary template portion in the template image based on the position information, the preliminary template portion having an area larger than an area of the suspected defect image and including a region corresponding to the position information; and cutting out the template part in the preliminary template part according to the suspected defect image.
Optionally, in this embodiment, the detecting device is configured to perform: the cutting out the template section of the preliminary template section based on the suspected defect image includes: aligning the suspected defect image with a corresponding portion of the preliminary template portion by a sliding window template matching method; and cutting out a part aligned with the suspected defect image from the preliminary template part to obtain the template part.
Optionally, in this embodiment, the detecting device is configured to perform: the detecting whether the suspected defect image has the target defect according to the template part and the suspected defect image includes: detecting the defects in the suspected defect image according to the template part to obtain the types of the defects and the labeling graphs of the defects, wherein the types comprise linear types and bulk types; and determining whether the corresponding defect is the target defect according to the dimension information of the marked graph.
Optionally, in this embodiment, the detecting device is configured to perform: according to the template part, detecting the defect in the suspected defect image to obtain the type of the defect and the labeling graph of the defect, comprising the following steps: splicing the suspected defect image and the template part into a six-channel image; inputting the six-channel image into an FCOS network detector to obtain the type of the defect and the labeling graph of the defect.
Optionally, in this embodiment, the detecting device is configured to perform: the marked graph is a marked detection frame.
Optionally, in this embodiment, the detecting device is configured to perform: the determining whether the corresponding defect is a target defect according to the size information of the marked graph includes: determining whether a length of a diagonal line of the mark detection frame is greater than a predetermined length in a case where the type of the defect is the line type; and determining the corresponding defect as the target defect when the length of the diagonal line of the mark detection frame is greater than a predetermined length.
Optionally, in this embodiment, the detecting device is configured to perform: the determining whether the corresponding defect is a target defect according to the size information of the marked graph includes: when the defect type is the blob type, intercepting a region to be detected in the suspected defect image by taking the center of the mark detection frame corresponding to the blob type as the center, wherein the region to be detected comprises the corresponding mark detection frame; performing semantic segmentation on the to-be-detected region to obtain a segmentation result; calculating the area of the corresponding defect according to the segmentation result; and determining the defect as the target defect when the area is larger than a predetermined area.
Optionally, in this embodiment, the detecting device is configured to perform: the above performing semantic segmentation on the to-be-detected region to obtain a segmentation result includes: and performing semantic segmentation on the to-be-detected region by using a full convolution network based on Unet to obtain the segmentation result.
Optionally, in this embodiment, the detecting device is configured to perform: the method for acquiring the suspected defect image, the template image and the position information of the suspected defect image of the target object in the template image comprises the following steps: and receiving the suspected defect image, the template image and the position information which are sent by the AOI equipment.
Example 3
The invention also provides a defect detection method, as shown in fig. 7, the method comprises the following steps:
step S202, the cloud server obtains a suspected defect image of the target object, a template image and position information of the suspected defect image in the template image, wherein the suspected defect image is an image suspected of having a defect, generally speaking, the suspected defect image is an image of a part of a certain surface of the target object, and the template image is a complete and defect-free image of at least one surface of the target object;
as an optional embodiment, the acquiring, by a cloud server, a suspected defect image of a target object, a template image, and position information of the suspected defect image in the template image includes: and the cloud server receives the suspected defect image, the template image and the position information which are sent by the AOI equipment. The template image may be an image taken in advance by the AOI device. In the method, the contents sent by the AOI equipment in the prior art are directly received, and the efficiency of the method is further improved.
Specifically, there are many cases of defects, and the defects on the PCB board may be: the ink covered on the circuit drops due to external factors to expose the color of copper, as shown in fig. 3(a), the portion circled by white circle in fig. 3(a) is the corresponding defect; the printing ink on the circuit or the copper surface falls off to cause copper leakage, and then a layer of gold is formed on the copper surface through a gold melting process; foreign matters exist above the ink or below the ink, so that the ink is uneven or different in color; ink drops on the ink layer, so that the ink is not flat, such as accumulation and the like; the ink is stuck on the bonding pad to cause the color of the bonding pad to be different; originally, the ink-covered area is stripped due to external factors, and as shown in fig. 3(b), the part circled by a white circle in fig. 3(b) is a corresponding defect; the white characters are stuck on the bonding pads to cause the bonding pads to show different colors; a narrow green oil area between two gold surfaces is called a green oil bridge, green oil falling of the green oil bridge is called a green-breaking oil bridge, and as shown in fig. 3(c), a part circled by a white circle in fig. 3(c) is a corresponding defect; the character frame is printed on the pad in an offset manner and is in contact with the pad; the characters are unclear or fall; the periphery of the bonding pad is heterochromatic and generally light black, and the defect is caused by the fact that ink in the bonding pad area is not completely removed.
Step S204, the cloud server acquires a template part corresponding to the suspected defect image in the template image according to the suspected defect image, the template image and the position information;
as an optional embodiment, the acquiring, by the cloud server, a template portion corresponding to the suspected defect image in the template image according to the suspected defect image, the template image, and the position information includes: the cloud server determines, based on the position information, a preliminary template portion in the template image, the preliminary template portion having an area larger than an area of the suspected defect image (for example, the suspected defect image has a resolution of 200 × 200, and the preliminary template portion has a resolution of 600 × 600), and the preliminary template portion includes an area corresponding to the position information; and the cloud server intercepts the template part in the preparation template part according to the suspected defect image. Because the acquired position information may have deviation, in the scheme, a part with a larger area than the preparation template is selected first, and the part contains complete suspected defect images as much as possible, so that the subsequent detection result is further ensured to be more accurate.
As an optional embodiment, the intercepting, by the cloud server, the template part in the preliminary template part according to the suspected-defect image includes: the cloud server aligns the suspected defect image with a corresponding part in the preparation template part by adopting a sliding window template matching method; the cloud server cuts out a portion aligned with the suspected defect image from the preliminary template portion to obtain the template portion. In the scheme, the template part can be obtained more accurately by adopting a sliding window template matching method, so that the accuracy of the subsequent detection result is further ensured.
Specifically, the suspected defect image and the template part image are shot by the same device in a similar environment, only horizontal and vertical translation exists between the suspected defect image and the template part, rotation and scaling change does not exist, a sliding window template matching method is adopted, the corresponding parts in the suspected defect image and the prepared template part can be aligned more accurately, the suspected defect image moves horizontally and vertically one by one with pixel points in the image of the prepared template part, the mean square error of the overlapped part of the two images is calculated, when the mean square error reaches the minimum, the two images are determined to be aligned, the part aligned with the suspected defect image is intercepted, and the more accurate and aligned template part can be obtained.
Specifically, the template image is extracted as shown in fig. 4(a) to obtain a preliminary template portion, as shown in fig. 4(b), in which a portion framed by a rectangular frame is a portion of the preliminary template portion aligned with the suspected defect image, which is actually a template portion, and the suspected defect image is extracted as shown in fig. 4(c), and the template portion obtained by extracting the portion framed by the rectangular frame in fig. 4(b) is shown in fig. 4 (d).
In step S206, the cloud server detects whether the suspected defect image has a target defect according to the template portion and the suspected defect image.
In the scheme of the application, a cloud server acquires a suspected defect image of a target object, a template image and position information of the suspected defect image in the template image; the cloud server acquires a template part corresponding to the suspected defect image in the template image according to the suspected defect image, the template image and the position information; the cloud server detects whether the suspected defect image has a target defect according to the template part and the suspected defect image; the cloud server can automatically detect whether the suspected defect image has the target defect or not without manual detection, so that the detection efficiency is higher, and the technical problem that the defect detection efficiency is lower due to manual detection is solved. In addition, the scheme greatly improves the accuracy and stability of detecting the target defects.
As an optional embodiment, the detecting, by the cloud server, whether the suspected-defect image has a target defect according to the template part and the suspected-defect image includes: the cloud server detects the defects in the suspected defect image according to the template part to obtain the types of the defects and the labeling graphs of the defects, wherein the types comprise linear types and bulk types; and the cloud server determines whether the corresponding defect is the target defect according to the size information of the marked graph. According to the scheme, whether the defect in the suspected defect image is the target defect or not can be determined more accurately through the dimension information of the marked graph.
Specifically, the types of defects mainly include two major types, a line type including at least scratches and cracks, and a bulk type including at least inks and copper leaks.
As an optional embodiment, the detecting, by the cloud server, the defect in the suspected-defect image according to the template part to obtain the type of the defect and a label graph of the defect includes: the cloud server splices the suspected defect image and the template part into a six-channel image; and the cloud server inputs the six-channel image into an FCOS network detector to obtain the type of the defect and the labeling graph of the defect. In the scheme, the suspected defect image and the template part are spliced to form a six-channel image, and then the image is input into the detector, so that the detection result is more accurate.
Of course, in a specific implementation process, the splicing and fusing process may also be performed in an input detector, that is, the suspected defect image and the template portion are input to the detector, and then the detector fuses features of the suspected defect image and the template portion, so as to perform detection and judgment, and obtain a corresponding result.
In addition, the network detector of the present application is not limited to the above-mentioned FCOS network detector, and may be other feasible network detectors, and those skilled in the art may select a suitable network detector according to the actual situation.
In addition, in the model training process of training the network detector, the defects of the training images can be marked with masks, so that the length and the area can be calculated according to the masks. However, the cost of mask labeling is too high, and we label the linear defects with the detection box and label the bulk defects with the mask.
As an optional embodiment, the label graph is a label detection box. The labeling graph is simpler and easier to realize, so that the detection efficiency of the detection method is higher, and of course, other graphs can be used for labeling in practical application.
As an optional embodiment, the determining, by the cloud server, whether the corresponding defect is a target defect according to the size information of the labeled graph includes: in a case where the type of the defect is the line type, the cloud server determines whether a length of a diagonal line of the mark detection box is greater than a predetermined length; and when the length of the diagonal line of the mark detection frame is greater than a predetermined length, the cloud server determines the corresponding defect as the target defect.
Specifically, the linear type defect is determined whether the linear type defect is a target defect by judging whether the length of the diagonal line of the marking detection frame is greater than a predetermined length, and when the length of the diagonal line is greater than the predetermined length, the current linear type defect can be more accurately determined to be the target defect.
As an optional embodiment, the determining, by the cloud server, whether the corresponding defect is a target defect according to the size information of the labeled graph includes: when the defect type is the blob type, the cloud server intercepts a to-be-detected area from the suspected defect image by taking the center of the label detection frame corresponding to the blob type as the center, wherein the to-be-detected area comprises the corresponding label detection frame; the cloud server carries out semantic segmentation on the to-be-detected area to obtain a segmentation result; calculating the area of the corresponding defect according to the segmentation result of the cloud server; when the area is larger than a predetermined area, the cloud server determines that the defect is the target defect.
Specifically, the blob type defect is determined whether the blob type defect is a target defect by judging whether the area of the defect is larger than a predetermined area, and when the area of the defect is larger than the predetermined area, the current blob type defect can be more accurately determined to be the target defect.
In an alternative embodiment, after determining the defect as the target defect, the target defect may be reported to the manufacturer, and the manufacturer may perform subsequent processing.
As an optional embodiment, the performing, by the cloud server, semantic segmentation on the to-be-detected region to obtain a segmentation result includes: and the cloud server performs semantic segmentation on the to-be-detected region by using a full convolution network based on Unet to obtain the segmentation result.
Specifically, the cloud server performs semantic segmentation on the to-be-detected region by using a full convolution network of the Unet, so that an accurate segmentation result can be obtained, and the obtained detection result is further ensured to be accurate.
As an alternative embodiment, the target object is a PCB board. Of course, the method of the present application can also be applied to other objects with defects.
Specifically, the target defect detected by the scheme of the present application is shown in fig. 5(a), a portion framed by a white rectangular frame in the figure is the target defect, the further detected target defect is shown in fig. 5(b), and a portion framed by a white rectangular frame in the figure is another target defect.
It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the invention. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required by the invention.
Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by a program instructing hardware associated with the terminal device, where the program may be stored in a computer-readable storage medium, and the storage medium may include: flash disks, Read-Only memories (ROMs), Random Access Memories (RAMs), magnetic or optical disks, and the like.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the above-described division of the units is only one type of division of logical functions, and other divisions may be realized in practice, 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 shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit may be stored in a computer-readable storage medium if it is implemented in the form of a software functional unit and sold or used as a separate product. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the above methods according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (13)
1. A method for detecting defects, comprising:
acquiring a suspected defect image, a template image and position information of the suspected defect image in the template image of a target object;
according to the suspected defect image, the template image and the position information, acquiring a template part corresponding to the suspected defect image in the template image;
and detecting whether the suspected defect image has target defects or not according to the template part and the suspected defect image.
2. The method of detecting a defect according to claim 1, wherein the obtaining a template portion corresponding to the suspected defect image in the template image based on the suspected defect image, the template image, and the position information includes:
determining a preliminary template part in the template image according to the position information, wherein the area of the preliminary template part is larger than that of the suspected defect image, and the preliminary template part comprises a region corresponding to the position information;
and intercepting the template part in the preparation template part according to the suspected defect image.
3. The method of claim 2, wherein the truncating the template portion of the preliminary template portion from the suspected defect image comprises:
aligning the suspected defect image with a corresponding part in the preparation template part by adopting a sliding window template matching method;
and cutting out the part aligned with the suspected defect image from the preparation template part to obtain the template part.
4. The method according to any one of claims 1 to 3, wherein the detecting whether the suspected defect image has a target defect or not according to the template portion and the suspected defect image comprises:
detecting the defects in the suspected defect image according to the template part to obtain the types of the defects and the labeling graphs of the defects, wherein the types comprise linear types and bulk types;
and determining whether the corresponding defect is the target defect or not according to the dimension information of the marked graph.
5. The method according to claim 4, wherein detecting the defect in the suspected-defect image according to the template portion to obtain the type of the defect and the label graph of the defect comprises:
splicing the suspected defect image and the template part into a six-channel image;
and inputting the six-channel image into an FCOS network detector to obtain the type of the defect and the labeling graph of the defect.
6. The method of claim 4, wherein the label graph is a label detection box.
7. The method for detecting the defect of claim 6, wherein the determining whether the corresponding defect is the target defect according to the dimension information of the labeled graph comprises:
determining whether the length of a diagonal line of the marking detection frame is greater than a predetermined length when the type of the defect is the linear type;
and under the condition that the length of the diagonal line of the mark detection frame is greater than a preset length, determining the corresponding defect as the target defect.
8. The method for detecting the defect of claim 6, wherein the determining whether the corresponding defect is the target defect according to the dimension information of the labeled graph comprises:
under the condition that the defect type is the blob type, intercepting a region to be detected in the suspected defect image by taking the center of the mark detection frame corresponding to the blob type as the center, wherein the region to be detected comprises the corresponding mark detection frame;
performing semantic segmentation on the region to be detected to obtain a segmentation result;
calculating the area of the corresponding defect according to the segmentation result;
determining the defect as the target defect if the area is greater than a predetermined area.
9. The method according to claim 8, wherein the semantic segmentation of the region to be detected to obtain a segmentation result comprises:
and performing semantic segmentation on the to-be-detected region by using a full convolution network based on Unet to obtain the segmentation result.
10. The method for detecting the defect according to any one of claims 1 to 3, wherein acquiring the suspected defect image of the target object, the template image and the position information of the suspected defect image in the template image comprises:
and receiving the suspected defect image, the template image and the position information which are sent by the AOI equipment.
11. The method of detecting defects according to any one of claims 1 to 3, wherein the target object is a PCB board.
12. A system for detecting defects, comprising:
the AOI equipment is used for acquiring a suspected defect image of a PCB, a template image and position information of the suspected defect image in the template image;
defect detection means, communicatively connected to said AOI device, for performing the detection method of any one of claims 1 to 11.
13. A method for detecting defects, comprising:
the method comprises the steps that a cloud server obtains a suspected defect image, a template image and position information of the suspected defect image in the template image of a target object;
the cloud server acquires a template part corresponding to the suspected defect image in the template image according to the suspected defect image, the template image and the position information;
and the cloud server detects whether the suspected defect image has a target defect according to the template part and the suspected defect image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110699282.9A CN113609897A (en) | 2021-06-23 | 2021-06-23 | Defect detection method and defect detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110699282.9A CN113609897A (en) | 2021-06-23 | 2021-06-23 | Defect detection method and defect detection system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113609897A true CN113609897A (en) | 2021-11-05 |
Family
ID=78336741
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110699282.9A Pending CN113609897A (en) | 2021-06-23 | 2021-06-23 | Defect detection method and defect detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113609897A (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005079154A2 (en) * | 2004-02-19 | 2005-09-01 | Camtek Ltd. | A method and a system for real-time defects verification |
| KR20170022346A (en) * | 2015-08-20 | 2017-03-02 | 충북대학교 산학협력단 | System and Method for Classification of PCB fault and Type of Fault |
| CN110473170A (en) * | 2019-07-10 | 2019-11-19 | 苏州卓融新能源科技有限公司 | A kind of artificial intelligence detection method suitable for the true and false determining defects of pcb board |
| CN110570393A (en) * | 2019-07-31 | 2019-12-13 | 华南理工大学 | mobile phone glass cover plate window area defect detection method based on machine vision |
| US20200126202A1 (en) * | 2018-10-23 | 2020-04-23 | International Business Machines Corporation | Detection for abnormal connectivity on a product |
| CN111080615A (en) * | 2019-12-12 | 2020-04-28 | 创新奇智(重庆)科技有限公司 | PCB defect detection system and detection method based on convolutional neural network |
| CN111241966A (en) * | 2020-01-06 | 2020-06-05 | 广东工业大学 | Invoice target area positioning method, device, equipment and medium |
| CN111368915A (en) * | 2020-03-04 | 2020-07-03 | 广东博智林机器人有限公司 | Drawing verification method, device, equipment and storage medium |
| CN111474184A (en) * | 2020-04-17 | 2020-07-31 | 河海大学常州校区 | AOI character defect detection method and device based on industrial machine vision |
| KR102174424B1 (en) * | 2019-05-24 | 2020-11-04 | 충북대학교 산학협력단 | Method for Inspecting Component basesd Server and system and apparatus therefor |
| CN111986178A (en) * | 2020-08-21 | 2020-11-24 | 北京百度网讯科技有限公司 | Product defect detection method and device, electronic equipment and storage medium |
| CN112053318A (en) * | 2020-07-20 | 2020-12-08 | 清华大学 | Two-dimensional PCB defect real-time automatic detection and classification device based on deep learning |
| WO2021027184A1 (en) * | 2019-08-09 | 2021-02-18 | 苏州康代智能科技股份有限公司 | Pcb maintenance system and maintenance method based on false point defect detection |
| CN112837302A (en) * | 2021-02-09 | 2021-05-25 | 广东拓斯达科技股份有限公司 | Mold state monitoring method and device, industrial personal computer, storage medium and system |
-
2021
- 2021-06-23 CN CN202110699282.9A patent/CN113609897A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005079154A2 (en) * | 2004-02-19 | 2005-09-01 | Camtek Ltd. | A method and a system for real-time defects verification |
| KR20170022346A (en) * | 2015-08-20 | 2017-03-02 | 충북대학교 산학협력단 | System and Method for Classification of PCB fault and Type of Fault |
| US20200126202A1 (en) * | 2018-10-23 | 2020-04-23 | International Business Machines Corporation | Detection for abnormal connectivity on a product |
| KR102174424B1 (en) * | 2019-05-24 | 2020-11-04 | 충북대학교 산학협력단 | Method for Inspecting Component basesd Server and system and apparatus therefor |
| CN110473170A (en) * | 2019-07-10 | 2019-11-19 | 苏州卓融新能源科技有限公司 | A kind of artificial intelligence detection method suitable for the true and false determining defects of pcb board |
| CN110570393A (en) * | 2019-07-31 | 2019-12-13 | 华南理工大学 | mobile phone glass cover plate window area defect detection method based on machine vision |
| WO2021027184A1 (en) * | 2019-08-09 | 2021-02-18 | 苏州康代智能科技股份有限公司 | Pcb maintenance system and maintenance method based on false point defect detection |
| CN111080615A (en) * | 2019-12-12 | 2020-04-28 | 创新奇智(重庆)科技有限公司 | PCB defect detection system and detection method based on convolutional neural network |
| CN111241966A (en) * | 2020-01-06 | 2020-06-05 | 广东工业大学 | Invoice target area positioning method, device, equipment and medium |
| CN111368915A (en) * | 2020-03-04 | 2020-07-03 | 广东博智林机器人有限公司 | Drawing verification method, device, equipment and storage medium |
| CN111474184A (en) * | 2020-04-17 | 2020-07-31 | 河海大学常州校区 | AOI character defect detection method and device based on industrial machine vision |
| CN112053318A (en) * | 2020-07-20 | 2020-12-08 | 清华大学 | Two-dimensional PCB defect real-time automatic detection and classification device based on deep learning |
| CN111986178A (en) * | 2020-08-21 | 2020-11-24 | 北京百度网讯科技有限公司 | Product defect detection method and device, electronic equipment and storage medium |
| CN112837302A (en) * | 2021-02-09 | 2021-05-25 | 广东拓斯达科技股份有限公司 | Mold state monitoring method and device, industrial personal computer, storage medium and system |
Non-Patent Citations (2)
| Title |
|---|
| 李正明;黎宏;孙俊;: "基于数字图像处理的印刷电路板缺陷检测", 仪表技术与传感器, no. 08, pages 87 - 89 * |
| 梁玮等著: "《计算机视觉》", 31 January 2021, 北京：北京理工大学出版社, pages: 157 - 160 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TW202107073A (en) | System and method for pcb inspection based on false defect detection | |
| CN105335963A (en) | Edge defect detection method and apparatus | |
| US9471972B2 (en) | Solder print inspecting device | |
| US10832399B2 (en) | Detection for abnormal connectivity on a product | |
| CN102608107A (en) | Automatic test piece interpretation method and system | |
| CN111951210A (en) | Data processing method, device and equipment | |
| US20220292661A1 (en) | Automated inspection system and operating method thereof | |
| CN113870175A (en) | Defect detection method, device, system, storage medium and processor | |
| CN115829929A (en) | Method, device and equipment for detecting defects of product surface image and storage medium | |
| CN112258507A (en) | Target object detection method and device of internet data center and electronic equipment | |
| CN114022436A (en) | Detection method, device and detection equipment for printed circuit board | |
| CN117132583A (en) | Wafer defect detection method and device, electronic equipment and nonvolatile storage medium | |
| CN115861327A (en) | PCB color change defect detection method, device, equipment and medium | |
| US20240168465A1 (en) | Rapid automation system and method for line clearance | |
| CN117589770A (en) | PCB patch board detection method, device, equipment and medium | |
| CN118097682A (en) | Watermark character recognition method and device, nonvolatile storage medium and electronic equipment | |
| CN113609897A (en) | Defect detection method and defect detection system | |
| CN117952941A (en) | Circuit board defect detection method and device | |
| CN105136818A (en) | Printing substrate image detecting method | |
| CN110516375B (en) | Abnormal board card detection method and device, electronic equipment and storage medium | |
| CN110058439B (en) | Method and apparatus for removing foreign matter on color filter | |
| CN109765704B (en) | Method and device for determining production equipment causing product defects | |
| CN115147386A (en) | Defect detection method and device for U-shaped pipe and electronic equipment | |
| CN115661155A (en) | Defect detection model construction method, device, equipment and storage medium | |
| JP2016099633A (en) | Maintenance inspection system using a portable terminal |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20240308 Address after: # 03-06, Lai Zan Da Building 1, 51 Belarusian Road, Singapore Applicant after: Alibaba Innovation Co. Country or region after: Singapore Address before: Room 01, 45th Floor, AXA Building, 8 Shanton Road, Singapore Applicant before: Alibaba Singapore Holdings Ltd. Country or region before: Singapore |
|
| TA01 | Transfer of patent application right |