CN117575995A - Device defect detection method, device, computer equipment and storage medium - Google Patents
Device defect detection method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN117575995A CN117575995A CN202311376792.8A CN202311376792A CN117575995A CN 117575995 A CN117575995 A CN 117575995A CN 202311376792 A CN202311376792 A CN 202311376792A CN 117575995 A CN117575995 A CN 117575995A
- Authority
- CN
- China
- Prior art keywords
- defect
- detection
- target
- image
- detected
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 403
- 230000007547 defect Effects 0.000 title claims abstract description 391
- 238000004590 computer program Methods 0.000 claims description 36
- 238000000034 method Methods 0.000 claims description 32
- 238000004364 calculation method Methods 0.000 claims description 29
- 238000007689 inspection Methods 0.000 claims description 8
- 238000010586 diagram Methods 0.000 description 10
- 238000012549 training Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 238000012805 post-processing Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 239000000919 ceramic Substances 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 230000032798 delamination Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Multimedia (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The application relates to a device defect detection method, a device, computer equipment and a storage medium, wherein the type of a defect to be detected is determined according to a target image identifier of a detection image; selecting a target detection model corresponding to the defect type to be detected from the candidate detection models; and finally, performing defect detection on the detected image by adopting a target detection model. According to the device defect detection method, the type of the defect to be detected can be automatically identified according to the target image identification of the detection image, and the target detection model corresponding to the type of the defect to be detected can be screened out, so that the detection of various defect images is automatically realized, and the device defect detection efficiency is improved; in addition, each candidate detection model is used for detecting different defects, can be suitable for more defect detection scenes, and expands the application range of the defect detection method.
Description
Technical Field
The present disclosure relates to the field of artificial intelligence, and in particular, to a device defect detection method, device, computer apparatus, and storage medium.
Background
With the development of electronic manufacturing technology, the production scale of chips is increasing. However, during the production of the chip, there may be some physical defects of the chip, such as delamination in the ceramic chip, voids in the sealed chip, scratches on the appearance of the chip, deformation of the leads, and the like.
When the scale of the generated chip is large, the detection of the defects is difficult to be completed manually, and the detection efficiency of the chip is seriously affected by means of manual inspection.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a device defect detection method, apparatus, computer device, and storage medium, which can improve the efficiency of device defect detection.
In a first aspect, the present application provides a device defect detection method, the method including:
acquiring a detection image of a device to be detected;
determining the type of the defect to be detected according to the target image identification of the detection image;
selecting a target detection model corresponding to the defect type to be detected from the candidate detection models;
and performing defect detection on the detection image by adopting the target detection model.
In one embodiment, the determining the type of the defect to be detected according to the target image identifier of the detection image includes:
And determining the type of the defect to be detected according to the target image identification of the detection image based on the corresponding relation between the candidate image identification and the candidate defect type.
In one embodiment, the performing defect detection on the detected image using the target detection model includes:
detecting whether the detected image has the target defect of the defect type to be detected or not by adopting the target detection model;
if the target defect exists, determining a target detection result of the detection image according to the size relation between the defect size of the target defect and a preset size threshold; the target detection result is used for representing whether the device to be detected is a qualified device or a disqualified device.
In one embodiment, the determining the target detection result of the detection image according to the size relationship between the defect size of the target defect and the preset size threshold includes:
if the defect size of the target defect is larger than a preset size threshold, determining a target detection result used for representing that the device to be detected is a disqualified device;
and if the defect size of the target defect is smaller than or equal to the preset size threshold, determining a target detection result used for representing that the device to be detected is a qualified device.
In one embodiment, the method further comprises:
extracting a region image containing the target defect from the detection image;
determining a defect calculation mode according to the shape of the target defect;
and determining the defect size of the target defect according to the area image by adopting the defect calculation mode.
In one embodiment, the determining the type of the defect to be detected according to the target image identifier of the detection image includes:
determining target acquisition equipment from candidate acquisition equipment according to the target image identification of the detection image;
and determining the type of the defect to be detected according to the image acquisition type of the target acquisition equipment.
In one embodiment, the method further comprises:
acquiring a detection image of the device to be detected from a local image storage space; the detection image is written into the local image storage space for the target acquisition equipment.
In a second aspect, the present application further provides a device defect detection apparatus, the apparatus including:
the acquisition module is used for acquiring a detection image of the device to be detected;
the determining module is used for determining the type of the defect to be detected according to the target image identification of the detection image;
The selection module is used for selecting a target detection model corresponding to the defect type to be detected from the candidate detection models;
and the detection module is used for detecting defects of the detection image by adopting the target detection model.
In a third aspect, the present application also provides a computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
acquiring a detection image of a device to be detected;
determining the type of the defect to be detected according to the target image identification of the detection image;
selecting a target detection model corresponding to the defect type to be detected from the candidate detection models;
and performing defect detection on the detection image by adopting the target detection model.
In a fourth aspect, the present application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
acquiring a detection image of a device to be detected;
determining the type of the defect to be detected according to the target image identification of the detection image;
Selecting a target detection model corresponding to the defect type to be detected from the candidate detection models;
and performing defect detection on the detection image by adopting the target detection model.
In a fifth aspect, the present application also provides a computer program product comprising a computer program which, when executed by a processor, performs the steps of:
acquiring a detection image of a device to be detected;
determining the type of the defect to be detected according to the target image identification of the detection image;
selecting a target detection model corresponding to the defect type to be detected from the candidate detection models;
and performing defect detection on the detection image by adopting the target detection model.
The device defect detection method, the device, the computer equipment and the storage medium determine the type of the defect to be detected according to the target image identification of the detection image; selecting a target detection model corresponding to the defect type to be detected from the candidate detection models; and finally, performing defect detection on the detected image by adopting a target detection model. According to the scheme, the type of the defect to be detected can be automatically identified according to the target image identification of the detection image, and the target detection model corresponding to the type of the defect to be detected can be screened out, so that various defect images can be automatically detected, and the defect detection efficiency of the device is improved; in addition, each candidate detection model is used for detecting different defects, can be suitable for more defect detection scenes, and expands the application range of the defect detection method.
Drawings
FIG. 1 is a diagram of an application environment for a device defect detection method in one embodiment;
FIG. 2 is a flow chart of a method of device defect detection in one embodiment;
FIG. 3 is a flow chart of a method for determining a type of defect to be detected in one embodiment;
FIG. 4 is a flow chart of a method of determining defect sizes in one embodiment;
FIG. 5 is a flow diagram of training candidate detection models in one embodiment;
FIG. 6 is a flow chart of a method for detecting device defects in another embodiment;
FIG. 7 is a schematic diagram of an implementation process of detecting a detection image in one embodiment;
FIG. 8 is a schematic diagram of a microscope and computer connection in one embodiment;
FIG. 9 is a block diagram of a device defect detection apparatus in one embodiment;
FIG. 10 is a block diagram of a device defect detection apparatus in another embodiment;
FIG. 11 is an internal block diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The device defect detection method provided by the embodiment of the application can be suitable for detecting whether the device has a defect or not. The method may be performed by a terminal. For example, fig. 1 is an application environment diagram of a device defect detection method provided in an embodiment of the present application. Wherein, a detection application is deployed in the detection terminal 102, and the detection application integrates a plurality of candidate detection models. The detection terminal 102 receives the detection image sent by the acquisition device 104, determines the type of the defect to be detected according to the image identification of the detection image, automatically matches a detection model corresponding to the type of the defect to be detected according to the type of the defect to be detected, and detects the detection image by using the detection model.
The detection terminal 102 and the acquisition device 104 may transmit data through a network, or may transmit data through a data connection line, and the data received by the detection terminal 102 may be stored in a local image storage space. The detection terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices and portable wearable devices, where the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart vehicle devices, and the like. The portable wearable device may be a smart watch, smart bracelet, headset, or the like. Acquisition device 104 may be a device for acquiring detection images of different defect types.
In one embodiment, as shown in fig. 2, a device defect detection method is provided, and the method is applied to the detection terminal 102 in fig. 1 for illustration, and includes the following steps:
s201, obtaining a detection image of a device to be detected.
Alternatively, the device to be detected may be understood as a device that needs to be detected; the detection image is an image taken of a device that needs to be detected. The detection image may include various types of images, for example, whether a device to be detected needs to detect whether the appearance has scratches, whether the shape meets the requirement, whether the interior has holes, faults, and the like, and other small elements may also exist in the device to be detected, and whether the small elements in the device to be detected are regular or not needs to be determined. Detecting defects in different aspects of the device to be detected requires capturing different types of detection images.
S202, determining the type of the defect to be detected according to the target image identification of the detection image.
Optionally, the target image identifier is an image identifier of the current detected image. It will be appreciated that after the inspection image is acquired, the inspection image may be identified to distinguish what type of defect the inspection image was used to detect. For example, when the detection image is acquired by the acquisition device, the image is named, and the detection image is used for detecting what type of defect according to different naming of the image.
S203, selecting a target detection model corresponding to the defect type to be detected from the candidate detection models.
Optionally, a detection application may be deployed in the detection device to detect the detected image, where multiple candidate detection models may be integrated in the detection application, and different candidate detection models are used to detect different types of defects, and a target detection model corresponding to the type of defect to be detected needs to be selected from the candidate detection models.
S204, performing defect detection on the detection image by adopting a target detection model.
Optionally, a target detection model is adopted to detect defects of the detection image so as to judge whether the device to be detected has defects of a corresponding type.
Optionally, after determining the target detection result of the detection image, a detection report may also be generated. The inspection report may include information such as attribute information, defect information, and decision criteria for determining the basis of the defect of the device to be inspected. For example, the method can comprise an original image and a comparison image of the device, detailed information of defects, number information of the defects and basis for judging whether the defects exist.
According to the device defect detection method, the type of the defect to be detected is determined according to the target image identification of the detection image; selecting a target detection model corresponding to the defect type to be detected from the candidate detection models; and finally, performing defect detection on the detected image by adopting a target detection model. The defect type to be detected can be automatically identified according to the target image identification of the detection image, and the target detection model corresponding to the defect type to be detected can be screened out, so that various defect images can be automatically detected, and the defect detection efficiency of the device is improved; in addition, each candidate detection model is used for detecting different defects, can be suitable for more defect detection scenes, and expands the application range of the defect detection method.
In one embodiment, the correspondence between the candidate image identifier and the candidate defect type may be pre-established, for example, four types of detection need to be performed on a device, that is, four types of defects are respectively appearance defect detection, internal cavity defect detection, internal fault defect detection, and internal element detection. When detecting different defects, different acquisition devices are required to acquire detection images, and the acquired detection images are transmitted to the specified storage path of the detection terminal 102 so that the detection terminal 102 can acquire the detection images in the specified storage path. After the detection terminal 102 acquires the detection image under the specified storage path, it is required to distinguish what kind of defect the acquired detection image is used for detecting, so that the detection image needs to be identified, and the identification is used for indicating what kind of type the detection image is used for detecting, that is, establishing a correspondence between the candidate image identification and the candidate defect type.
After the detection terminal 102 obtains the detection image under the specified storage path, the type of the defect to be detected can be determined according to the target image identification of the detection image based on the corresponding relationship between the candidate image identification and the candidate defect type, so as to match with a corresponding detection model, thereby realizing automatic detection of multiple defects of the device to be detected.
Further, referring to fig. 3, fig. 3 provides a flow chart of a method for determining a type of defect to be detected. The method specifically comprises the following steps:
s301, determining target acquisition equipment from candidate acquisition equipment according to target image identification of the detection image.
It will be appreciated that different types of defects of the device to be inspected need to be inspected by different inspection images, which need to be acquired by different acquisition devices. For example, an appearance defect of a device to be inspected needs to be collected by a microscope apparatus; whether the defect of the cavity exists in the device to be detected or not needs to be collected by X-ray equipment; whether faults exist in the device to be detected or not needs to be acquired by ultrasonic equipment. Different image identifications are generated when different acquisition devices acquire the pictures, and the generated image identifications can reflect what acquisition device the pictures are acquired by.
In view of this, the target acquisition device may be determined from the candidate acquisition devices according to the target image identification of the detection image, which type of device the detection image is acquired by may be understood as being determined according to the target image identification of the detection image.
S302, determining the type of the defect to be detected according to the image acquisition type of the target acquisition equipment.
After determining which type of the target acquisition device is, the defect type to be detected can be determined according to the image acquisition type of the target acquisition device.
It can be appreciated that the image acquisition type of the target acquisition device is known, and the defect type to be detected can be determined according to the image acquisition type; and further, the automatic detection of various defects of the device is realized, and the detection efficiency of the device is improved.
In one embodiment, acquiring the detection image of the device to be detected may acquire the detection image of the device to be detected from the local image storage space; the detection image is written into a local image storage space for the target acquisition equipment; the local image storage space may be understood as a designated storage path of the detection terminal 102, and may be, for example, a target folder.
Alternatively, the acquisition device 104 may be connected to the detection terminal 102 through a data line, where the acquisition device 104 writes the detection image into a local image storage space of the detection terminal 102, and the detection terminal 102 determines a defect detection type corresponding to the detection image according to the image identifier and matches the defect detection type with a corresponding detection model.
Alternatively, in the case where the acquisition device 104 is not connected to the detection terminal 102, the detection images acquired by different acquisition devices 104 may be imported into the local image storage space of the detection terminal 102, where in this case, the detection terminal 102 may determine, according to the image identifier, a defect detection type corresponding to the detection image, and match the corresponding detection model.
According to the embodiment of the application, the detection image of the device to be detected is obtained in the local image storage space, and the local image storage space comprises the images for detecting various defect types, so that the detection equipment 104 can automatically obtain the detection image, the detection image can be detected in a classified mode, and the efficiency of image detection is improved.
In one embodiment, S204 may be specifically implemented by the following manner:
detecting whether the detected image has target defects of the defect type to be detected or not by adopting a target detection model; if the defect exists, determining a target detection result of the detection image according to the size relation between the defect size of the target defect and a preset size threshold; the target detection result is used for representing whether the device to be detected is a qualified device or a disqualified device.
It can be understood that the degree of the target defect is determined by comparing the defect size of the target defect with the size of the preset size threshold, and the device to be detected is determined to be a qualified device or a disqualified device according to the degree of the target defect.
Further, according to the size relation between the defect size of the target defect and the preset size threshold, determining a target detection result of the detection image, and judging whether the defect size of the target defect is larger than the preset size threshold, if so, determining a target detection result for representing that the device to be detected is a disqualified device; and if the defect size of the target defect is smaller than or equal to the preset size threshold value, determining a target detection result used for representing that the device to be detected is a qualified device.
In one embodiment, before determining whether the defect size of the target defect is greater than the preset size threshold, the defect size of the target defect needs to be obtained, and therefore, fig. 4 provides a flowchart of a method for determining the defect size, referring to fig. 4, specifically including the following steps:
s401, extracting a region image including the target defect from the detected image.
It will be appreciated that a detection device may have a defect only in a certain portion, and corresponds to information that a certain region in a detection image includes a defect, so that the target region may be truncated, that is, a region image including the target defect may be extracted from the detection image, so that subsequent processing may be performed on the region image including the target defect in a targeted manner.
S402, determining a defect calculation mode according to the shape of the target defect.
Optionally, the shape of the target defect may be determined by extracting the defect feature of the area image including the target defect, and then determining the defect calculation mode according to the shape of the target defect. For example, when the shape of the target defect is determined to be a scratch, the defect calculation method may be determined to calculate the length of the scratch; if the shape of the target defect is determined to be an irregular contour, the defect calculation mode can be determined to calculate the area, the length or the width of the contour and other information.
S403, determining the defect size of the target defect according to the region image by adopting a defect calculation mode.
When the defect calculation mode is determined, the defect size of the target defect can be determined according to the area image by adopting the defect calculation mode. For example, when the shape of the target defect is determined to be a scratch, and the determined defect calculation mode is to calculate the length of the scratch, the defect size of the target defect can be determined according to the area image; and then scaling in equal proportion, and calculating to obtain the actual size of the target defect of the detection device.
In the embodiment of the application, the defect size of the target defect is determined by extracting the region image containing the target defect, and the region image containing the target defect can be processed.
In one embodiment, referring to FIG. 5, FIG. 5 provides a flow chart for training candidate detection models. Firstly, a defect gallery is established, wherein pictures in the defect gallery can be taken from a detection mechanism or a chip development unit; and then, marking defects of the pictures according to the chip defect standard by using deep learning marking software. If the picture is blurred, picture enhancement techniques may be employed to improve sharpness. After the pictures are marked, dividing the pictures into a training set, a verification set and a test set according to a preset proportion (for example, 7:2:1), wherein the training set is used for training the detection model, the verification set is used for verifying the precision of the detection model, and the test set is used for testing the detection model. And when the detection model precision is greater than the preset precision (for example, 99%), the training is stopped.
Then using a trained detection model to detect defects, wherein the detection model can determine the detected defect types according to the identification of the picture; a box or polygonal ring may also be used to outline the defective image area; and performing defect size calculation on defects of different shapes according to the standard of the chip, and calculating the length and the area of the defects if any. If the defect size is larger than the preset size threshold, outputting the defect type and the related data of the defect; and if the defect size is not greater than the preset size threshold, outputting a detection result that the device corresponding to the picture is a qualified product. The following describes the process of the device defect detection method in detail.
In one embodiment, referring to fig. 6, fig. 6 provides a flow chart of a device defect detection method, which specifically includes the following steps:
s601, obtaining a detection image of a device to be detected from a local image storage space.
Optionally, the detected image is written into the local image storage space for the target acquisition device. For example, the acquisition device 104 may be connected to the detection terminal 102 through a data line, where the acquisition device 104 writes the detection image into a local image storage space of the detection terminal 102, and the detection terminal 102 determines a defect detection type corresponding to the detection image according to the image identifier and matches the defect detection type with the corresponding detection model.
Alternatively, in the case where the acquisition device 104 is not connected to the detection terminal 102, the detection images acquired by different acquisition devices 104 may be imported into the local image storage space of the detection terminal 102, where in this case, the detection terminal 102 may determine, according to the image identifier, a defect detection type corresponding to the detection image, and match the corresponding detection model.
S602, determining the type of the defect to be detected according to the target image identification of the detection image.
Optionally, after the detection terminal 102 obtains the detection image from the local image storage space, the type of the defect to be detected may be determined according to the target image identifier of the detection image based on the correspondence between the candidate image identifier and the candidate defect type, so as to match with a corresponding detection model, so as to realize automatic detection of multiple defects of the device to be detected.
Optionally, the detection terminal 102 may further determine a target acquisition device from candidate acquisition devices according to the target image identifier of the detected image, and determine the type of defect to be detected according to the image acquisition type of the target acquisition device.
S603, selecting a target detection model corresponding to the defect type to be detected from the candidate detection models.
Optionally, a detection application may be deployed in the detection device to detect the detected image, where multiple candidate detection models may be integrated in the detection application, and different candidate detection models are used to detect different types of defects, and a target detection model corresponding to the type of defect to be detected needs to be selected from the candidate detection models.
S604, detecting whether the detected image has the target defect of the defect type to be detected by adopting a target detection model, if so, executing S605-S608, and if not, executing S609.
S605 extracts a region image including the target defect from the detected image.
It will be appreciated that a detection device may have a defect only in a certain portion, and corresponds to information that a certain region in a detection image includes a defect, so that the target region may be truncated, that is, a region image including the target defect may be extracted from the detection image, so that subsequent processing may be performed on the region image including the target defect in a targeted manner.
S606, determining a defect calculation mode according to the shape of the target defect.
Optionally, the shape of the target defect may be determined by extracting the defect feature of the area image including the target defect, and then determining the defect calculation mode according to the shape of the target defect. For example, when the shape of the target defect is determined to be a scratch, the defect calculation method may be determined to calculate the length of the scratch; if the shape of the target defect is determined to be an irregular contour, the defect calculation mode can be determined to calculate the area, the length or the width of the contour and other information.
S607, determining the defect size of the target defect according to the area image by adopting a defect calculation mode.
When the defect calculation mode is determined, the defect size of the target defect can be determined according to the area image by adopting the defect calculation mode. For example, when the shape of the target defect is determined to be a scratch, and the determined defect calculation mode is to calculate the length of the scratch, the defect size of the target defect can be determined according to the area image; and then scaling in equal proportion, and calculating to obtain the actual size of the target defect of the detection device.
S608, determining a target detection result of the detection image according to the size relation between the defect size of the target defect and the preset size threshold.
Optionally, the target detection result is used for representing whether the device to be detected is a qualified device or a disqualified device. Whether the defect size of the target defect is larger than a preset size threshold value can be judged, and if the defect size of the target defect is larger than the preset size threshold value, a target detection result used for representing that the device to be detected is a disqualified device is determined; and if the defect size of the target defect is smaller than or equal to the preset size threshold value, determining a target detection result used for representing that the device to be detected is a qualified device.
S609, determining that the detection image is the target detection result of the qualified device.
Under the condition that the target detection model detects that the detection image does not have the target defect of the defect type to be detected, the target detection result of the qualified device can be directly output.
The specific processes of S601 to S609 may be referred to the description of the method embodiments, and the implementation principle and technical effects are similar, and are not repeated herein.
In one embodiment, the acquisition device 104 is a microscope device, and the detection terminal 102 is a computer device. The detection application for detecting whether the device has defects in the computer equipment integrates a plurality of candidate detection models for detecting the defects. Referring to fig. 7, fig. 7 provides a specific implementation process for detecting a detection image.
Firstly, loading a device to be detected on a slide glass of a microscope, triggering a shooting control part on the microscope, sending a request for acquiring an image acquisition instruction to computer equipment by the microscope, and sending the image acquisition instruction to the microscope after the computer equipment receives the request for acquiring the image acquisition instruction sent by the microscope so as to control the microscope to complete acquisition of a detection image; and transmitting the acquired detection image to a computer. The computer equipment detects an image to be detected in the local storage space, acquires a detection image in the local storage space, detects the detection image by using the detection application, and outputs a detection result.
Optionally, the computer monitors in real time whether the microscope transmits the image to be detected to the computer through the scheduling module. When the detection application runs for the first time, each candidate model file and the reading configuration file are loaded, then defect detection is carried out, finally the detection result is sent to the interaction module for post-processing, the post-processing comprises visualization of the detection result and detection report generation, the interaction module can receive external input of a user, and the external input can influence the visualization effect and the content of an output report. The scheduling module monitors the designated folder at the same time, and when a user or other hardware equipment stores the defect picture in the folder, the scheduling module is triggered, and the scheduling module sends the picture to the detection application to carry out subsequent image defect detection.
In one embodiment, referring to FIG. 8, FIG. 8 provides a schematic diagram of a microscope and computer connection. The microscope and the computer can be connected by using a secondary development interface, and the transmission of the detection image is performed.
Optionally, the computer may monitor, in real time, whether the microscope transmits the image to be detected to the computer through the scheduling module, for example, the scheduling module may monitor, through the scheduling thread, whether there is a data stream input in the microscope thread, and if so, determine that the microscope transmits the image to be detected to the computer. The scheduling module can monitor whether the file monitoring thread has data stream input or not through the scheduling thread, and if so, the scheduling module determines that the image to be detected exists in the specified folder.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a device defect detection device for realizing the device defect detection method. The implementation of the solution provided by the device is similar to that described in the above method, so the specific limitation in the embodiments of the device defect detection device or devices provided below may be referred to the limitation of the device defect detection method hereinabove, and will not be repeated herein.
In one embodiment, as shown in fig. 9, there is provided a device defect detection apparatus including:
the acquisition module 10 is configured to acquire a detection image of a device to be detected.
The first determining module 20 is configured to determine a type of defect to be detected according to the target image identifier of the detected image.
And a selection module 30, configured to select a target detection model corresponding to the defect type to be detected from the candidate detection models.
And the detection module 40 is used for performing defect detection on the detection image by adopting the target detection model.
The device defect detection device determines the type of the defect to be detected according to the target image identification of the detection image; selecting a target detection model corresponding to the defect type to be detected from the candidate detection models; and finally, performing defect detection on the detected image by adopting a target detection model. The defect type to be detected can be automatically identified according to the target image identification of the detection image, and the target detection model corresponding to the defect type to be detected can be screened out, so that various defect images can be automatically detected, and the defect detection efficiency of the device is improved; in addition, each candidate detection model is used for detecting different defects, can be suitable for more defect detection scenes, and expands the application range of the defect detection method.
In one embodiment, the first determining module 20 is specifically configured to:
and determining the type of the defect to be detected according to the target image identification of the detection image based on the corresponding relation between the candidate image identification and the candidate defect type.
In one embodiment, the first determining module 20 specifically includes:
the first determining unit is used for determining target acquisition equipment from candidate acquisition equipment according to the target image identification of the detection image;
and the second determining unit is used for determining the type of the defect to be detected according to the image acquisition type of the target acquisition equipment.
In one embodiment, the obtaining module 10 is specifically configured to:
acquiring a detection image of a device to be detected from a local image storage space; the detection image is written into the local image storage space for the target acquisition equipment.
In one embodiment, the detection module 40 specifically includes:
the detection unit is used for detecting whether the detected image has target defects of the defect type to be detected or not by adopting a target detection model;
a third determining unit, configured to determine, if the target defect exists, a target detection result of the detected image according to a size relationship between a defect size of the target defect and a preset size threshold; the target detection result is used for representing whether the device to be detected is a qualified device or a disqualified device.
In an embodiment, the third determining unit is specifically configured to:
if the defect size of the target defect is larger than a preset size threshold, determining a target detection result used for representing that the device to be detected is a disqualified device; and if the defect size of the target defect is smaller than or equal to the preset size threshold value, determining a target detection result used for representing that the device to be detected is a qualified device.
In one embodiment, referring to fig. 10, on the basis of fig. 9, the device defect detecting apparatus further includes:
an extraction module 50 for extracting a region image containing the target defect from the detected image;
a second determining module 60, configured to determine a defect calculation mode according to the shape of the target defect; and determining the defect size of the target defect according to the region image by adopting a defect calculation mode.
The respective modules in the above device defect detection apparatus may be implemented in whole or in part by software, hardware, and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure thereof may be as shown in fig. 11. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a device defect detection method.
The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like. It will be appreciated by those skilled in the art that the structure shown in fig. 11 is merely a block diagram of a portion of the structure associated with the present application and is not limiting of the computer device to which the present application applies, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:
acquiring a detection image of a device to be detected;
determining the type of the defect to be detected according to the target image identification of the detection image;
selecting a target detection model corresponding to the defect type to be detected from the candidate detection models;
and detecting defects of the detected image by adopting a target detection model.
In one embodiment, the processor when executing the computer program further performs the steps of:
and determining the type of the defect to be detected according to the target image identification of the detection image based on the corresponding relation between the candidate image identification and the candidate defect type.
In one embodiment, the processor when executing the computer program further performs the steps of:
determining target acquisition equipment from candidate acquisition equipment according to the target image identification of the detection image; and determining the type of the defect to be detected according to the image acquisition type of the target acquisition equipment.
In one embodiment, the processor when executing the computer program further performs the steps of:
acquiring a detection image of a device to be detected from a local image storage space; the detection image is written into the local image storage space for the target acquisition equipment.
In one embodiment, the processor when executing the computer program further performs the steps of:
detecting whether the detected image has target defects of the defect type to be detected or not by adopting a target detection model; if the defect exists, determining a target detection result of the detection image according to the size relation between the defect size of the target defect and a preset size threshold; the target detection result is used for representing whether the device to be detected is a qualified device or a disqualified device.
In one embodiment, the processor when executing the computer program further performs the steps of:
if the defect size of the target defect is larger than a preset size threshold, determining a target detection result used for representing that the device to be detected is a disqualified device; and if the defect size of the target defect is smaller than or equal to the preset size threshold value, determining a target detection result used for representing that the device to be detected is a qualified device.
In one embodiment, the processor when executing the computer program further performs the steps of:
extracting a region image containing the target defect from the detection image; determining a defect calculation mode according to the shape of the target defect; and determining the defect size of the target defect according to the region image by adopting a defect calculation mode.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring a detection image of a device to be detected;
determining the type of the defect to be detected according to the target image identification of the detection image;
selecting a target detection model corresponding to the defect type to be detected from the candidate detection models;
and detecting defects of the detected image by adopting a target detection model.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and determining the type of the defect to be detected according to the target image identification of the detection image based on the corresponding relation between the candidate image identification and the candidate defect type.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining target acquisition equipment from candidate acquisition equipment according to the target image identification of the detection image; and determining the type of the defect to be detected according to the image acquisition type of the target acquisition equipment.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring a detection image of a device to be detected from a local image storage space; the detection image is written into the local image storage space for the target acquisition equipment.
In one embodiment, the computer program when executed by the processor further performs the steps of:
detecting whether the detected image has target defects of the defect type to be detected or not by adopting a target detection model; if the defect exists, determining a target detection result of the detection image according to the size relation between the defect size of the target defect and a preset size threshold; the target detection result is used for representing whether the device to be detected is a qualified device or a disqualified device.
In one embodiment, the computer program when executed by the processor further performs the steps of:
if the defect size of the target defect is larger than a preset size threshold, determining a target detection result used for representing that the device to be detected is a disqualified device; and if the defect size of the target defect is smaller than or equal to the preset size threshold value, determining a target detection result used for representing that the device to be detected is a qualified device.
In one embodiment, the computer program when executed by the processor further performs the steps of:
extracting a region image containing the target defect from the detection image; determining a defect calculation mode according to the shape of the target defect; and determining the defect size of the target defect according to the region image by adopting a defect calculation mode.
In one embodiment, a computer program product is provided comprising a computer program which, when executed by a processor, performs the steps of:
acquiring a detection image of a device to be detected;
determining the type of the defect to be detected according to the target image identification of the detection image;
selecting a target detection model corresponding to the defect type to be detected from the candidate detection models;
and detecting defects of the detected image by adopting a target detection model.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and determining the type of the defect to be detected according to the target image identification of the detection image based on the corresponding relation between the candidate image identification and the candidate defect type.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining target acquisition equipment from candidate acquisition equipment according to the target image identification of the detection image; and determining the type of the defect to be detected according to the image acquisition type of the target acquisition equipment.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring a detection image of a device to be detected from a local image storage space; the detection image is written into the local image storage space for the target acquisition equipment.
In one embodiment, the computer program when executed by the processor further performs the steps of:
detecting whether the detected image has target defects of the defect type to be detected or not by adopting a target detection model; if the defect exists, determining a target detection result of the detection image according to the size relation between the defect size of the target defect and a preset size threshold; the target detection result is used for representing whether the device to be detected is a qualified device or a disqualified device.
In one embodiment, the computer program when executed by the processor further performs the steps of:
if the defect size of the target defect is larger than a preset size threshold, determining a target detection result used for representing that the device to be detected is a disqualified device; and if the defect size of the target defect is smaller than or equal to the preset size threshold value, determining a target detection result used for representing that the device to be detected is a qualified device.
In one embodiment, the computer program when executed by the processor further performs the steps of:
extracting a region image containing the target defect from the detection image; determining a defect calculation mode according to the shape of the target defect; and determining the defect size of the target defect according to the region image by adopting a defect calculation mode.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.
Claims (10)
1. A device defect detection method, the method comprising:
acquiring a detection image of a device to be detected;
determining the type of the defect to be detected according to the target image identification of the detection image;
selecting a target detection model corresponding to the defect type to be detected from the candidate detection models;
and performing defect detection on the detection image by adopting the target detection model.
2. The method according to claim 1, wherein determining the type of defect to be detected from the target image identification of the detection image comprises:
and determining the type of the defect to be detected according to the target image identification of the detection image based on the corresponding relation between the candidate image identification and the candidate defect type.
3. The method according to claim 1, wherein determining the type of defect to be detected from the target image identification of the detection image comprises:
determining target acquisition equipment from candidate acquisition equipment according to the target image identification of the detection image;
and determining the type of the defect to be detected according to the image acquisition type of the target acquisition equipment.
4. A method according to claim 3, wherein said acquiring a detection image of a device to be detected comprises:
acquiring a detection image of the device to be detected from a local image storage space; the detection image is written into the local image storage space for the target acquisition equipment.
5. The method of claim 1, wherein said performing defect detection on said inspection image using said object detection model comprises:
Detecting whether the detected image has the target defect of the defect type to be detected or not by adopting the target detection model;
if the target defect exists, determining a target detection result of the detection image according to the size relation between the defect size of the target defect and a preset size threshold; the target detection result is used for representing whether the device to be detected is a qualified device or a disqualified device.
6. The method according to claim 5, wherein determining the target detection result of the detection image according to the size relationship between the defect size of the target defect and a preset size threshold value comprises:
if the defect size of the target defect is larger than a preset size threshold, determining a target detection result used for representing that the device to be detected is a disqualified device;
and if the defect size of the target defect is smaller than or equal to the preset size threshold, determining a target detection result used for representing that the device to be detected is a qualified device.
7. The method of claim 5, wherein the method further comprises:
extracting a region image containing the target defect from the detection image;
Determining a defect calculation mode according to the shape of the target defect;
and determining the defect size of the target defect according to the area image by adopting the defect calculation mode.
8. A device defect inspection apparatus, the apparatus comprising:
the acquisition module is used for acquiring a detection image of the device to be detected;
the determining module is used for determining the type of the defect to be detected according to the target image identification of the detection image;
the selection module is used for selecting a target detection model corresponding to the defect type to be detected from the candidate detection models;
and the detection module is used for detecting defects of the detection image by adopting the target detection model.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311376792.8A CN117575995A (en) | 2023-10-23 | 2023-10-23 | Device defect detection method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311376792.8A CN117575995A (en) | 2023-10-23 | 2023-10-23 | Device defect detection method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117575995A true CN117575995A (en) | 2024-02-20 |
Family
ID=89861391
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311376792.8A Pending CN117575995A (en) | 2023-10-23 | 2023-10-23 | Device defect detection method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117575995A (en) |
-
2023
- 2023-10-23 CN CN202311376792.8A patent/CN117575995A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200394416A1 (en) | Method and apparatus for training feature extraction model, computer device, and computer-readable storage medium | |
| US9442832B2 (en) | User workflow replication for execution error analysis | |
| CN110726724A (en) | Defect detection method, system and device | |
| US9558852B2 (en) | Method and apparatus for defect repair in NAND memory device | |
| JP2020533654A (en) | Holographic anti-counterfeit code inspection method and equipment | |
| CN111897660B (en) | Model deployment method, model deployment device and terminal equipment | |
| US20240071111A1 (en) | Method, apparatus and system for inspecting cell crush | |
| CN111598084B (en) | Defect segmentation network training method, device, equipment and readable storage medium | |
| CN116206125A (en) | Appearance defect identification method, appearance defect identification device, computer equipment and storage medium | |
| CN117576108B (en) | Visual optimization method and device for wafer defect detection and computer equipment | |
| CN117575995A (en) | Device defect detection method, device, computer equipment and storage medium | |
| CN115471703A (en) | Two-dimensional code detection method, model training method, device, equipment and storage medium | |
| CN115965856B (en) | Image detection model construction method, device, computer equipment and storage medium | |
| CN116051518B (en) | Trojan horse position positioning method, trojan horse position positioning device, computer equipment and storage medium | |
| CN117074412A (en) | Solder appearance defect detection method, device, equipment and storage medium | |
| CN117115568B (en) | Data screening method, device, equipment and storage medium | |
| CN117372348A (en) | Defect analysis method, device, computer equipment and storage medium thereof | |
| CN117975473A (en) | Bill text detection model training and detection method, device, equipment and medium | |
| CN118338337A (en) | Reliability detection method, apparatus, computer device and storage medium | |
| CN116049009A (en) | Test method, test device, computer equipment and computer readable storage medium | |
| CN117788362A (en) | Defect detection method, system, device, computer equipment and storage medium | |
| CN118297458A (en) | Quality detection method, apparatus, device, storage medium, and program product | |
| CN118277270A (en) | Method, device, computer equipment and storage medium for acquiring execution result | |
| CN116956305A (en) | Evaluation method, apparatus, device, medium and program product for penetration test | |
| CN116896763A (en) | Time delay test method, time delay test device, computer equipment and storage medium |
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 |