CN115326832A - Automatic detection method and automatic detection device for wafer package - Google Patents
Automatic detection method and automatic detection device for wafer package Download PDFInfo
- Publication number
- CN115326832A CN115326832A CN202211062833.1A CN202211062833A CN115326832A CN 115326832 A CN115326832 A CN 115326832A CN 202211062833 A CN202211062833 A CN 202211062833A CN 115326832 A CN115326832 A CN 115326832A
- Authority
- CN
- China
- Prior art keywords
- image
- wafer
- risk
- acquiring
- denoised
- 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 30
- 238000012545 processing Methods 0.000 claims abstract description 52
- 239000012634 fragment Substances 0.000 claims abstract description 27
- 238000000034 method Methods 0.000 claims abstract description 25
- 238000004806 packaging method and process Methods 0.000 claims abstract description 14
- 230000002159 abnormal effect Effects 0.000 claims description 18
- 230000004927 fusion Effects 0.000 claims description 13
- 238000004458 analytical method Methods 0.000 claims description 10
- 238000003860 storage Methods 0.000 claims description 7
- 238000005336 cracking Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 4
- 230000002708 enhancing effect Effects 0.000 claims description 4
- 238000012790 confirmation Methods 0.000 claims description 3
- 238000013467 fragmentation Methods 0.000 claims description 3
- 238000006062 fragmentation reaction Methods 0.000 claims description 3
- 235000012431 wafers Nutrition 0.000 description 143
- 238000007689 inspection Methods 0.000 description 13
- 238000005286 illumination Methods 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 208000010392 Bone Fractures Diseases 0.000 description 1
- 206010017076 Fracture Diseases 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012858 packaging process Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Container, Conveyance, Adherence, Positioning, Of Wafer (AREA)
Abstract
The embodiment of the invention discloses an automatic detection method and an automatic detection device for wafer packaging, which relate to the technical field of image processing, and the method comprises the following steps: acquiring image information aiming at wafer packaging; processing the image information to obtain a processed image; carrying out wafer placement state recognition on the processed image to obtain a state recognition result; judging whether a fragment risk exists or not based on the state identification result; and generating a corresponding detection result based on the judgment result. The wafer packaging fragment risk is automatically identified by adopting an image identification mode, so that the wafer fragment risk is quickly and accurately determined, and the wafer detection efficiency and the wafer detection accuracy are improved.
Description
Technical Field
The invention relates to the technical field of image recognition, in particular to an automatic detection method of a wafer package, an automatic detection device of the wafer package and a computer readable storage medium.
Background
With the continuous development of science and technology and the continuous popularization of intelligent equipment, the demand of people on chips is larger and larger, and therefore the production capacity of the chips is also larger and larger.
In the chip production process, wafers are first produced by upstream enterprises and then transported to subsequent production factories for subsequent processing to produce the required chips, so that safe and reliable transportation of the wafers is of great importance.
In practical applications, technicians find that there is a problem of chipping during transportation of wafers to the customer end after they are produced, and the chipping problem is mainly caused by several factors: 1. after the wafer is produced and subjected to particle detection, when the wafer is placed in a biased or misplaced mode in the packaging process, fragments can be caused; 2. the stress of the wafer itself causes chipping problems during transport as well.
In order to solve the technical problems, in the prior art, a manual inspection mode is often adopted to inspect the placement condition of a wafer in the placement process so as to continuously process the wafer with a placement error or a fragment risk, however, the manual inspection has the problems of judgment error, omission and inconsistent standards, and meanwhile, no picture can be traced in the inspection process, so that the actual requirements of an enterprise cannot be met.
Disclosure of Invention
In order to solve the technical problems in the prior art, embodiments of the present invention provide an automatic detection method and an automatic detection apparatus for wafer packaging, which automatically identify the risk of fragments of the wafer packaging by using an image identification method, so as to quickly and accurately determine the risk of fragments of the wafer, and improve the detection efficiency and the detection accuracy of the wafer.
In order to achieve the above object, an embodiment of the present invention provides an automatic detection method for wafer packaging, where the method includes: acquiring image information aiming at wafer packaging; processing the image information to obtain a processed image; carrying out wafer placement state recognition on the processed image to obtain a state recognition result; judging whether a fragment risk exists or not based on the state identification result; and generating a corresponding detection result based on the judgment result.
Preferably, the acquiring image information for the wafer package includes: acquiring a first image of the wafer package under a first brightness; acquiring a second image of the wafer package at a second brightness; and taking the first image and the second image as image information for wafer packaging.
Preferably, the processing the image information to obtain a processed image includes: performing denoising processing on the first image and the second image to obtain a denoised first image and a denoised second image; performing gray scale processing on the denoised first image and the denoised second image to obtain a first gray scale image and a second gray scale image; executing a first fusion operation on the first gray level image and the second gray level image to generate a first fused image; acquiring a first channel image of the denoised first image in a preset color channel and acquiring a second channel image of the denoised second image in the preset color channel; respectively carrying out enhancement processing on the first channel image and the real-time second channel image to obtain an enhanced first image and an enhanced second image; executing a second fusion operation on the enhanced first image and the enhanced second image to generate a second fused image; generating a processed image based on the first fused image and the second fused image.
Preferably, the performing wafer placement state recognition on the processed image to obtain a state recognition result includes: carrying out crack identification on the processed image to obtain crack identification information; judging whether the wafer in the processed image has cracks or not based on the crack identification information; if the wafer has cracks, generating a wafer cracking state identification result; if the wafer has no cracks, carrying out wafer spacing identification on the processed image to obtain spacing identification information; judging whether the wafer has an offset state or not based on the spacing identification information; if the wafer has an offset condition, generating a state identification result of the wafer offset; and if the wafer does not have the bias arrangement condition, generating a recognition result of the normal arrangement state of the wafer.
Preferably, the method further comprises: after determining that the risk of fragments exists, acquiring a risk wafer with the risk of fragments; extracting a region image of the preset range of the risk wafer from the processed image; carrying out anomaly analysis on the area image to generate a corresponding anomaly risk factor; and establishing an incidence relation between the abnormal risk factor and the area image, and storing and feeding back the area image and the abnormal risk factor.
Correspondingly, the invention also provides an automatic detection device for the wafer package, which comprises: an image acquisition unit for acquiring image information for the wafer package; the processing unit is used for processing the image information to obtain a processed image; the recognition unit is used for carrying out wafer placement state recognition on the processed image to obtain a state recognition result; a judging unit for judging whether there is a risk of fragmentation based on the state recognition result; and a result generation unit for generating a corresponding detection result based on the judgment result.
Preferably, the image acquisition unit includes: the first image acquisition module is used for acquiring a first image of the wafer package under first brightness; the second image acquisition module is used for acquiring a second image of the wafer package under a second brightness; an image determination module to use the first image and the second image as image information for a wafer package.
Preferably, the processing unit comprises: the first processing module is used for performing denoising processing on the first image and the second image to obtain a denoised first image and a denoised second image; performing gray processing on the denoised first image and the denoised second image to obtain a first gray image and a second gray image; executing a first fusion operation on the first gray level image and the second gray level image to generate a first fused image; the second processing module is used for acquiring a first channel image of the denoised first image in a preset color channel and acquiring a second channel image of the denoised second image in the preset color channel; respectively enhancing the first channel image and the real-time second channel image to obtain an enhanced first image and an enhanced second image; executing a second fusion operation on the enhanced first image and the enhanced second image to generate a second fused image; a processing confirmation module for generating a processed image based on the first fused image and the second fused image.
Preferably, the identification unit is specifically configured to: carrying out crack identification on the processed image to obtain crack identification information; judging whether the wafer in the processed image has cracks or not based on the crack identification information; if the wafer has cracks, generating a wafer cracking state identification result; if the wafer has no cracks, carrying out wafer spacing identification on the processed image to obtain spacing identification information; judging whether the wafer has an offset state or not based on the spacing identification information; if the wafer has the bias condition, generating a state identification result of the bias of the wafer; and if the wafer does not have the bias arrangement condition, generating a state identification result of normal wafer arrangement.
Preferably, the apparatus further comprises a positioning unit for: after determining that the risk of fragments exists, acquiring a risk wafer with the risk of fragments; extracting an area image of the preset range of the risk wafer from the processed image; carrying out anomaly analysis on the area image to generate a corresponding anomaly risk factor; and establishing an incidence relation between the abnormal risk factor and the area image, and storing and feeding back the area image and the abnormal risk factor.
In another aspect, the present invention also provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the method provided by the present invention.
Through the technical scheme provided by the invention, the invention at least has the following technical effects:
the method comprises the steps of obtaining images of the wafer package by adopting different illumination modes, carrying out image fusion processing, carrying out channel weighting processing and image enhancement processing on the gray scale of the images, enabling the processed images to have higher definition and more prominent details, and improving the identification accuracy in the process of identifying the wafer package;
on the other hand, the characteristics of the wafer package under various risk conditions are identified, whether the wafer has a fragment risk or not is quickly and accurately identified, the product yield of an enterprise is improved, and the actual requirements of the enterprise are met.
Additional features and advantages of embodiments of the invention will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the embodiments of the invention without limiting the embodiments of the invention. In the drawings:
fig. 1 is a schematic view of an automatic inspection apparatus for wafer packages according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating an embodiment of an automatic inspection method for wafer packages according to the present invention;
fig. 3 is a flowchart illustrating a specific implementation of processing image information in an automatic detection method for a wafer package according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an automatic inspection apparatus for wafer packages according to an embodiment of the present invention.
Detailed Description
The following describes in detail embodiments of the present invention with reference to the drawings. It should be understood that the detailed description and specific examples, while indicating embodiments of the invention, are given by way of illustration and explanation only, not limitation.
The terms "system" and "network" in embodiments of the invention may be used interchangeably. "plurality" means two or more, and in view of this, a plurality may also be understood as "at least two" in the embodiments of the present invention. "and/or" describes the association relationship of the associated object, indicating that there may be three relationships, for example, a and/or B, which may indicate: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" generally indicates that the preceding and succeeding related objects are in an "or" relationship, unless otherwise specified. It is to be understood that the terms first, second, etc. used in the description of the embodiments of the invention are used for distinguishing between similar elements and not necessarily for describing a sequential or chronological order.
Referring to fig. 1, an embodiment of the present invention is applied to an automatic inspection apparatus for a wafer package, where the automatic inspection apparatus includes a placement platform for placing the wafer package, an image capturing device disposed above the wafer package for capturing image information of the wafer package, the image capturing device obtains the image information of the wafer package through a lens and sends the image information to a processing device for data processing and corresponding display, for example, the image processing device is any one of a personal computer, a tablet computer, a server, and the like.
Referring to fig. 2, an embodiment of the invention provides an automatic detection method for wafer packages, including:
s10) acquiring image information aiming at the wafer package;
s20) processing the image information to obtain a processed image;
s30) carrying out wafer placement state recognition on the processed image to obtain a state recognition result;
s40) judging whether fragment risks exist or not based on the state identification result;
s50) generating a corresponding detection result based on the determination result.
In a possible implementation manner, first acquiring image information for a wafer package, in an embodiment of the present invention, the acquiring image information for a wafer package includes: acquiring a first image of the wafer package under a first brightness; acquiring a second image of the wafer package at a second brightness; and taking the first image and the second image as image information for wafer packaging.
Specifically, lights are arranged around the lens, for example, a white LED strip is arranged, after the wafer package is placed on the placement table, the image capturing device first captures a first image of the wafer package without light irradiation, then turns on the white LED strip, at this time, a second image of the wafer package with light irradiation is captured, and the first image and the second image are used as image information for the wafer package.
In the embodiment of the invention, the wafer package is subjected to image acquisition under different illumination conditions, so that on one hand, the accurate identification can be carried out by combining images under different illumination conditions, and more image details of the wafer package can be obtained; on the other hand, the influence of insufficient definition of wafer package identification under single illumination intensity can be effectively avoided, and therefore the accuracy of subsequent identification is further improved.
However, in the practical application process, there may be more interference or influence on the image directly acquired by the image acquisition device, for example, the first image may not be clearly identified due to insufficient illumination; the second image may also be abnormal because of an excessive illumination intensity (when the wafer is packaged in a plastic package, an excessive light may be reflected due to light irradiation to cause an overexposure of the image acquired by the image acquisition device in a case where the wafer is placed at a different position), and therefore, the image information acquired primarily needs to be processed.
Referring to fig. 3, in the embodiment of the present invention, the processing the image information to obtain a processed image includes:
s21) denoising the first image and the second image to obtain a denoised first image and a denoised second image;
s22) performing gray level processing on the denoised first image and the denoised second image to obtain a first gray level image and a second gray level image;
s23) performing a first fusion operation on the first gray level image and the second gray level image to generate a first fused image;
s24) acquiring a first channel image of the denoised first image in a preset color channel and acquiring a second channel image of the denoised second image in the preset color channel;
s25) respectively enhancing the first channel image and the real-time second channel image to obtain an enhanced first image and an enhanced second image;
s26) performing second fusion operation on the enhanced first image and the enhanced second image to generate a second fused image;
s27) generating a processed image based on the first fused image and the second fused image.
In a possible implementation manner, first, denoising processing is performed on the first image and the second image, for example, denoising is performed on the first image and the second image through a preset low-pass filter, so as to obtain a denoised first image and a denoised second image, at this time, grayscale processing is further performed on the denoised images, so as to further extract details of the images, and obtain a first grayscale image and a second grayscale image, at this time, a first fusion operation is performed on the first grayscale image and the second grayscale image, for example, a clear region meeting a preset definition requirement in the first grayscale image and the second grayscale image is fused, so as to obtain a fused image.
At this time, a first channel image of the denoised first image in a preset color channel and a second channel image of the denoised second image in the preset color channel are obtained, in this embodiment, the preset color channel may be an RGB channel or a CMY channel, and a technician may select an optimal color channel according to an actual processing effect to extract a corresponding channel image, which should belong to the protection scope of the embodiment of the present invention, and therefore, redundant description is not repeated here. After acquiring the corresponding first channel image and second channel image, further performing corresponding enhancement processing, for example, the first channel image is an R component grayscale image R (i, j), a G component grayscale image (i, j), and a B component grayscale image (i, j), at this time, a first weighted grayscale image corresponding to the first channel image is obtained according to a preset weighting factor, for example, the first weighted grayscale image f (i, j) =0.2R (i, j) +0.55G (i, j) +0.25B (i, j), and based on the same principle, a second weighted grayscale image corresponding to the second channel image is obtained, at this time, image enhancement processing is performed on the weighted grayscale image according to a preset point arithmetic algorithm (for example, grayscale correction, grayscale transformation, histogram modification, and the like), and an enhanced first image and an enhanced second image are obtained, in which details in a wafer package are highlighted and enhanced, and the enhanced first image and the enhanced second image are obtained, and then fused based on the fused first image and the second image, and then, the fused second image is generated.
In the embodiment of the invention, the acquired wafer package images under different brightness are analyzed and fused, so that the images in the subsequent analysis have clearer and more accurate image details; meanwhile, the images of the images under multiple channels are weighted and enhanced, so that details in the subsequently analyzed images are further enhanced and displayed, and the accuracy and the sensitivity in the subsequent analysis process can be further improved. After the processed image is obtained, the image of the wafer package may be subjected to fracture risk identification.
In an embodiment of the present invention, the performing wafer placement state recognition on the processed image to obtain a state recognition result includes: carrying out crack identification on the processed image to obtain crack identification information; judging whether the wafer in the processed image has cracks or not based on the crack identification information; if the wafer has cracks, generating a wafer cracking state identification result; if the wafer has no cracks, carrying out wafer spacing identification on the processed image to obtain spacing identification information; judging whether the wafer has an offset state or not based on the spacing identification information; if the wafer has the bias condition, generating a state identification result of the bias of the wafer; and if the wafer does not have the bias arrangement condition, generating a recognition result of the normal arrangement state of the wafer.
In a possible implementation manner, crack identification is performed on the processed image, for example, the grain direction in the processed image may be directly analyzed, and when a grain direction which is not consistent with that of a normal wafer exists, it may be determined that a crack exists; of course, the processed image may also be analyzed by a pre-trained intelligent recognition algorithm, for example, a deep learning algorithm based on a neural network, to determine whether there is a crack in the current wafer, and if there is a crack, a state recognition result of the wafer breakage is immediately generated and immediately fed back to the corresponding manager or plant personnel.
In another embodiment, since the current wafer has no crack, indirect identification of the wafer in the wafer package can be further performed, and pitch identification information can be obtained, as is readily known to those skilled in the art, one wafer package includes a plurality of wafers, and thus the indirect identification information is the pitch between every two adjacent wafers, and whether the wafer has an offset condition can be identified according to the pitch, for example, in this embodiment, it is found that a certain wafer has an offset condition, and thus a corresponding wafer offset condition identification result is immediately generated.
In the subsequent detection process, the processing device automatically judges whether the wafer risk exists according to the state identification result, for example, when the state identification result of wafer breakage or wafer deflection is obtained, the wafer risk exists, and therefore detection information with the wafer risk is immediately generated and sent to a manager or a factory worker.
In the embodiment of the invention, the automatic identification method aiming at the wafer package is adopted, and a manual sampling inspection or manual checking mode is not adopted, so that the labor cost of an enterprise is greatly reduced, and the working efficiency is improved; on the other hand, the deviation of manual inspection is avoided, and the inspection accuracy is improved.
However, in the practical application process, the risk of fragments exists only through simple feedback, and the personnel still needs to go to the site for verification manually, so that certain trouble is still caused to technicians.
In order to solve the above technical problem, in an embodiment of the present invention, the method further includes: after determining that the risk of the fragments exists, acquiring a risk wafer with the risk of the fragments; extracting an area image of the preset range of the risk wafer from the processed image; carrying out anomaly analysis on the area image to generate a corresponding anomaly risk factor; and establishing an incidence relation between the abnormal risk factor and the area image, and storing and feeding back the area image and the abnormal risk factor.
In a possible implementation manner, after the existence of the fragment risk is determined, further acquiring a risk wafer with the fragment risk, for example, framing the risk wafer in a processed image, then extracting an area image of a preset range of the risk wafer from the processed image, for example, the preset range may be half of a distance between adjacent wafers, performing anomaly analysis on the area image at this time, and generating a corresponding anomaly risk factor, for example, when the analysis finds that the structure of the wafer packaging box is abnormal, taking an abnormal structure as the anomaly risk factor; when the sundries exist in the wafer packaging box, the sundries are used as abnormal risk factors, then the incidence relation between the abnormal risk factors and the area images is established and stored in the corresponding storage device, and then the abnormal risk factors and the area images are fed back to a manager together, so that the manager can conveniently, remotely, quickly and accurately verify and determine the wafer fragment risk and determine the corresponding risk factors, the manual workload is further reduced, the working efficiency is improved, and the risk identification accuracy is improved.
The following describes an automatic inspection apparatus for wafer packages according to an embodiment of the present invention with reference to the accompanying drawings.
Referring to fig. 4, based on the same inventive concept, an embodiment of the present invention provides an automatic inspection apparatus for wafer packages, including: the image acquisition unit is used for acquiring image information aiming at the wafer package; the processing unit is used for processing the image information to obtain a processed image; the recognition unit is used for carrying out wafer placement state recognition on the processed image to obtain a state recognition result; a judging unit for judging whether there is a risk of fragmentation based on the state recognition result; and a result generation unit for generating a corresponding detection result based on the judgment result.
In an embodiment of the present invention, the image acquisition unit includes: the first image acquisition module is used for acquiring a first image of the wafer package under first brightness; the second image acquisition module is used for acquiring a second image of the wafer package under a second brightness; an image determination module to use the first image and the second image as image information for a wafer package.
In an embodiment of the present invention, the processing unit includes: the first processing module is used for performing denoising processing on the first image and the second image to obtain a denoised first image and a denoised second image; performing gray processing on the denoised first image and the denoised second image to obtain a first gray image and a second gray image; executing a first fusion operation on the first gray level image and the second gray level image to generate a first fused image; the second processing module is used for acquiring a first channel image of the denoised first image in a preset color channel and acquiring a second channel image of the denoised second image in the preset color channel; respectively enhancing the first channel image and the real-time second channel image to obtain an enhanced first image and an enhanced second image; executing a second fusion operation on the enhanced first image and the enhanced second image to generate a second fused image; a processing confirmation module configured to generate a processed image based on the first fused image and the second fused image.
In an embodiment of the present invention, the identification unit is specifically configured to: carrying out crack identification on the processed image to obtain crack identification information; judging whether the wafer in the processed image has cracks or not based on the crack identification information; if the wafer has cracks, generating a wafer cracking state identification result; if the wafer has no cracks, carrying out wafer spacing identification on the processed image to obtain spacing identification information; judging whether the wafer has an offset state or not based on the spacing identification information; if the wafer has the bias condition, generating a state identification result of the bias of the wafer; and if the wafer does not have the bias arrangement condition, generating a state identification result of normal wafer arrangement.
In an embodiment of the present invention, the apparatus further includes a positioning unit, where the positioning unit is configured to: after determining that the risk of the fragments exists, acquiring a risk wafer with the risk of the fragments; extracting a region image of the preset range of the risk wafer from the processed image; carrying out anomaly analysis on the area image to generate a corresponding anomaly risk factor; and establishing an incidence relation between the abnormal risk factor and the area image, and storing and feeding back the area image and the abnormal risk factor.
Further, an embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the method described in the present invention.
Although the embodiments of the present invention have been described in detail with reference to the accompanying drawings, the embodiments of the present invention are not limited to the specific details of the above embodiments, and various simple modifications may be made to the technical solutions of the embodiments of the present invention within the technical idea of the embodiments of the present invention, and these simple modifications all belong to the protection scope of the embodiments of the present invention.
It should be noted that the various features described in the foregoing embodiments may be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the embodiments of the present invention do not describe every possible combination.
Those skilled in the art will understand that all or part of the steps in the method according to the above embodiments may be implemented by a program, which is stored in a storage medium and includes several instructions to enable a single chip, a chip, or a processor (processor) to execute all or part of the steps in the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In addition, any combination of various different implementation manners of the embodiments of the present invention can be made, and the embodiments of the present invention should also be regarded as the disclosure of the embodiments of the present invention as long as the combination does not depart from the spirit of the embodiments of the present invention.
Claims (11)
1. An automatic detection method for wafer packaging is characterized by comprising the following steps:
acquiring image information aiming at wafer packaging;
processing the image information to obtain a processed image;
carrying out wafer placement state recognition on the processed image to obtain a state recognition result;
judging whether fragment risks exist or not based on the state identification result;
and generating a corresponding detection result based on the judgment result.
2. The method of claim 1, wherein the obtaining image information for the wafer package comprises:
acquiring a first image of the wafer package under a first brightness;
acquiring a second image of the wafer package at a second brightness;
and taking the first image and the second image as image information for the wafer package.
3. The method of claim 2, wherein the processing the image information to obtain a processed image comprises:
performing denoising processing on the first image and the second image to obtain a denoised first image and a denoised second image;
performing gray processing on the denoised first image and the denoised second image to obtain a first gray image and a second gray image;
executing a first fusion operation on the first gray level image and the second gray level image to generate a first fused image;
acquiring a first channel image of the denoised first image in a preset color channel and acquiring a second channel image of the denoised second image in the preset color channel;
respectively carrying out enhancement processing on the first channel image and the real-time second channel image to obtain an enhanced first image and an enhanced second image;
executing a second fusion operation on the enhanced first image and the enhanced second image to generate a second fused image;
generating a processed image based on the first fused image and the second fused image.
4. The method of claim 1, wherein the performing wafer placement state recognition on the processed image to obtain a state recognition result comprises:
carrying out crack identification on the processed image to obtain crack identification information;
judging whether the wafer in the processed image has cracks or not based on the crack identification information;
if the wafer has cracks, generating a wafer cracking state identification result;
if the wafer has no cracks, carrying out wafer spacing identification on the processed image to obtain spacing identification information;
judging whether the wafer has an offset state or not based on the spacing identification information;
if the wafer has an offset condition, generating a state identification result of the wafer offset;
and if the wafer does not have the bias arrangement condition, generating a state identification result of normal wafer arrangement.
5. The method of claim 1, further comprising:
after determining that the risk of fragments exists, acquiring a risk wafer with the risk of fragments;
extracting an area image of the preset range of the risk wafer from the processed image;
carrying out anomaly analysis on the area image to generate a corresponding anomaly risk factor;
and establishing an incidence relation between the abnormal risk factor and the area image, and storing and feeding back the area image and the abnormal risk factor.
6. An automatic detection device for wafer packaging, the device comprising:
the image acquisition unit is used for acquiring image information aiming at the wafer package;
the processing unit is used for processing the image information to obtain a processed image;
the recognition unit is used for carrying out wafer placement state recognition on the processed image to obtain a state recognition result;
a judging unit for judging whether there is a risk of fragmentation based on the state recognition result;
and a result generation unit for generating a corresponding detection result based on the judgment result.
7. The apparatus according to claim 6, wherein the image acquisition unit comprises:
the first image acquisition module is used for acquiring a first image of the wafer package under first brightness;
the second image acquisition module is used for acquiring a second image of the wafer package under a second brightness;
an image determination module to use the first image and the second image as image information for a wafer package.
8. The apparatus of claim 7, wherein the processing unit comprises:
the first processing module is used for performing denoising processing on the first image and the second image to obtain a denoised first image and a denoised second image; performing gray processing on the denoised first image and the denoised second image to obtain a first gray image and a second gray image; executing a first fusion operation on the first gray level image and the second gray level image to generate a first fused image;
the second processing module is used for acquiring a first channel image of the denoised first image in a preset color channel and acquiring a second channel image of the denoised second image in the preset color channel; respectively enhancing the first channel image and the real-time second channel image to obtain an enhanced first image and an enhanced second image; executing a second fusion operation on the enhanced first image and the enhanced second image to generate a second fused image;
a processing confirmation module configured to generate a processed image based on the first fused image and the second fused image.
9. The apparatus according to claim 6, wherein the identification unit is specifically configured to:
carrying out crack identification on the processed image to obtain crack identification information;
judging whether the wafer in the processed image has cracks or not based on the crack identification information;
if the wafer has cracks, generating a wafer cracking state identification result;
if the wafer has no cracks, carrying out wafer spacing identification on the processed image to obtain spacing identification information;
judging whether the wafer has an offset state or not based on the spacing identification information;
if the wafer has an offset condition, generating a state identification result of the wafer offset;
and if the wafer does not have the bias arrangement condition, generating a state identification result of normal wafer arrangement.
10. The apparatus of claim 6, further comprising a positioning unit configured to:
after determining that the risk of the fragments exists, acquiring a risk wafer with the risk of the fragments;
extracting a region image of the preset range of the risk wafer from the processed image;
carrying out anomaly analysis on the area image to generate a corresponding anomaly risk factor;
and establishing an incidence relation between the abnormal risk factor and the area image, and storing and feeding back the area image and the abnormal risk factor.
11. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211062833.1A CN115326832A (en) | 2022-09-01 | 2022-09-01 | Automatic detection method and automatic detection device for wafer package |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211062833.1A CN115326832A (en) | 2022-09-01 | 2022-09-01 | Automatic detection method and automatic detection device for wafer package |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115326832A true CN115326832A (en) | 2022-11-11 |
Family
ID=83927389
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211062833.1A Pending CN115326832A (en) | 2022-09-01 | 2022-09-01 | Automatic detection method and automatic detection device for wafer package |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115326832A (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07273170A (en) * | 1994-03-31 | 1995-10-20 | Sumitomo Precision Prod Co Ltd | Distortion measuring method for wafer carrier |
| KR20020046829A (en) * | 2000-12-15 | 2002-06-21 | 윤종용 | Apparatus for inspecting wafer |
| JP2003282675A (en) * | 2002-03-20 | 2003-10-03 | Tokyo Seimitsu Co Ltd | Wafer mapping device |
| KR20050024922A (en) * | 2003-09-05 | 2005-03-11 | 김광렬 | Apparatus for detecting a defect on edge area of a wafer and method therefor |
| KR20130026698A (en) * | 2011-09-06 | 2013-03-14 | 주식회사 엘지실트론 | Method of inspecting wafer |
| CN108562586A (en) * | 2017-12-25 | 2018-09-21 | 西南石油大学 | A kind of pipeline oil-water two-phase flow distributed mutually recognition methods |
| CN110263609A (en) * | 2019-01-27 | 2019-09-20 | 杭州品茗安控信息技术股份有限公司 | A kind of automatic identifying method of safety cap wear condition |
| CN111462031A (en) * | 2020-03-27 | 2020-07-28 | Oppo广东移动通信有限公司 | Multi-frame HDR image processing method and device, storage medium and electronic equipment |
| CN113450302A (en) * | 2020-03-24 | 2021-09-28 | 东莞新能德科技有限公司 | Tab detection method and device based on machine learning and computer readable storage medium |
| CN113744184A (en) * | 2021-07-27 | 2021-12-03 | 江苏农林职业技术学院 | Snakehead ovum counting method based on image processing |
| CN114740017A (en) * | 2021-01-07 | 2022-07-12 | 富泰华工业（深圳）有限公司 | Method and system for detecting wafer arrangement state in wafer box |
-
2022
- 2022-09-01 CN CN202211062833.1A patent/CN115326832A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07273170A (en) * | 1994-03-31 | 1995-10-20 | Sumitomo Precision Prod Co Ltd | Distortion measuring method for wafer carrier |
| KR20020046829A (en) * | 2000-12-15 | 2002-06-21 | 윤종용 | Apparatus for inspecting wafer |
| JP2003282675A (en) * | 2002-03-20 | 2003-10-03 | Tokyo Seimitsu Co Ltd | Wafer mapping device |
| KR20050024922A (en) * | 2003-09-05 | 2005-03-11 | 김광렬 | Apparatus for detecting a defect on edge area of a wafer and method therefor |
| KR20130026698A (en) * | 2011-09-06 | 2013-03-14 | 주식회사 엘지실트론 | Method of inspecting wafer |
| CN108562586A (en) * | 2017-12-25 | 2018-09-21 | 西南石油大学 | A kind of pipeline oil-water two-phase flow distributed mutually recognition methods |
| CN110263609A (en) * | 2019-01-27 | 2019-09-20 | 杭州品茗安控信息技术股份有限公司 | A kind of automatic identifying method of safety cap wear condition |
| CN113450302A (en) * | 2020-03-24 | 2021-09-28 | 东莞新能德科技有限公司 | Tab detection method and device based on machine learning and computer readable storage medium |
| CN111462031A (en) * | 2020-03-27 | 2020-07-28 | Oppo广东移动通信有限公司 | Multi-frame HDR image processing method and device, storage medium and electronic equipment |
| CN114740017A (en) * | 2021-01-07 | 2022-07-12 | 富泰华工业（深圳）有限公司 | Method and system for detecting wafer arrangement state in wafer box |
| CN113744184A (en) * | 2021-07-27 | 2021-12-03 | 江苏农林职业技术学院 | Snakehead ovum counting method based on image processing |
Non-Patent Citations (1)
| Title |
|---|
| 方明;李洪娜;雷立宏;梁铭;: "低照度视频图像增强算法综述", 长春理工大学学报(自然科学版), no. 03, 15 June 2016 (2016-06-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102102874B1 (en) | Automatic optical inspection system and operating method thereof | |
| KR101415628B1 (en) | Lumber inspection method, device and program | |
| CN113095438B (en) | Wafer defect classification method, device and system thereof, electronic equipment and storage medium | |
| US20060291713A1 (en) | Board inspecting apparatus, its parameter setting method and parameter setting apparatus | |
| CN109829883B (en) | Product quality detection method and device | |
| JP5085860B2 (en) | Wood inspection method, apparatus and program | |
| CN113096119B (en) | Method and device for classifying wafer defects, electronic equipment and storage medium | |
| JP2006292725A (en) | Substrate inspection device, its inspection logic setting method, and inspection logic setting device | |
| CA2638415C (en) | Patterned wafer defect inspection system and method | |
| US11315832B2 (en) | Wafer singulation process control | |
| CN114119535A (en) | Laser cleaning effect on-line monitoring method based on visual detection | |
| CN104778439B (en) | Ultrasound detection clamp types intelligent identification Method and device based on Quick Response Code | |
| TWI531787B (en) | An automatic optical detection method and an automatic optical detection system for carrying out the method | |
| US8358831B2 (en) | Probe mark inspection | |
| CN115326832A (en) | Automatic detection method and automatic detection device for wafer package | |
| JP2012190935A (en) | Chip position specification system, chip position specification device, chip position specification program, and chip position specification method | |
| KR20230139166A (en) | Inspection Method for Wood Product | |
| CN111693533B (en) | Workpiece surface quality detection method and device and appearance machine | |
| KR102015620B1 (en) | System and Method for detecting Metallic Particles | |
| CN112288747A (en) | Intelligent detection method and device for steel billets | |
| KR20150137474A (en) | Vision inspecting method using color image separation | |
| CN112730427B (en) | Product surface defect detection method and system based on machine vision | |
| JP4858227B2 (en) | Inspection parameter setting support device, control program and control method thereof | |
| KR102028196B1 (en) | LED module examine apparatus for using image processing | |
| CN117710306A (en) | Positioning method, processor and storage medium for semiconductor device defect |
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 |