CN116883399A - Visual detection method, device, system and equipment for defects in sapphire shouldering stage - Google Patents
Visual detection method, device, system and equipment for defects in sapphire shouldering stage Download PDFInfo
- Publication number
- CN116883399A CN116883399A CN202311145368.2A CN202311145368A CN116883399A CN 116883399 A CN116883399 A CN 116883399A CN 202311145368 A CN202311145368 A CN 202311145368A CN 116883399 A CN116883399 A CN 116883399A
- Authority
- CN
- China
- Prior art keywords
- sapphire
- image
- detected
- shouldering stage
- stage
- 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
- 229910052594 sapphire Inorganic materials 0.000 title claims abstract description 129
- 239000010980 sapphire Substances 0.000 title claims abstract description 129
- 230000007547 defect Effects 0.000 title claims abstract description 106
- 238000001514 detection method Methods 0.000 title claims abstract description 23
- 230000000007 visual effect Effects 0.000 title claims abstract description 8
- 238000000034 method Methods 0.000 claims abstract description 37
- 238000012549 training Methods 0.000 claims abstract description 36
- 238000012360 testing method Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 12
- 238000012795 verification Methods 0.000 claims description 12
- 238000011179 visual inspection Methods 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000007689 inspection Methods 0.000 claims description 5
- 238000003384 imaging method Methods 0.000 claims description 4
- 238000010899 nucleation Methods 0.000 claims description 4
- 230000002950 deficient Effects 0.000 claims 1
- 238000002360 preparation method Methods 0.000 abstract description 4
- 238000012797 qualification Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 6
- 239000013078 crystal Substances 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 239000011521 glass Substances 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000004575 stone Substances 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
- 238000003466 welding Methods 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
- G06N3/0455—Auto-encoder networks; Encoder-decoder networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
- G06V10/763—Non-hierarchical techniques, e.g. based on statistics of modelling distributions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Multimedia (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Probability & Statistics with Applications (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The application relates to the field of sapphire growth, in particular to a visual detection method, device, system and equipment for defects in a sapphire shouldering stage. The method comprises the following steps: training the variation automatic encoder model based on a sample image set of the sapphire in the shouldering stage to obtain a picture generation model; collecting an image to be detected of the sapphire to be detected in a shouldering stage, and inputting the image to be detected into the picture generation model to obtain a reconstructed image; and determining whether the sapphire to be detected has defects in the shouldering stage or not based on the comparison of the reconstructed image and the image to be detected. According to the technical scheme, the defect detection of the sapphire in the shouldering stage can be rapidly and accurately realized, so that the qualification rate of sapphire preparation is improved.
Description
Technical Field
The application relates to the field of sapphire growth, in particular to a visual detection method, device, system and equipment for defects in a sapphire shouldering stage.
Background
Sapphire is a window material widely used in infrared military devices, satellite space technology, and high-intensity lasers. The sapphire has huge demand and good market prospect in the current artificial synthesis of sapphire.
In the process of manually preparing the sapphire, the sapphire is required to be prepared by a crystal growth furnace. The sapphire may have defects in the shouldering stage, and the traditional defect judgment mode is judged by manually observing a window made of electric welding glass and gold-plated glass. Because strong light in the furnace can not be observed for a long time and errors easily occur in manual observation by experience, the defect detection efficiency and the accuracy in the sapphire shouldering stage are low.
Disclosure of Invention
Based on the foregoing, it is necessary to provide a method, a device, a system and a computer device for visually detecting defects in a sapphire shoulder stage.
In a first aspect, an embodiment of the present application provides a method for visually detecting a defect in a shoulder stage of sapphire, where the method includes:
training the variation automatic encoder model based on a sample image set of the sapphire in the shouldering stage to obtain a picture generation model;
collecting an image to be detected of the sapphire to be detected in a shouldering stage, and inputting the image to be detected into the picture generation model to obtain a reconstructed image;
and determining whether the sapphire to be detected has defects in the shouldering stage or not based on the comparison of the reconstructed image and the image to be detected.
In an embodiment, the training the variational automatic encoder model based on the sample image set of the sapphire in the shouldering stage to obtain the image generation model includes:
dividing the sample image set into a training set, a verification set and a test set based on a preset proportion; the training set and the verification set are composed of sample images of sapphire, wherein the sample images do not have defects in the shouldering stage; the test set is composed of sample images of the sapphire with defects in the shouldering stage;
training the variation automatic encoder model based on the training set to obtain an initial picture generation model;
and continuously verifying the picture generation model in the training process based on the verification set so as to adjust the super-parameters of the model training algorithm based on the verification result until the test result based on the test set meets the preset condition.
In an embodiment, the determining whether the sapphire to be measured has a defect in the shouldering stage based on the comparison of the reconstructed image and the image to be measured includes:
comparing the reconstructed image with the image to be detected to obtain a gray level difference image;
and determining whether the sapphire to be detected has defects in the shouldering stage or not based on the gray level difference image.
In an embodiment, the determining whether the sapphire to be measured has a defect in the shouldering stage based on the gray scale difference image includes:
clustering the gray level difference images to obtain background clusters and defect clusters;
based on the background cluster and the defect cluster, carrying out binarization processing on the gray level difference image to obtain a binarized image;
and determining whether the sapphire to be detected has defects in the shouldering stage or not based on the area of the region, corresponding to the defect cluster, in the binarized image.
In an embodiment, the determining whether the sapphire to be tested has a defect in the shouldering stage based on the area of the region of the defect cluster corresponding to the binarized image includes:
if the area of the region is larger than the preset area, determining that the sapphire to be tested has defects in the shouldering stage; otherwise, determining that the sapphire to be measured has no defect in the shouldering stage.
In an embodiment, the sample image and the image to be detected in the sample image set are respectively obtained by stitching a plurality of sub-images shot by the image acquisition device, and each sub-image corresponds to a different imaging angle of the sapphire in the shouldering stage.
In an embodiment, the method further comprises:
if the sapphire to be tested has defects in the shouldering stage, after the defects are cleaned, re-seeding and shouldering the sapphire to be tested until the sapphire to be tested has no defects in the shouldering stage.
In a second aspect, an embodiment of the present application provides a sapphire shoulder stage defect visual inspection device, the device including:
the training module is used for training the variation automatic encoder model based on the sample image set of the sapphire in the shouldering stage to obtain a picture generation model;
the detection module is used for collecting an image to be detected of the sapphire to be detected in the shouldering stage, inputting the image to be detected into the picture generation model and obtaining a reconstructed image;
the determining module is used for determining whether the sapphire to be detected has defects in the shouldering stage or not based on the comparison of the reconstructed image and the image to be detected.
In a third aspect, an embodiment of the present application provides a sapphire shoulder-stage defect visual detection system, which is characterized in that the system includes an image acquisition device for acquiring an image of a sapphire to be detected in a shoulder stage, and a detection device as described in the second aspect connected to the image acquisition device.
In a fourth aspect, an embodiment of the present application proposes a computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the steps of the method according to the first aspect when executing the computer program.
Compared with the prior art, the method, the device, the system and the computer equipment are characterized in that the image generation model is obtained by training the variation automatic encoder model based on the sample image set of the sapphire in the shouldering stage, the image to be detected of the sapphire to be detected in the shouldering stage is collected and input into the image generation model to obtain the reconstructed image, and whether the defect exists in the sapphire to be detected in the shouldering stage is determined based on the comparison of the reconstructed image and the image to be detected. According to the technical scheme, the defect detection of the sapphire in the shouldering stage can be rapidly and accurately realized, so that the qualification rate of sapphire preparation is improved.
Drawings
FIG. 1 is a schematic diagram of a terminal in an embodiment;
FIG. 2 is a flow chart of a method for visually inspecting defects in a sapphire shouldering stage according to an embodiment;
FIG. 3 is a flow chart of a model training method according to an embodiment;
FIG. 4 is a flow chart illustrating a defect determination method according to an embodiment;
FIG. 5 is a second flow chart of a defect determining method according to an embodiment;
FIG. 6 is a schematic diagram of an overall process of a visual inspection method for defects in a sapphire shouldering stage according to an embodiment;
FIG. 7 is a schematic diagram showing a module connection of a visual inspection device for defects in a sapphire shouldering stage according to an embodiment;
FIG. 8 is a schematic diagram of a visual inspection system for defects in a sapphire shoulder stage according to an embodiment;
fig. 9 is a schematic structural diagram of a computer device in an embodiment.
Detailed Description
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are used in the description of the embodiments will be briefly described below. It is apparent that the drawings in the following description are only some examples or embodiments of the present application, and it is apparent to those of ordinary skill in the art that the present application may be applied to other similar situations according to the drawings without inventive effort. Unless otherwise apparent from the context of the language or otherwise specified, like reference numerals in the figures refer to like structures or operations.
As used in the specification and in the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.
While the present application makes various references to certain modules in a system according to embodiments of the present application, any number of different modules may be used and run on a computing device and/or processor. The modules are merely illustrative and different aspects of the systems and methods may use different modules.
It will be understood that when an element or module is referred to as being "connected," "coupled" to another element, module, or block, it can be directly connected or coupled or in communication with the other element, module, or block, or intervening elements, modules, or blocks may be present unless the context clearly dictates otherwise. The term "and/or" as used herein may include any and all combinations of one or more of the associated listed items.
The visual detection method for the defects of the sapphire shoulder stage, provided by the application, can be applied to a terminal shown in figure 1. As shown in fig. 1, the terminal may include one or two (only one is shown in fig. 1) processors 102 and a memory 104 for storing data, wherein the processors 102 may include, but are not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA. The terminal may also include a transmission device 106 for communication functions and an input-output device 108. It will be appreciated by those skilled in the art that the structure shown in fig. 1 is merely illustrative and is not intended to limit the structure of the terminal. For example, the terminal may also include more or fewer components than shown in fig. 1, or have a different configuration than shown in fig. 1.
The memory 104 may be used to store a computer program, for example, a software program of application software and a module, such as a computer program corresponding to the sapphire shoulder-stage defect visual inspection method in the present embodiment, and the processor 102 executes the computer program stored in the memory 104 to perform various functional applications and data processing, that is, implement the above-mentioned method. Memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory remotely located relative to the processor 102, which may be connected to the terminal via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device 106 is used to receive or transmit data via a network. The network includes a wireless network provided by a communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (NIC) that may be connected to other network devices through a base station to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module for communicating with the internet wirelessly.
In an embodiment, as shown in fig. 2, a method for visually detecting defects in a sapphire shoulder stage is provided, and the method is applied to the terminal in fig. 1 for illustration, and includes the following steps:
s202: training the variation automatic encoder model based on a sample image set of the sapphire in the shouldering stage to obtain a picture generation model.
The sample image set comprises a normal state image of the sapphire in the shouldering stage without defects and an abnormal state image with defects.
Specifically, an image acquisition device is adopted to acquire a normal state image and an abnormal state image of the sapphire in the shouldering stage. The image acquisition device is, for example, an area camera.
The sapphire is rotated by rotation of the seed rod during the shouldering stage. In order to ensure the integrity of the concentrated crystal shoulder edge lines and the shoulder surfaces of the sample images, a plurality of images belonging to the same shoulder are spliced to obtain a complete state image so as to improve the precision of a picture generation model.
The number of spliced images is determined according to the working distance of the area array camera, the rotation speed of the seed crystal rod and the clear imaging field area. If the clear view area is large, less image stitching is required; if the clear field of view area is small, more image stitching is required.
S204: and acquiring an image to be detected of the sapphire to be detected in the shouldering stage, and inputting the image to be detected into the picture generation model to obtain a reconstructed image.
It should be noted that, the image to be measured is also obtained by splicing a plurality of sub-images to be measured shot by the image acquisition device, and each sub-image to be measured corresponds to different imaging angles of the sapphire to be measured in the shouldering stage.
The trained picture generation model is provided with the characteristics of the normal state image extracted and the normal state reconstructed image obtained by reconstruction, namely the normal state image with defects is input into the trained picture generation model, and then the normal state image (reconstructed image) without defects is obtained.
S206: and determining whether the sapphire to be detected has defects in the shouldering stage or not based on the comparison of the reconstructed image and the image to be detected.
Under the condition that the image to be measured has defects, the reconstructed image and the image to be measured have differences, and whether the sapphire to be measured has defects in the shouldering stage can be determined through comparison of the reconstructed image and the image to be measured.
Based on the steps S202-S206, training the variation automatic encoder model based on a sample image set of the sapphire in the shouldering stage to obtain a picture generation model, collecting an image to be detected of the sapphire in the shouldering stage, inputting the image to be detected into the picture generation model to obtain a reconstructed image, and based on comparison of the reconstructed image and the image to be detected, rapidly and accurately determining whether the sapphire to be detected has defects in the shouldering stage, so that the qualification rate of sapphire preparation is improved.
In step S202, as shown in fig. 3, the training the automatic variation encoder model based on the sample image set of the sapphire in the shoulder stage, to obtain a picture generation model includes:
s302: and dividing the sample image set into a training set, a verification set and a test set based on a preset proportion.
The training set and the verification set are composed of sample images of sapphire, wherein the sample images do not have defects in the shouldering stage, the test set is composed of sample images of sapphire, the sample images of sapphire do not have defects in the shouldering stage, and each sample image is not repeated.
In an example embodiment, the sample image set includes 2000 images, and the training set, the validation set, and the test set are in a preset ratio of 8:1: 1. For images with defects, marking of the location of the defect can be performed.
S304: and training the variation automatic encoder model based on the training set to obtain an initial picture generation model.
The variable automatic encoder model adopts a multi-scale structure, the encoding network is connected with the corresponding decoding network through the layers, each layer is provided with a respective hidden variable layer, the generalization capability is enhanced through a self-attention mechanism, and the hidden variable starts from the deepest layer of the encoding network and is fed back to each layer step by step.
In order to improve the quality of the image generated by the model, the network of the variational automatic encoder model adopts a U-net form, but each layer of network is connected with each other, and each layer of network maintains the encoding dimension of the variational automatic encoder.
In order to increase the speed of model reasoning, the network of the variational automatic encoder model adopts mixed precision calculation.
S306: and continuously verifying the picture generation model in the training process based on the verification set so as to adjust the super-parameters of the model training algorithm based on the verification result until the test result based on the test set meets the preset condition.
In order to improve the generalization capability of the model, the super-parameters of the model training algorithm are adjusted by adopting a genetic algorithm, so that the test result of the test set meets the preset condition.
The preset conditions are, for example: the accuracy of the cross ratio detection of the model subjected to super parameter adjustment to the test set reaches more than 60%.
In step S204, as shown in fig. 4, the determining whether the sapphire to be measured has a defect in the shouldering stage based on the comparison between the reconstructed image and the image to be measured includes:
s402: comparing the reconstructed image with the image to be detected to obtain a gray level difference image;
s404: and determining whether the sapphire to be detected has defects in the shouldering stage or not based on the gray level difference image.
In this embodiment, the reconstructed image and the image to be measured are compared to obtain a gray level difference image, and whether the sapphire to be measured has defects in the shouldering stage can be determined based on the gray level difference image.
In a specific embodiment, as shown in fig. 5, the determining, based on the gray level difference image, whether the sapphire to be tested has a defect in the shouldering stage includes:
s502: clustering the gray level difference images to obtain background clusters and defect clusters;
for example, clustering is carried out on the gray level difference images by adopting a DBSCAN clustering algorithm based on density, so as to obtain background clusters and defect clusters.
S504: and carrying out binarization processing on the gray level difference image based on the background cluster and the defect cluster to obtain a binarized image.
And finding a binarization threshold according to the background cluster and the defect cluster, and carrying out binarization processing on the gray level difference image according to the binarization threshold to obtain a binarization image.
S506: and determining whether the sapphire to be detected has defects in the shouldering stage or not based on the area of the region, corresponding to the defect cluster, in the binarized image.
If the area of the region is larger than the preset area, determining that the sapphire to be tested has defects in the shouldering stage; otherwise, determining that the sapphire to be measured has no defect in the shouldering stage.
Based on the defect detection method, whether the sapphire to be detected has defects in the shouldering stage can be rapidly and accurately judged.
Further, if the sapphire to be measured has defects in the shouldering stage, after the defects are cleaned, re-seeding and shouldering the sapphire to be measured until the sapphire to be measured has no defects in the shouldering stage. And finally, storing the image to be measured.
Further, defect detection is performed at the shouldering stage of the sapphire according to a preset frequency. The shouldering stage of sapphire is approximately 3-4 days, and defect detection is performed by using the detection method at a frequency of three times a day, for example.
The overall flow chart of the sapphire shouldering stage defect visual detection method is shown in fig. 6, firstly, a sample image set of the sapphire at the shouldering stage is collected, a variation automatic encoder model is trained by the sample image set to obtain a picture generation model, then an image to be detected of the sapphire at the stone shouldering stage is input into the picture generation model to obtain a reconstructed image, whether the sapphire to be detected has defects at the shouldering stage is determined based on comparison of the reconstructed image and the image to be detected, if the defects are cleaned, the sapphire to be detected is subjected to seeding again and shouldering, and finally the image to be detected is stored.
It should be understood that, although the steps in the above-described flowcharts are shown in order as indicated by the arrows, these steps are not necessarily performed in order as 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 above may include a plurality of steps or stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of execution of the steps or stages is not necessarily sequential, but may be performed in turn or alternately with at least a part of other steps or stages.
In one embodiment, as shown in fig. 7, there is provided a sapphire shoulder stage defect visual inspection apparatus, the apparatus comprising:
the training module 702 is configured to train the variation automatic encoder model based on a sample image set of the sapphire in a shoulder stage, so as to obtain a picture generation model;
the detection module 704 is configured to collect an image to be detected of the sapphire to be detected at the shouldering stage, and input the image to the picture generation model to obtain a reconstructed image;
and the determining module 706 is configured to determine whether the sapphire to be tested has a defect in the shouldering stage based on the comparison between the reconstructed image and the image to be tested.
In this embodiment, the training module trains the variation automatic encoder model based on the sample image set of the sapphire in the shouldering stage to obtain a picture generation model, the detecting module collects the image to be detected of the sapphire in the shouldering stage, inputs the image to be detected into the picture generation model to obtain a reconstructed image, and the determining module determines whether the sapphire to be detected has defects in the shouldering stage based on the comparison of the reconstructed image and the image to be detected. According to the technical scheme, the defect detection of the sapphire in the shouldering stage can be rapidly and accurately realized, so that the qualification rate of sapphire preparation is improved.
For specific limitation of the defect visual inspection device in the sapphire shouldering stage, reference may be made to the limitation of the defect visual inspection method hereinabove, and no further description is given here. The above-mentioned sapphire shoulder stage defect visual inspection device can be realized by all or part of software, hardware and their combination. 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, as shown in fig. 8, there is provided a sapphire shoulder-stage defect vision inspection system, which includes an image capturing device 802 for capturing an image of sapphire to be inspected at the shoulder stage, and an inspection device (not shown in the drawings) as in the above embodiment connected to the image capturing device.
The image acquisition device 802 is installed in the camera mount 804, and the camera mount 804 is connected with the vision observation window 806, and the image acquisition device 802 can gather the sapphire through the vision observation window 806 and put the image of shoulder stage, and the crystal growth bell 808 is located to the vision observation window 806, and crystal growth bell 808 still is connected with seed pole 810 that can rotate.
In one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 9. The computer device includes a processor, a memory, and a network interface 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, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is for storing motion detection data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program, when executed by a processor, implements the steps of any of the sapphire shoulder-stage defect vision inspection method embodiments described above.
It will be appreciated by persons skilled in the art that the architecture shown in fig. 9 is merely a block diagram of some of the architecture relevant to the present inventive arrangements and is not limiting as to the computer device to which the present inventive arrangements are applicable, 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 readable storage medium is provided having a computer program stored thereon, which when executed by a processor, implements the steps of any of the sapphire shoulder stage defect vision inspection method embodiments described above.
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, which may be stored on a non-transitory computer readable storage medium and which, when executed, may comprise the steps of the above-described embodiments of the methods. Any reference to memory, storage, database, or other medium used in 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, or the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (StaticRandom Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like.
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 foregoing examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
Claims (10)
1. A visual inspection method for defects in a sapphire shouldering stage, the method comprising:
training the variation automatic encoder model based on a sample image set of the sapphire in the shouldering stage to obtain a picture generation model;
collecting an image to be detected of the sapphire to be detected in a shouldering stage, and inputting the image to be detected into the picture generation model to obtain a reconstructed image;
and determining whether the sapphire to be detected has defects in the shouldering stage or not based on the comparison of the reconstructed image and the image to be detected.
2. The method of claim 1, wherein training the variational automatic encoder model based on the sapphire sample image set at the shouldering stage to obtain a picture generation model comprises:
dividing the sample image set into a training set, a verification set and a test set based on a preset proportion; the training set and the verification set are composed of sample images of sapphire, wherein the sample images do not have defects in the shouldering stage; the test set is composed of sample images of the sapphire with defects in the shouldering stage;
training the variation automatic encoder model based on the training set to obtain an initial picture generation model;
and continuously verifying the picture generation model in the training process based on the verification set so as to adjust the super-parameters of the model training algorithm based on the verification result until the test result based on the test set meets the preset condition.
3. The method of claim 1, wherein determining whether the sapphire to be measured has a defect in the shouldering stage based on the comparison of the reconstructed image and the image to be measured comprises:
comparing the reconstructed image with the image to be detected to obtain a gray level difference image;
and determining whether the sapphire to be detected has defects in the shouldering stage or not based on the gray level difference image.
4. The method of claim 3, wherein determining whether the sapphire to be tested is defective in the shouldering stage based on the grayscale difference image comprises:
clustering the gray level difference images to obtain background clusters and defect clusters;
based on the background cluster and the defect cluster, carrying out binarization processing on the gray level difference image to obtain a binarized image;
and determining whether the sapphire to be detected has defects in the shouldering stage or not based on the area of the region, corresponding to the defect cluster, in the binarized image.
5. The method of claim 4, wherein determining whether the sapphire to be tested has a defect at the shouldering stage based on the area of the region in the binary image corresponding to the defect cluster comprises:
if the area of the region is larger than the preset area, determining that the sapphire to be tested has defects in the shouldering stage; otherwise, determining that the sapphire to be measured has no defect in the shouldering stage.
6. The method according to claim 1, wherein the sample image in the sample image set and the image to be measured are respectively obtained by stitching a plurality of sub-images shot by an image acquisition device, and each sub-image corresponds to a different imaging angle of the sapphire in the shouldering stage.
7. The method according to any one of claims 1 to 6, further comprising:
if the sapphire to be tested has defects in the shouldering stage, after the defects are cleaned, re-seeding and shouldering the sapphire to be tested until the sapphire to be tested has no defects in the shouldering stage.
8. A sapphire shoulder stage defect vision inspection device, the device comprising:
the training module is used for training the variation automatic encoder model based on the sample image set of the sapphire in the shouldering stage to obtain a picture generation model;
the detection module is used for collecting an image to be detected of the sapphire to be detected in the shouldering stage, inputting the image to be detected into the picture generation model and obtaining a reconstructed image;
the determining module is used for determining whether the sapphire to be detected has defects in the shouldering stage or not based on the comparison of the reconstructed image and the image to be detected.
9. A sapphire shouldering stage defect visual detection system, characterized in that the system comprises an image acquisition device for acquiring an image to be detected of the sapphire to be detected in the shouldering stage, and the detection device according to claim 8 connected with the image acquisition device.
10. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311145368.2A CN116883399A (en) | 2023-09-06 | 2023-09-06 | Visual detection method, device, system and equipment for defects in sapphire shouldering stage |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311145368.2A CN116883399A (en) | 2023-09-06 | 2023-09-06 | Visual detection method, device, system and equipment for defects in sapphire shouldering stage |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116883399A true CN116883399A (en) | 2023-10-13 |
Family
ID=88262529
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311145368.2A Pending CN116883399A (en) | 2023-09-06 | 2023-09-06 | Visual detection method, device, system and equipment for defects in sapphire shouldering stage |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116883399A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117456292A (en) * | 2023-12-26 | 2024-01-26 | 浙江晶盛机电股份有限公司 | Sapphire defect detection method, device, electronic device and storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110220912A (en) * | 2019-05-28 | 2019-09-10 | 太原理工大学 | A kind of sapphire growth defective vision detection method based on deep learning |
| CN111402197A (en) * | 2020-02-09 | 2020-07-10 | 西安工程大学 | Detection method for yarn-dyed fabric cut piece defect area |
| CN111553929A (en) * | 2020-05-12 | 2020-08-18 | 重庆邮电大学 | Mobile phone screen defect segmentation method, device and equipment based on converged network |
| CN113256602A (en) * | 2021-06-10 | 2021-08-13 | 中科云尚(南京)智能技术有限公司 | Unsupervised fan blade defect detection method and system based on self-encoder |
| CN114463280A (en) * | 2022-01-12 | 2022-05-10 | 西安电子科技大学 | Chip surface defect parallel detection method based on improved convolution variational self-encoder |
| US20220207707A1 (en) * | 2020-12-30 | 2022-06-30 | Hon Hai Precision Industry Co., Ltd. | Image defect detection method, electronic device using the same |
| CN114764768A (en) * | 2020-12-31 | 2022-07-19 | 富泰华工业（深圳）有限公司 | Defect detection and classification method and device, electronic equipment and storage medium |
| CN114862776A (en) * | 2022-04-22 | 2022-08-05 | 深圳职业技术学院 | Product surface defect detection method and device, computer equipment and medium |
| CN115375617A (en) * | 2022-06-28 | 2022-11-22 | 鲁班嫡系机器人（深圳）有限公司 | Defect detection and training method and device, storage medium and equipment |
| WO2023050563A1 (en) * | 2021-09-29 | 2023-04-06 | 西安工程大学 | Autoencoder-based detection method for defective area of colored textured fabric |
| CN115984276A (en) * | 2023-03-20 | 2023-04-18 | 内蒙古晶环电子材料有限公司 | Shoulder-laying defect real-time detection method and device, computer equipment and storage medium |
-
2023
- 2023-09-06 CN CN202311145368.2A patent/CN116883399A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110220912A (en) * | 2019-05-28 | 2019-09-10 | 太原理工大学 | A kind of sapphire growth defective vision detection method based on deep learning |
| CN111402197A (en) * | 2020-02-09 | 2020-07-10 | 西安工程大学 | Detection method for yarn-dyed fabric cut piece defect area |
| CN111553929A (en) * | 2020-05-12 | 2020-08-18 | 重庆邮电大学 | Mobile phone screen defect segmentation method, device and equipment based on converged network |
| US20220207707A1 (en) * | 2020-12-30 | 2022-06-30 | Hon Hai Precision Industry Co., Ltd. | Image defect detection method, electronic device using the same |
| CN114764768A (en) * | 2020-12-31 | 2022-07-19 | 富泰华工业（深圳）有限公司 | Defect detection and classification method and device, electronic equipment and storage medium |
| CN113256602A (en) * | 2021-06-10 | 2021-08-13 | 中科云尚(南京)智能技术有限公司 | Unsupervised fan blade defect detection method and system based on self-encoder |
| WO2023050563A1 (en) * | 2021-09-29 | 2023-04-06 | 西安工程大学 | Autoencoder-based detection method for defective area of colored textured fabric |
| CN114463280A (en) * | 2022-01-12 | 2022-05-10 | 西安电子科技大学 | Chip surface defect parallel detection method based on improved convolution variational self-encoder |
| CN114862776A (en) * | 2022-04-22 | 2022-08-05 | 深圳职业技术学院 | Product surface defect detection method and device, computer equipment and medium |
| CN115375617A (en) * | 2022-06-28 | 2022-11-22 | 鲁班嫡系机器人（深圳）有限公司 | Defect detection and training method and device, storage medium and equipment |
| CN115984276A (en) * | 2023-03-20 | 2023-04-18 | 内蒙古晶环电子材料有限公司 | Shoulder-laying defect real-time detection method and device, computer equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 张奔: "基于机器视觉的轴承滚子表面缺陷检测研究", 中国优秀硕士学位论文全文数据库工程科技Ⅱ辑, pages 029 - 72 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117456292A (en) * | 2023-12-26 | 2024-01-26 | 浙江晶盛机电股份有限公司 | Sapphire defect detection method, device, electronic device and storage medium |
| CN117456292B (en) * | 2023-12-26 | 2024-04-19 | 浙江晶盛机电股份有限公司 | Sapphire defect detection method, device, electronic device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111553303B (en) | Remote sensing orthographic image dense building extraction method based on convolutional neural network | |
| CN109712127B (en) | Power transmission line fault detection method for machine inspection video stream | |
| CN116883399A (en) | Visual detection method, device, system and equipment for defects in sapphire shouldering stage | |
| CN111862013B (en) | Insulator detection method, device and equipment based on deep convolutional neural network | |
| JP2023139099A (en) | Learning data collecting apparatus, learning data collecting method, and program | |
| CN110826588A (en) | Drainage pipeline defect detection method based on attention mechanism | |
| CN110555831B (en) | Deep learning-based drainage pipeline defect segmentation method | |
| CN110736748A (en) | Immunohistochemical nuclear plasma staining section diagnosis method and system | |
| CN113205039B (en) | Power equipment fault image recognition disaster investigation system and method based on multiple DCNN networks | |
| CN111178392B (en) | Aero-engine hole detection image damage segmentation method based on deep neural network | |
| CN111160432A (en) | Automatic classification method and system for panel production defects | |
| CN104252056A (en) | Detection method and device of substrate | |
| CN112785578A (en) | Road crack detection method and system based on U-shaped codec neural network | |
| CN114862832A (en) | Method, device and equipment for optimizing defect detection model and storage medium | |
| CN113870204A (en) | Method and device for detecting abnormality of optical glass | |
| CN106897683B (en) | Ground object detection method and system of remote sensing image | |
| CN117095246A (en) | Polarization imaging-based deep learning pointer instrument reading identification method | |
| CN116433647A (en) | Insulator image quality evaluation method and system based on multitask learning | |
| CN116778357A (en) | Power line unmanned aerial vehicle inspection method and system utilizing visible light defect identification | |
| CN111652932B (en) | Vector verification method, device and equipment for remote sensing image geographic positioning | |
| CN113570560A (en) | Method for rapidly detecting geometric model errors of remote sensing image | |
| CN113191389A (en) | Submarine pipeline autonomous inspection method and device based on optical vision technology | |
| KR102263029B1 (en) | Risk level estimation method for fire damaged structure | |
| CN116166966B (en) | Water quality degradation event detection method based on multi-mode data fusion | |
| CN111651648A (en) | Intelligent generation method and device for pole tower key component inspection plan |
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 |