CN112907498B - Pore identification method, device, equipment and storage medium - Google Patents
Pore identification method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112907498B CN112907498B CN201911130002.1A CN201911130002A CN112907498B CN 112907498 B CN112907498 B CN 112907498B CN 201911130002 A CN201911130002 A CN 201911130002A CN 112907498 B CN112907498 B CN 112907498B
- Authority
- CN
- China
- Prior art keywords
- pore
- image
- identification
- metallographic
- metallographic image
- 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.)
- Active
Links
- 239000011148 porous material Substances 0.000 title claims abstract description 196
- 238000000034 method Methods 0.000 title claims abstract description 66
- 238000003860 storage Methods 0.000 title claims abstract description 17
- 238000012549 training Methods 0.000 claims abstract description 60
- 239000002131 composite material Substances 0.000 claims abstract description 25
- 230000008569 process Effects 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims description 16
- 230000009467 reduction Effects 0.000 claims description 15
- 238000007906 compression Methods 0.000 claims description 12
- 238000002372 labelling Methods 0.000 claims description 10
- 239000011800 void material Substances 0.000 claims description 9
- 230000006835 compression Effects 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 6
- 230000006870 function Effects 0.000 description 7
- 230000007547 defect Effects 0.000 description 6
- 238000005070 sampling Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000007689 inspection Methods 0.000 description 4
- 239000000047 product Substances 0.000 description 4
- 238000001914 filtration Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 229920000049 Carbon (fiber) Polymers 0.000 description 2
- 239000004917 carbon fiber Substances 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000007667 floating Methods 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 238000010587 phase diagram Methods 0.000 description 2
- 239000011347 resin Substances 0.000 description 2
- 229920005989 resin Polymers 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000000227 grinding Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005498 polishing Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 239000002699 waste material Substances 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10056—Microscopic image
- G06T2207/10061—Microscopic image from scanning electron microscope
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses a pore identification method, a device, equipment and a storage medium, wherein the method comprises the following steps: acquiring a metallographic image of the composite material; inputting the metallographic image into a pre-trained pore recognition model; the method comprises the steps of determining a pore edge pixel point of a training sample by performing bilinear interpolation on the compressed training sample in the training process of the pore identification model; and determining a pore recognition result of the metallographic image according to the output result of the pore recognition model. Through the technical scheme provided by the operation of the request, the problems that the pore statistics work is time-consuming and labor-consuming and the statistics error is large can be solved, and the effect of improving the efficiency and the accuracy of pore identification is achieved.
Description
Technical Field
The embodiment of the invention relates to a computer technology, in particular to a pore identification method, a device, equipment and a storage medium.
Background
The pores of the composite material are gas hole type defects distributed in the resin layer and the carbon fiber layer of the composite material laminated structure, the diameters of the holes are generally distributed in the range of 1-100 mu m, and the gas hole type defects are the most common internal quality defects in the composite material product. A large number of documents and test data show that the effect of pores on the interlaminar shear strength of a composite material workpiece is remarkable. Therefore, pore detection plays a very positive and important role in evaluating the internal quality of a composite product, improving the quality and continuously improving the product process as an important component of nondestructive detection.
At present, composite porosity is usually obtained by manual identification or identification by an image analyzer.
The manual identification is very huge in the number of collected metallographic pictures, so that the pore statistics work is time-consuming and labor-consuming, and the statistical results of different staff can be different, so that the efficiency is very low. The image analyzer recognizes that the influence of human factors is small, but the image analyzer is easily influenced by the metallographic surface quality, and the statistical error is large.
Disclosure of Invention
The embodiment of the invention provides a method, a device, equipment and a storage medium for identifying pores, which are used for realizing the effect of improving the efficiency and the accuracy of pore identification.
In a first aspect, an embodiment of the present invention provides a method for identifying a pore, including:
acquiring a metallographic image of the composite material;
inputting the metallographic image into a pre-trained pore recognition model; the method comprises the steps of determining a pore edge pixel point of a training sample by performing bilinear interpolation on the compressed training sample in the training process of the pore identification model;
and determining a pore recognition result of the metallographic image according to the output result of the pore recognition model.
In a second aspect, an embodiment of the present invention further provides an apparatus for identifying a hole, including:
The image acquisition module is used for acquiring a metallographic image of the composite material;
the model input module is used for inputting the metallographic image into a pre-trained pore recognition model; the method comprises the steps of determining a pore edge pixel point of a training sample by performing bilinear interpolation on the compressed training sample in the training process of the pore identification model;
and the recognition result determining module is used for determining the pore recognition result of the metallographic image according to the output result of the pore recognition model.
In a third aspect, an embodiment of the present invention further provides an apparatus, including:
one or more processors;
Storage means for storing one or more programs,
The one or more programs, when executed by the one or more processors, cause the one or more processors to implement the aperture identification method as described above.
In a fourth aspect, embodiments of the present invention also provide a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a void identification method as described above.
According to the embodiment of the invention, a metallographic image of the composite material is obtained; inputting the metallographic image into a pre-trained pore recognition model; the method comprises the steps of determining a pore edge pixel point of a training sample by performing bilinear interpolation on the compressed training sample in the training process of the pore identification model; and determining a pore recognition result of the metallographic image according to the output result of the pore recognition model. By adopting the technical scheme provided by the invention, the problems of time and labor waste and larger statistical error in pore statistics work are solved, and the effect of improving the efficiency and accuracy of pore identification is realized.
Drawings
FIG. 1 is a flowchart of a method for identifying voids according to a first embodiment of the present invention;
FIG. 2 is a training flow chart of a void identification model according to a second embodiment of the present invention;
Fig. 3 is a schematic structural diagram of a hole recognition device according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of an apparatus according to a fourth embodiment of the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting thereof. It should be further noted that, for convenience of description, only some, but not all of the structures related to the present invention are shown in the drawings.
Example 1
Fig. 1 is a flowchart of a pore identification method according to an embodiment of the present invention, where the method may be applied to identify pores in a metallographic image of a composite material, and the method may be performed by a pore identification device according to an embodiment of the present invention, and the device may be implemented by software and/or hardware. Referring to fig. 1, a method for identifying a pore provided in this embodiment includes:
S110, acquiring a metallographic image of the composite material.
The composite material is a new material which is formed by artificially optimizing and combining material components with different properties by adopting a material preparation technology, and is applied to the fields of aviation, aerospace, high-end automobiles and the like. The metallographic phase of the composite material is a section obtained by cutting, embedding, grinding, polishing and the like of the composite material.
The metallographic section can be observed through a metallographic microscope, a metallographic image can be obtained, and at least one metallographic image can be obtained by the same composite material.
S120, inputting the metallographic image into a pre-trained pore recognition model; and in the training process, the pore identification model determines pore edge pixel points of the training sample by performing bilinear interpolation on the compressed training sample.
Wherein, the pores of the composite material are gas hole type defects distributed in the resin layer and the carbon fiber layer of the laminated structure of the composite material, the diameters of the holes are generally in the range of 1-100 mu m, and the gas hole type defects are internal quality defects in the composite material product. The pore recognition model is used for recognizing a pore part in an input metallographic image, and may be a machine learning model such as a convolutional neural network, which is not limited in this embodiment.
In the training process of the pore recognition model, a metallographic image is compressed, and the coordinates of sampling points are usually floating points in the compression process, so that the pixel value of the compressed sampling points is obtained by using an interpolation method. At this time, the pixel value of the point is calculated by four pixel values adjacent to each other around the point in a bilinear interpolation mode.
In the actual recognition process, each pixel point is detected, and if the probability of other pixel points adjacent to the pixel is high, for example, more than eighty percent, and the pixel points also accord with the recognition rule, the pixel points are judged to belong to the pore edge points, so that the pore edge pixel points are determined.
S130, determining a pore recognition result of the metallographic image according to the output result of the pore recognition model.
The output result of the pore identification model can be the range and/or the position distribution of each pore of the pores on the golden image. The pore identification result may be whether a pore exists on the golden phase diagram, or may be a specific kind of pore identification, which is not limited in this embodiment.
According to the technical scheme provided by the embodiment, a metallographic image of the composite material is taken; inputting the metallographic image into a pre-trained pore recognition model; the method comprises the steps of determining a pore edge pixel point of a training sample by performing bilinear interpolation on the compressed training sample in the training process of the pore identification model; and determining a pore recognition result of the metallographic image according to the output result of the pore recognition model. The problem that the pore statistics work is time-consuming and labor-consuming and the statistics error is large is solved, and the effect of improving the efficiency and the accuracy of pore identification is achieved.
On the basis of the above technical solution, optionally, after determining the pore recognition result of the metallographic image according to the output result of the pore recognition model, the method further includes:
Performing spot check on the pore recognition result of the metallographic image;
if the accuracy of the pore identification result of the metallographic image is lower than a preset reference value, performing secondary labeling on the pores of the metallographic image, and updating the pore identification model by taking the metallographic image after secondary labeling as a training sample.
The sampling inspection of the pore identification result can be performed manually, and the pore identification result of the output phase image is inspected. If the accuracy of the pore identification result of the metallographic image is not lower than the preset reference value, the pore identification model is continuously put into use.
In the identification process, an unexpected pore type may occur, which has not occurred in the previous training sample, thus resulting in an accuracy of the pore identification result lower than a preset reference value, and thus, when an error is found in the spot check, the wrong pore type will be identified. Labeling is performed manually, and images after manual labeling are used as training samples, so that the pore recognition model is updated.
According to the embodiment, on the basis of the embodiment, through carrying out sampling inspection and secondary labeling on the pore identification result of the metallographic image, the reduction of the accuracy of the pore identification result caused by unexpected pore types is prevented, and the accuracy of the pore identification and the application range of the pore identification method are improved.
Example two
Fig. 2 is a training flowchart of a pore recognition model according to a second embodiment of the present invention. The technical scheme is to supplement the training process of the pre-trained pore recognition model. Compared with the scheme, the scheme is specifically characterized in that the training process of the pre-trained pore recognition model comprises the following steps of:
the training process of the pre-trained pore recognition model is as follows:
Inputting a metallographic image sample, and carrying out noise reduction treatment on the metallographic image sample;
extracting a characteristic block from the metallographic image sample after the noise reduction treatment;
Compressing the characteristic image blocks, and obtaining compressed characteristic image blocks after bilinear interpolation;
performing aperture edge point identification processing on the compressed characteristic image block to obtain aperture edge pixel points of the compressed characteristic image block;
And determining the pore contour formed by the pore edge pixel points of the compressed characteristic block by adopting a fitting function, and taking the pore contour as a pore recognition result.
Specifically, a training flowchart of the pore recognition model is shown in fig. 2:
S210, inputting a metallographic image sample, and carrying out noise reduction treatment on the metallographic image sample.
The metallographic image sample can be a metallographic image acquired in advance, and the metallographic image is used as a training sample.
The noise reduction process may be, but is not limited to, employing median filtering, maximum filtering, and/or minimum filtering algorithms, etc.
S220, extracting a characteristic block from the metallographic image sample after the noise reduction processing.
The feature block is extracted by selecting a pore candidate region of the image obtained by the noise reduction processing by using information such as texture, edge, color and the like in the image after the noise reduction processing, wherein the pore candidate region is a range where pores are approximately located, and a part which may be the pores is outlined in a square frame, a circle, an ellipse, an irregular polygon and the like to be used as a region needing further processing.
And S230, compressing the characteristic image blocks, and obtaining compressed characteristic image blocks after bilinear interpolation.
The compression processing is to compress the picture, and then calculate the pixel value of the point with the coordinates of the floating point number due to compression by adopting a bilinear interpolation method. The pixel points of the compressed feature image blocks are in one-to-one correspondence with the pixel points of the original image.
S240, performing aperture edge point identification processing on the compressed characteristic image block to obtain aperture edge pixel points of the compressed characteristic image block.
And analyzing the pore region by the pore identification model to generate an identification rule, such as a gray level change rule, of the pixel points at the pore edge in the pore identification model, so as to obtain the pixel points at the pore edge of the compressed characteristic block.
S250, determining the pore contour formed by the pore edge pixel points of the compressed characteristic block by adopting a fitting function, and taking the pore contour as a pore identification result.
The fitting function is used to line the obtained aperture edge pixels, thereby forming the outline of the aperture. The aperture outline can be formed in the original image by reversely mapping the pixel points at the edge of the aperture of the compressed characteristic block back to the original image; the pore contours can also be obtained from the compressed feature blocks and mapped back to the original figure. After the pore identification result is obtained, the pore identification result can be compared with the marking direction of the metallographic image, and whether the determined pore identification result is consistent with the marking information or not is determined.
Based on the embodiment, the embodiment identifies the pore contour through the trained pore identification model, so that the pore range on the golden phase diagram is obtained, and the efficiency and the accuracy of pore identification are improved.
On the basis of the technical scheme, optionally, the metallographic image sample is a metallographic image sample with a pore mark;
Correspondingly, after determining the pore contour formed by the pore edge pixel points of the compressed characteristic block by adopting a fitting function, and taking the pore contour as a pore identification result, the method further comprises the following steps:
comparing the pore identification result with a pore mark of a metallographic image sample to obtain a comparison result;
If the comparison result meets the preset standard, the completion of the training of the pore recognition model is determined.
The selection of the metallographic image sample with the pore mark can be divided into a typical metallographic sample and a special metallographic sample; typical metallographic specimens need to be sufficiently clear and free of significant attachments, and special metallographic specimens include internally contaminated, surface scratched and attached, and the like, with the remainder being unpredictable in pore morphology. And marking all pore areas on the two types of samples, and inputting the marked samples into a pore identification model for training.
Comparing the result of the pore identification with a pore mark to obtain a comparison result;
if the comparison result meets the preset standard, for example, the accuracy rate reaches more than ninety percent, the completion of the training of the pore recognition model is determined. If the result does not meet the standard, the parameter in the training process can be adjusted so that the result meets the expected standard.
By marking the pores of the special metallographic sample, the inclusion, scratch and attachment are prevented from being mistakenly identified as the pores; and comparing the result of the pore identification with the pore mark until the result meets the preset standard, thereby improving the accuracy of the pore identification.
Based on the technical scheme, optionally, the compression ratio of the compression treatment is 1:16.
The compression process accelerates the processing speed of the pore recognition model, thereby improving the efficiency of pore recognition.
Example III
Fig. 3 is a schematic structural diagram of a hole recognition device according to a third embodiment of the present invention. The device can be realized by hardware and/or software, and the pore identification method provided by any embodiment of the invention can be executed, and has the corresponding functional modules and beneficial effects of the execution method. As shown in fig. 3, the apparatus includes:
an image acquisition module 310, configured to acquire a metallographic image of the composite material;
A model input module 320 for inputting the metallographic image to a pre-trained pore recognition model; the method comprises the steps of determining a pore edge pixel point of a training sample by performing bilinear interpolation on the compressed training sample in the training process of the pore identification model;
and the recognition result determining module 330 is configured to determine a pore recognition result of the metallographic image according to an output result of the pore recognition model.
According to the technical scheme provided by the embodiment, a metallographic image of the composite material is taken; inputting the metallographic image into a pre-trained pore recognition model; the method comprises the steps of determining a pore edge pixel point of a training sample by performing bilinear interpolation on the compressed training sample in the training process of the pore identification model; and determining a pore recognition result of the metallographic image according to the output result of the pore recognition model. The problem that the pore statistics work is time-consuming and labor-consuming and the statistics error is large is solved, and the effect of improving the efficiency and the accuracy of pore identification is achieved.
Based on the technical proposal, alternatively,
A model training module, the model training module comprising:
the sample noise reduction processing unit is used for inputting a metallographic image sample and carrying out noise reduction processing on the metallographic image sample;
The characteristic block extracting unit is used for extracting characteristic blocks from the metallographic image samples subjected to noise reduction treatment;
The characteristic image block compression unit is used for compressing the characteristic image block and obtaining a compressed characteristic image block after bilinear interpolation;
The pixel point acquisition unit is used for carrying out aperture edge point identification processing on the compressed characteristic image block to obtain aperture edge pixel points of the compressed characteristic image block;
The recognition result determining unit is used for determining the pore contour formed by the pore edge pixel points of the compressed characteristic block by adopting a fitting function, and the pore contour is used as a pore recognition result.
On the basis of the technical schemes, optionally, the metallographic image sample is a metallographic image sample with a pore mark;
Correspondingly, the device further comprises:
the comparison result acquisition module is used for comparing the pore recognition result with the pore mark of the metallographic image sample after the recognition result determination module to obtain a comparison result;
and the model training completion determining module is used for determining that the pore recognition model training is completed if the comparison result meets the preset standard.
Based on the above technical solutions, optionally, the compression ratio of the compression process is 1:16.
On the basis of the above technical solutions, optionally, the apparatus further includes:
The identification result sampling inspection module is used for sampling inspection of the pore identification result of the metallographic image after the identification result determination module;
And the secondary labeling module is used for secondarily labeling the pores of the metallographic image if the accuracy rate of the pore identification result of the metallographic image is lower than a preset reference value after the identification result determining module, and updating the pore identification model by taking the metallographic image after the secondary labeling as a training sample.
Example IV
Fig. 4 is a schematic structural diagram of an apparatus according to a fourth embodiment of the present invention, and as shown in fig. 4, the apparatus includes a processor 40, a memory 41, an input device 42 and an output device 43; the number of processors 40 in the device may be one or more, one processor 40 being taken as an example in fig. 4; the processor 40, the memory 41, the input means 42 and the output means 43 in the device may be connected by a bus or other means, in fig. 4 by way of example.
The memory 41 is a computer readable storage medium, and may be used to store a software program, a computer executable program, and modules, such as program instructions/modules corresponding to the void identification method in the embodiment of the present invention. The processor 40 performs various functional applications of the device and data processing, i.e., implements the above-described aperture identification method, by running software programs, instructions and modules stored in the memory 41.
The memory 41 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, at least one application program required for functions; the storage data area may store data created according to the use of the terminal, etc. In addition, memory 41 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some examples, memory 41 may further include memory located remotely from processor 40, which may be connected to the device 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.
Example five
A fifth embodiment of the present invention also provides a storage medium containing computer-executable instructions, which when executed by a computer processor, are for performing a void identification method, the method comprising:
acquiring a metallographic image of the composite material;
inputting the metallographic image into a pre-trained pore recognition model; the method comprises the steps of determining a pore edge pixel point of a training sample by performing bilinear interpolation on the compressed training sample in the training process of the pore identification model;
and determining a pore recognition result of the metallographic image according to the output result of the pore recognition model.
Of course, the storage medium containing the computer executable instructions provided in the embodiments of the present invention is not limited to the method operations described above, and may also perform the related operations in the pore identification method provided in any embodiment of the present invention.
From the above description of embodiments, it will be clear to a person skilled in the art that the present invention may be implemented by means of software and necessary general purpose hardware, but of course also by means of hardware, although in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as a floppy disk, a Read-only memory (ROM), a random access memory (RandomAccessMemory, RAM), a FLASH memory (FLASH), a hard disk or an optical disk of a computer, etc., and include several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments of the present invention.
It should be noted that, in the above-mentioned embodiments of the search apparatus, each unit and module included are only divided according to the functional logic, but not limited to the above-mentioned division, as long as the corresponding functions can be implemented; in addition, the specific names of the functional units are also only for distinguishing from each other, and are not used to limit the protection scope of the present invention.
Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.
Claims (8)
1. A method of identifying a void, comprising:
acquiring a metallographic image of the composite material;
inputting the metallographic image into a pre-trained pore recognition model; the method comprises the steps of determining a pore edge pixel point of a training sample by performing bilinear interpolation on the compressed training sample in the training process of the pore identification model;
determining a pore recognition result of the metallographic image according to the output result of the pore recognition model;
the training process of the pre-trained pore recognition model is as follows:
Inputting a metallographic image sample, and carrying out noise reduction treatment on the metallographic image sample;
extracting a characteristic block from the metallographic image sample after the noise reduction treatment;
Compressing the characteristic image blocks, and obtaining compressed characteristic image blocks after bilinear interpolation;
performing aperture edge point identification processing on the compressed characteristic image block to obtain aperture edge pixel points of the compressed characteristic image block;
determining the pore contour formed by the pore edge pixel points of the compressed characteristic block by adopting a fitting function, and taking the pore contour as a pore identification result;
the metallographic image sample is provided with a pore mark.
2. The method of claim 1, wherein after determining the aperture contour formed by the aperture edge pixels of the compressed feature tile using the fitting function as the aperture recognition result, the method further comprises:
comparing the pore identification result with a pore mark of a metallographic image sample to obtain a comparison result;
If the comparison result meets the preset standard, the completion of the training of the pore recognition model is determined.
3. The method of claim 1, wherein the compression process has a compression ratio of 1:16.
4. The method of claim 1, wherein after determining the void identification result of the metallographic image from the output result of the void identification model, the method further comprises:
Performing spot check on the pore recognition result of the metallographic image;
if the accuracy of the pore identification result of the metallographic image is lower than a preset reference value, performing secondary labeling on the pores of the metallographic image, and updating the pore identification model by taking the metallographic image after secondary labeling as a training sample.
5. A void identification device, comprising:
The image acquisition module is used for acquiring a metallographic image of the composite material;
the model input module is used for inputting the metallographic image into a pre-trained pore recognition model; the method comprises the steps of determining a pore edge pixel point of a training sample by performing bilinear interpolation on the compressed training sample in the training process of the pore identification model;
The recognition result determining module is used for determining a pore recognition result of the metallographic image according to the output result of the pore recognition model;
a model training module, the model training module comprising:
the sample noise reduction processing unit is used for inputting a metallographic image sample and carrying out noise reduction processing on the metallographic image sample;
The characteristic block extracting unit is used for extracting characteristic blocks from the metallographic image samples subjected to noise reduction treatment;
The characteristic image block compression unit is used for compressing the characteristic image block and obtaining a compressed characteristic image block after bilinear interpolation;
The pixel point acquisition unit is used for carrying out aperture edge point identification processing on the compressed characteristic image block to obtain aperture edge pixel points of the compressed characteristic image block;
The recognition result determining unit is used for determining the pore contour formed by the pore edge pixel points of the compressed characteristic block by adopting a fitting function, and taking the pore contour as a pore recognition result;
the metallographic image sample is provided with a pore mark.
6. The apparatus of claim 5, wherein the metallographic image sample is a metallographic image sample with void marks;
Correspondingly, the device further comprises:
the comparison result acquisition module is used for comparing the pore recognition result with the pore mark of the metallographic image sample after the recognition result determination module to obtain a comparison result;
and the model training completion determining module is used for determining that the pore recognition model training is completed if the comparison result meets the preset standard.
7. An aperture identification device, the device comprising:
one or more processors;
Storage means for storing one or more programs,
The one or more programs, when executed by the one or more processors, cause the one or more processors to implement the aperture identification method of any of claims 1-4.
8. A computer readable storage medium having stored thereon a computer program, which when executed by a processor implements the aperture identification method according to any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911130002.1A CN112907498B (en) | 2019-11-18 | 2019-11-18 | Pore identification method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911130002.1A CN112907498B (en) | 2019-11-18 | 2019-11-18 | Pore identification method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112907498A CN112907498A (en) | 2021-06-04 |
| CN112907498B true CN112907498B (en) | 2024-04-30 |
Family
ID=76103113
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911130002.1A Active CN112907498B (en) | 2019-11-18 | 2019-11-18 | Pore identification method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112907498B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115131334B (en) * | 2022-07-21 | 2023-07-25 | 北京汉飞航空科技有限公司 | Machine learning-based aerial small hole type identification and automatic sequencing method |
| CN117808856B (en) * | 2023-12-28 | 2024-08-30 | 中国人民解放军陆军装甲兵学院士官学校 | Component strength optimization method based on artificial intelligence |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102013210864A1 (en) * | 2012-06-19 | 2013-12-19 | GM Global Technology Operations, LLC (n.d. Ges. d. Staates Delaware) | Method for determining pore size and pore distribution in metal casting, involves grouping measured pores size and spaces in cluster for generating measuring value for pores size or pores distribution in sample on cluster-to-cluster basis |
| CN104766095A (en) * | 2015-04-16 | 2015-07-08 | 成都汇智远景科技有限公司 | Mobile terminal image identification method |
| CN105699341A (en) * | 2014-11-28 | 2016-06-22 | 中国科学院金属研究所 | A fluorescence metallographic measuring method for pores of a metal material |
| CN108416748A (en) * | 2018-02-26 | 2018-08-17 | 阿博茨德（北京）科技有限公司 | The image pre-processing method and device of JPEG compression document |
| WO2018166114A1 (en) * | 2017-03-13 | 2018-09-20 | 平安科技（深圳）有限公司 | Picture identification method and system, electronic device, and medium |
| CN108647588A (en) * | 2018-04-24 | 2018-10-12 | 广州绿怡信息科技有限公司 | Goods categories recognition methods, device, computer equipment and storage medium |
| CN109409428A (en) * | 2018-10-25 | 2019-03-01 | 北京木业邦科技有限公司 | Training method, device and the electronic equipment of plank identification and plank identification model |
| CN109615630A (en) * | 2019-01-18 | 2019-04-12 | 东北大学 | Semi-continuous casting alusil alloy Analysis on Microstructure method based on image processing techniques |
| CN109829483A (en) * | 2019-01-07 | 2019-05-31 | 鲁班嫡系机器人（深圳）有限公司 | Defect recognition model training method, device, computer equipment and storage medium |
| CN110110661A (en) * | 2019-05-07 | 2019-08-09 | 西南石油大学 | A kind of rock image porosity type recognition methods based on unet segmentation |
| CN110308151A (en) * | 2019-07-22 | 2019-10-08 | 重庆大学 | A kind of surface of workpiece defect identification method and device based on machine vision |
| CN110348461A (en) * | 2019-07-05 | 2019-10-18 | 江苏海事职业技术学院 | A kind of Surface Flaw feature extracting method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9031990B2 (en) * | 2009-08-11 | 2015-05-12 | Q2 Management Inc. | Data processing system for manufacturing quality inspection management system |
-
2019
- 2019-11-18 CN CN201911130002.1A patent/CN112907498B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102013210864A1 (en) * | 2012-06-19 | 2013-12-19 | GM Global Technology Operations, LLC (n.d. Ges. d. Staates Delaware) | Method for determining pore size and pore distribution in metal casting, involves grouping measured pores size and spaces in cluster for generating measuring value for pores size or pores distribution in sample on cluster-to-cluster basis |
| CN105699341A (en) * | 2014-11-28 | 2016-06-22 | 中国科学院金属研究所 | A fluorescence metallographic measuring method for pores of a metal material |
| CN104766095A (en) * | 2015-04-16 | 2015-07-08 | 成都汇智远景科技有限公司 | Mobile terminal image identification method |
| WO2018166114A1 (en) * | 2017-03-13 | 2018-09-20 | 平安科技（深圳）有限公司 | Picture identification method and system, electronic device, and medium |
| CN108416748A (en) * | 2018-02-26 | 2018-08-17 | 阿博茨德（北京）科技有限公司 | The image pre-processing method and device of JPEG compression document |
| CN108647588A (en) * | 2018-04-24 | 2018-10-12 | 广州绿怡信息科技有限公司 | Goods categories recognition methods, device, computer equipment and storage medium |
| CN109409428A (en) * | 2018-10-25 | 2019-03-01 | 北京木业邦科技有限公司 | Training method, device and the electronic equipment of plank identification and plank identification model |
| CN109829483A (en) * | 2019-01-07 | 2019-05-31 | 鲁班嫡系机器人（深圳）有限公司 | Defect recognition model training method, device, computer equipment and storage medium |
| CN109615630A (en) * | 2019-01-18 | 2019-04-12 | 东北大学 | Semi-continuous casting alusil alloy Analysis on Microstructure method based on image processing techniques |
| CN110110661A (en) * | 2019-05-07 | 2019-08-09 | 西南石油大学 | A kind of rock image porosity type recognition methods based on unet segmentation |
| CN110348461A (en) * | 2019-07-05 | 2019-10-18 | 江苏海事职业技术学院 | A kind of Surface Flaw feature extracting method |
| CN110308151A (en) * | 2019-07-22 | 2019-10-08 | 重庆大学 | A kind of surface of workpiece defect identification method and device based on machine vision |
Non-Patent Citations (1)
| Title |
|---|
| 高志强等.深度学习从入门到实战.中国铁道出版社,2018,第66-67页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112907498A (en) | 2021-06-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3937128A2 (en) | Image defect detection method and apparatus, electronic device, storage medium and product | |
| CN110148130B (en) | Method and device for detecting part defects | |
| CN108682008B (en) | A kind of Leukocyte Image clarity evaluation method and device | |
| CN109767422A (en) | Pipe detection recognition methods, storage medium and robot based on deep learning | |
| CN112907498B (en) | Pore identification method, device, equipment and storage medium | |
| Sharifzadeh et al. | Detection of steel defect using the image processing algorithms | |
| CN114022403A (en) | Method and device for detecting defects of display panel | |
| CN110136116B (en) | Injection pump defect detection method, device, equipment and storage medium | |
| CN115684176B (en) | Online visual detection system for film surface defects | |
| CN106296689B (en) | Flaw detection method, system and device | |
| CN107490582A (en) | A kind of streamline Work Piece Verification System Based | |
| CN111524117A (en) | Tunnel surface defect detection method based on characteristic pyramid network | |
| CN106780464A (en) | A kind of fabric defect detection method based on improvement Threshold segmentation | |
| CN112784835A (en) | Method and device for identifying authenticity of circular seal, electronic equipment and storage medium | |
| CN111879972A (en) | Workpiece surface defect detection method and system based on SSD network model | |
| CN107993223A (en) | Scratch detection method, apparatus and electronic equipment | |
| CN112967224A (en) | Electronic circuit board detection system, method and medium based on artificial intelligence | |
| CN112465784A (en) | Method for detecting appearance abnormity of subway clamp | |
| CN116188826A (en) | Template matching method and device under complex illumination condition | |
| CN116128826A (en) | YOLOv 5-based lithium battery defect detection method, system, equipment and storage medium | |
| CN115456996A (en) | Discrete defect detection method for nuclear fuel pellet and related assembly | |
| CN104504702A (en) | Cement notch pavement crack recognition method based on square lattice searching method | |
| CN112967223A (en) | Artificial intelligence-based textile detection system, method and medium | |
| CN111476779B (en) | Sawn timber surface defect position positioning method and sawn timber surface defect position positioning system | |
| CN115526867B (en) | Method and device for extracting crack defects of X-ray image of carbon fiber composite gas cylinder |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |