CN113935415A - Quality detection model training method and device, electronic equipment and storage medium - Google Patents
Quality detection model training method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113935415A CN113935415A CN202111199659.0A CN202111199659A CN113935415A CN 113935415 A CN113935415 A CN 113935415A CN 202111199659 A CN202111199659 A CN 202111199659A CN 113935415 A CN113935415 A CN 113935415A
- Authority
- CN
- China
- Prior art keywords
- sample image
- sample
- detection model
- quality detection
- training
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 152
- 238000012549 training Methods 0.000 title claims abstract description 77
- 238000000034 method Methods 0.000 title claims abstract description 54
- 230000007547 defect Effects 0.000 claims abstract description 62
- 230000002950 deficient Effects 0.000 claims description 30
- 238000007689 inspection Methods 0.000 claims description 23
- 238000012360 testing method Methods 0.000 claims description 22
- 238000012545 processing Methods 0.000 claims description 18
- 238000012372 quality testing Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 4
- 238000005336 cracking Methods 0.000 claims 1
- 230000003287 optical effect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 229920000298 Cellophane Polymers 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000003825 pressing Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000002313 adhesive film Substances 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005034 decoration Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06T2207/10024—Color image
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses a quality detection model training method and device, electronic equipment and a storage medium. The method comprises the following steps: obtaining a sample image of the decorative plate, and generating a sample identifier of the sample image based on the type information of the sample image; the sample mark comprises a defect mark and a qualified mark; constructing a sample image set according to the sample images and the sample identifications corresponding to the sample images; and training to obtain a quality detection model meeting preset conditions based on the sample image set and the target detection algorithm. According to the technical scheme of the embodiment of the invention, the pressed artificial decorative plate can be detected according to the quality detection model, the accuracy and the detection efficiency of the detection result are improved, and the human resources are saved.
Description
Technical Field
The embodiment of the invention relates to the technical field of computer vision processing, in particular to a quality detection model training method and device, electronic equipment and a storage medium.
Background
At present, in the home decoration industry, artificial decorative plates become one of main raw materials of people, the pressing and pasting process is the most core process for generating abundant, various and attractive artificial decorative plates, and in order to ensure high yield of pressing and pasting, the quality of products needs to be detected.
In the prior art, the pressed artificial decorative plate is manually detected by professional technicians, so that the produced artificial decorative plate is qualified. However, the levels of the process personnel are uneven, so that the detection result is low in accuracy and high in error rate; and the efficiency of detecting the artificial decorative plate is low, and a large amount of human resources and time resources are consumed.
Therefore, the problem to be solved urgently is to provide the decorative plate quality detection method which is high in accuracy and time-saving.
Disclosure of Invention
The embodiment of the invention provides a quality detection model training method and device, electronic equipment and a storage medium, so that a pressed and pasted artificial decorative plate can be detected according to the quality detection model, the accuracy and the detection efficiency of a detection result are improved, and human resources are saved.
In a first aspect, an embodiment of the present invention provides a quality detection model training method, including:
acquiring a sample image of a decorative plate, and generating a sample identifier of the sample image based on the type information of the sample image; wherein the sample mark comprises a defect mark and a qualified mark;
constructing a sample image set according to the sample image and the sample identification corresponding to the sample image;
and training to obtain a quality detection model meeting preset conditions based on the sample image set and the target detection algorithm.
In a second aspect, an embodiment of the present invention further provides a quality detection model training apparatus, where the apparatus includes:
the system comprises an acquisition sample image module, a display module and a display module, wherein the acquisition sample image module is used for acquiring a sample image of a decorative plate and generating a sample identifier of the sample image based on the type information of the sample image; wherein the sample mark comprises a defect mark and a qualified mark;
a sample image set constructing module, configured to construct a sample image set according to the sample image and the sample identifier corresponding to the sample image;
and the training quality detection model module is used for training to obtain a quality detection model meeting preset conditions based on the sample image set and the target detection algorithm.
In a third aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement a quality detection model training method as provided by any of the embodiments of the invention.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the quality detection model training method provided in any embodiment of the present invention.
The quality detection model training method provided by the embodiment of the invention comprises the steps of obtaining a sample image of a decorative plate, and generating a sample identifier of the sample image based on the type information of the sample image; the sample mark comprises a defect mark and a qualified mark; constructing a sample image set according to the sample images and the sample identifications corresponding to the sample images; and training to obtain a quality detection model meeting preset conditions through a sample image set and a target detection algorithm. The detection of the pressed artificial decorative plate is realized according to the quality detection model, the accuracy and the detection efficiency of the detection result are improved, and the human resources are saved.
In addition, the quality detection model training device, the electronic equipment and the storage medium provided by the invention correspond to the method, and have the same beneficial effects.
Drawings
In order to illustrate the embodiments of the present invention more clearly, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings can be obtained by those skilled in the art without inventive effort.
FIG. 1 is a flowchart of a quality testing model training method according to an embodiment of the present invention;
FIG. 2 is a flow chart of another quality testing model training method according to an embodiment of the present invention;
FIG. 3 is a block diagram of a quality testing model training apparatus according to an embodiment of the present invention;
fig. 4 is a structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
It should be further noted that, for the convenience of description, only some but not all of the relevant aspects of the present invention are shown in the drawings. Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the operations (or steps) as a sequential process, many of the operations can be performed in parallel, concurrently or simultaneously. In addition, the order of the operations may be re-arranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like.
In order that those skilled in the art will better understand the disclosure, the invention will be described in further detail with reference to the accompanying drawings and specific embodiments.
Example one
Fig. 1 is a flowchart of a quality detection model training method according to an embodiment of the present invention. The method may be performed by a quality detection model training apparatus, which may be implemented by software and/or hardware, and may be configured in a terminal and/or a server to implement the quality detection model training method in the embodiments of the present invention.
As shown in fig. 1, the method of the embodiment may specifically include:
s101, obtaining a sample image of the decorative plate, and generating a sample identifier of the sample image based on the type information of the sample image; wherein, the sample identification comprises a defect identification and a qualified identification.
In the embodiment of the invention, the quality detection model can be trained through the sample image of the artificial decorative plate. Specifically, the sample images of the decorative sheet may include a qualified sample image, a defective sample image, and an extended sample image corresponding to the defective sample image.
Optionally, obtaining a sample image of the decorative sheet includes: acquiring a defect sample image of a defective decorative plate with defects; performing image processing on the defect sample image to obtain an extended sample image generated after the image processing; and acquiring a qualified sample image of the qualified decorative plate corresponding to the defective decorative plate.
Specifically, when determining the defective decorative boards for training the quality inspection model, a preset number of defective decorative boards can be selected according to different sizes, different board types, different adhesive film paper types and different defect positions of the decorative boards, the comprehensiveness of the selected defective decorative boards is ensured, and images of the defective decorative boards are collected to serve as defect sample images.
It should be noted that the number of the selected defective decorative boards with different sizes, different board types, different cellophane types, and different defective positions may be different, and a person skilled in the art may set the number of the selected defective decorative boards with different sizes, different board types, different cellophane types, and different defective positions according to the actual application situation, which does not limit the embodiment of the present invention.
Further, the defect types of the artificial decorative panel include at least one of a fray, a wet flower, a dry flower, a scratch, and a crack. Acquiring a defect sample image of a defective decorative sheet having a defect includes acquiring a defect sample image of a defective decorative sheet having at least one defect of a burst edge, a wet pattern, a dry pattern, a scratch, and a crack.
Furthermore, in order to improve the accuracy of the training quality detection model, the number of samples can be increased by processing the images of the defective sample. Optionally, the image processing is performed on the defect sample image, and includes: and at least one of cutting, turning, mirroring, rotating, adjusting brightness, adjusting chroma, adding noise, sharpening and converting the defect sample image into a gray scale image is carried out on the defect sample image.
Specifically, the random cropping processing may be performed on the defect sample image, the cropping mode includes cropping the corners, the center or the irregular shape of the defect sample image, and at least one of the area, the size and the shape of the cropping may be preset.
Specifically, the image processing mode further comprises turning, mirroring or rotating the defect sample image; the defect sample image may be horizontally or vertically flipped, and the defect sample image may be rotated by a preset angle to form a new defect sample image. Further, the image quality of the defective sample image can also be processed. For example, the brightness of the defect sample image can be adjusted by a preset proportion or adjusted by a preset proportion; adjusting the contrast of the defect sample image, and also adjusting the chromaticity of the defect sample image to change R, G, B color component proportion; or carrying out Gaussian blurring, sharpening, noise addition or conversion on the defect sample image into a gray level image.
Correspondingly, qualified sample images of qualified decorative boards of different sizes, different board types and different cellophane types can be obtained. Optionally, obtain the qualified sample image of the qualified decorative board that corresponds with the defect decorative board, include: acquiring qualified sample images of qualified decorative plates corresponding to the defective decorative plates in a first preset number; the sum of the number of the defect sample images and the number of the extension sample images is a second preset number, and the ratio of the first preset data to the second preset number is a preset fixed value.
Illustratively, the preset fixed value includes 1, i.e., the number of acquired qualified sample images is the same as the sum of the numbers of the defective sample images and the extended sample images. Further, the number of the defective sample images is the same as the number of the extended sample images. Those skilled in the art can also set the number of defective sample images, the number of extended sample images, and the number of qualified sample images according to the actual application, and the embodiments of the present invention are not limited.
In particular implementations, the defect identification or the qualified identification of the sample image may be generated based on type information that the sample image is a defective sample and a qualified sample. Illustratively, the corresponding identifier of the defect sample image and the extension sample image is a defect identifier; and the identification corresponding to the qualified sample image is a qualified identification. The mark may be made of at least one of a number, a letter, a character, and a letter. For example, the pass flag is set to 1 and the defect flag is set to 0.
S102, constructing a sample image set according to the sample images and the sample identifications corresponding to the sample images.
Illustratively, the sample image set is specifically a VOC data set, and the VOC data set can be divided into image files and identification files, wherein the image files are used for storing the sample images, and the identification files are used for storing sample identifications corresponding to the sample images; the sample identifications are stored in a text format. Further, the absolute position of the sample image in the storage space is stored in the identification file corresponding to each identification. Based on the corresponding relationship between the sample identifications and the absolute positions, the sample images corresponding to the sample identifications can be determined.
S103, training to obtain a quality detection model meeting preset conditions based on the sample image set and the target detection algorithm.
Specifically, the sample images in the sample image set may be used as an input item of the target detection algorithm, and the quality detection model may be trained based on the sample identifiers in the sample image set. For example, the quality detection model may be a YOLOV5 network structure.
Further, the trained quality detection model needs to meet preset conditions to ensure the accuracy and effectiveness of the quality detection model. Illustratively, the preset condition includes that the detection accuracy of the quality detection model obtained through the test can reach a preset threshold; or, the loss function of the quality inspection model tends to converge. A person skilled in the art can set a preset condition that the quality detection model satisfies according to an actual application situation, and the embodiment of the present invention is not limited.
The quality detection model training method provided by the embodiment of the invention comprises the steps of obtaining a sample image of a decorative plate, and generating a sample identifier of the sample image based on the type information of the sample image; the sample mark comprises a defect mark and a qualified mark; constructing a sample image set according to the sample images and the sample identifications corresponding to the sample images; and training to obtain a quality detection model meeting preset conditions through a sample image set and a target detection algorithm. The detection of the pressed artificial decorative plate is realized according to the quality detection model, the accuracy and the detection efficiency of the detection result are improved, and the human resources are saved.
Example two
Fig. 2 is a flowchart of another quality inspection model training method according to an embodiment of the present invention. The present embodiment is optimized based on the above technical solutions. Optionally, the sample image set includes a training sample image set and a testing sample image set; based on the sample image set and the target detection algorithm, training to obtain a quality detection model meeting preset conditions, wherein the quality detection model comprises the following steps: training to obtain a quality detection model to be detected based on a training sample image set and a target detection algorithm; inputting the inspection sample image set into a quality detection model to be inspected to obtain a model output result corresponding to the inspection sample image set; comparing the model output result with an actual quality result corresponding to the test sample image set, and counting the ratio of the number of the test sample images with the consistent model output result and the actual quality result to the total number of the test sample images; and when the ratio is larger than a preset threshold value, determining the quality detection model to be detected as the quality detection model meeting the preset condition. Optionally, after the quality detection model meeting the preset condition is obtained through training, the method further includes: collecting an image to be detected of a decorative plate to be detected; and inputting the image to be detected into the quality detection model, and determining whether the decorative plate to be detected is qualified or not based on the output result of the quality detection model. The same or corresponding terms as those in the above embodiments are not explained in detail herein.
As shown in fig. 2, the method of the embodiment may specifically include:
s201, obtaining a sample image of the decorative plate, and generating a sample identifier of the sample image based on the type information of the sample image; wherein, the sample identification comprises a defect identification and a qualified identification.
S202, constructing a sample image set according to the sample image and the sample identification corresponding to the sample image; the sample image set includes a training sample image set and a testing sample image set.
S203, training to obtain a quality detection model to be detected based on a training sample image set and a target detection algorithm; and inputting the inspection sample image set into a quality detection model to be inspected to obtain a model output result corresponding to the inspection sample image set.
In a specific implementation, the training sample image set is used for training the quality detection model, and the inspection sample image set is used for inspecting whether the quality detection model meets the preset condition. Specifically, the quality detection model to be detected can be obtained by training based on a training sample image set and a target detection algorithm. Illustratively, the target detection algorithm includes a YOLO algorithm.
For example, the quality detection model may be trained based on a training sample image set and a prior art YOLOV5 pre-training model. Specifically, one item of the number of sample types in the YOLOV5 pre-training model can be set as "pass" and "fail"; the product can also be set into six types of qualified products, broken edges, wet flowers, dry flowers, scratches and cracks. Those skilled in the art can also set the size of the target detection box of the YOLOV5 pre-training model according to the actual application, and the embodiment of the present invention is not limited thereto.
Furthermore, the inspection sample images can be input into the quality detection model to be inspected, and the model output result output by the quality detection model to be inspected is the detection result of each inspection sample image.
And S204, comparing the model output result with the actual quality result corresponding to the test sample image set, and counting the ratio of the number of the test sample images with the consistent model output result and actual quality result to the total number of the test sample images.
Specifically, the inspection sample image set includes an inspection sample identifier of the inspection image sample, and the inspection sample identifier is used to reflect an actual quality result of the inspection sample image, that is, whether the inspection sample image is a qualified image. Illustratively, the actual quality result of the test sample image may be determined by the test sample identification.
Further, the model output result of each inspection sample image in the inspection sample image set is compared with the corresponding actual quality result, when the model output result is consistent with the actual quality result, the model output result is correct, and when the model output result is inconsistent with the actual quality result, the model output result is wrong. The ratio of the number of the test sample images with the consistent model output result and the actual quality result to the total number of the test sample images can be counted, and the detection accuracy of the quality detection model to be detected is determined through the ratio.
S205, when the ratio is larger than a preset threshold value, determining the quality detection model to be detected as the quality detection model meeting the preset condition.
It should be noted that, a person skilled in the art may preset a minimum value of the detection accuracy rate that the quality detection model needs to satisfy, and set the minimum value as a preset threshold; and judging whether the ratio is greater than a preset threshold value, and determining that the quality detection model to be inspected is a qualified model when the ratio is greater than the preset threshold value, so that the preset condition is met, and the method can be used for the actual detection process of the decorative plate. And when the ratio is smaller than or equal to the preset threshold value, the quality detection model to be detected is unqualified, and retraining is required. For example, the preset threshold may be 95%.
S206, collecting an image to be detected of the decorative plate to be detected; and inputting the image to be detected into the quality detection model, and determining whether the decorative plate to be detected is qualified or not based on the output result of the quality detection model.
Furthermore, the decorative board to be detected is detected through a quality detection model obtained through training so as to screen out unqualified decorative boards. Specifically, the images to be detected of the decorative plate to be detected are collected, and the collected images to be detected can be sequentially input into the quality detection model; and the images to be detected can be input into the quality detection model in batches. When the images to be detected are detected in batch, image numbers can be set for the images to be detected in advance, and each image to be detected corresponds to the output result of the quality detection model based on the image numbers.
Illustratively, the output of the quality detection model may be represented by at least one of a number, a symbol, and a letter. For example, when the output result is 0, it indicates that the image to be detected is an unqualified image, that is, the decorative board to be detected corresponding to the image to be detected is unqualified; and when the output result is 1, the image to be detected is represented as a qualified image, namely the decorative plate to be detected corresponding to the image to be detected is qualified.
Further, when unqualified decorative boards to be detected are detected, warning information can be generated and fed back to the management user terminal, and the warning information comprises the serial numbers of the decorative boards to be detected and the images of the decorative boards to be detected, so that managers can conveniently check the decorative boards.
According to the quality detection model training method provided by the embodiment of the invention, the quality detection model is set to meet the preset detection accuracy rate, and the detection effectiveness of the quality detection model is ensured; in the actual detection, warning information is generated to prompt a manager when an unqualified decorative plate is found, so that the user experience is improved, and the manager can conveniently review the unqualified decorative plate.
EXAMPLE III
Fig. 3 is a structural diagram of a quality testing model training apparatus according to an embodiment of the present invention, which is used for executing the quality testing model training method according to any of the above embodiments. The device and the quality detection model training method of each embodiment belong to the same inventive concept, and details which are not described in detail in the embodiment of the quality detection model training device can refer to the embodiment of the quality detection model training method. The device may specifically comprise:
the sample image obtaining module 10 is used for obtaining a sample image of the decorative plate and generating a sample identifier of the sample image based on the type information of the sample image; the sample mark comprises a defect mark and a qualified mark;
a sample image set constructing module 11, configured to construct a sample image set according to the sample image and the sample identifier corresponding to the sample image;
and the training quality detection model module 12 is used for training to obtain a quality detection model meeting preset conditions based on the sample image set and the target detection algorithm.
On the basis of any optional technical solution in the embodiment of the present invention, optionally, the module 10 for obtaining a sample image includes:
the sample image acquiring unit is used for acquiring a defect sample image of a defective decorative plate with defects; performing image processing on the defect sample image to obtain an extended sample image generated after the image processing; and acquiring a qualified sample image of the qualified decorative plate corresponding to the defective decorative plate.
On the basis of any optional technical solution in the embodiment of the present invention, optionally, the unit for obtaining a sample image includes:
and the image processing unit is used for performing at least one of cutting, turning, mirroring, rotating, brightness adjusting, chroma adjusting, noise adding, sharpening and conversion to a gray-scale image on the defect sample image.
On the basis of any optional technical solution in the embodiment of the present invention, optionally, the unit for obtaining a sample image includes:
the qualified sample image acquiring unit is used for acquiring qualified sample images of qualified decorative plates corresponding to the defective decorative plates in a first preset number; the sum of the number of the defect sample images and the number of the extension sample images is a second preset number, and the ratio of the first preset data to the second preset number is a preset fixed value.
On the basis of any optional technical solution in the embodiment of the present invention, optionally, the unit for obtaining a sample image includes:
and the defect sample image acquiring unit is used for acquiring a defect sample image of a defect decorative plate with at least one defect of edge explosion, wet flower, dry flower, scratch and crack.
Optionally, the sample image set includes a training sample image set and a testing sample image set; on the basis of any optional technical solution in the embodiment of the present invention, optionally, the training quality detection model module 12 includes:
the training model unit is used for training to obtain a quality detection model to be detected based on a training sample image set and a target detection algorithm; inputting the inspection sample image set into a quality detection model to be inspected to obtain a model output result corresponding to the inspection sample image set; comparing the model output result with an actual quality result corresponding to the test sample image set, and counting the ratio of the number of the test sample images with the consistent model output result and the actual quality result to the total number of the test sample images; and when the ratio is larger than a preset threshold value, determining the quality detection model to be detected as the quality detection model meeting the preset condition.
On the basis of any optional technical solution in the embodiment of the present invention, optionally, the apparatus further includes:
the test image module is used for acquiring an image to be tested of the decorative plate to be tested; and inputting the image to be detected into the quality detection model, and determining whether the decorative plate to be detected is qualified or not based on the output result of the quality detection model.
The quality detection model training device provided by the embodiment of the invention can realize the following method: obtaining a sample image of the decorative plate, and generating a sample identifier of the sample image based on the type information of the sample image; the sample mark comprises a defect mark and a qualified mark; constructing a sample image set according to the sample images and the sample identifications corresponding to the sample images; and training to obtain a quality detection model meeting preset conditions through a sample image set and a target detection algorithm. The detection of the pressed artificial decorative plate is realized according to the quality detection model, the accuracy and the detection efficiency of the detection result are improved, and the human resources are saved.
It should be noted that, in the embodiment of the quality inspection model training apparatus, the included units and modules are only divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
Example four
Fig. 4 is a structural diagram of an electronic device according to an embodiment of the present invention. FIG. 4 illustrates a block diagram of an exemplary electronic device 20 suitable for use in implementing embodiments of the present invention. The illustrated electronic device 20 is merely an example and should not be used to limit the functionality or scope of embodiments of the present invention.
As shown in fig. 4, the electronic device 20 is embodied in the form of a general purpose computing device. The components of the electronic device 20 may include, but are not limited to: one or more processors or processing units 201, a system memory 202, and a bus 203 that couples the various system components (including the system memory 202 and the processing unit 201).
The system memory 202 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)204 and/or cache memory 205. The electronic device 20 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, the storage system 206 may be used to read from and write to non-removable, nonvolatile magnetic media. A magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 203 by one or more data media interfaces. Memory 202 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.
A program/utility 208 having a set (at least one) of program modules 207 may be stored, for example, in memory 202, such program modules 207 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 207 generally perform the functions and/or methodologies of embodiments of the present invention as described herein.
The electronic device 20 may also communicate with one or more external devices 209 (e.g., keyboard, pointing device, display 210, etc.), with one or more devices that enable a user to interact with the electronic device 20, and/or with any devices (e.g., network card, modem, etc.) that enable the electronic device 20 to communicate with one or more other computing devices. Such communication may occur via input/output (I/O) interfaces 211. Also, the electronic device 20 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet) via the network adapter 212. As shown, the network adapter 212 communicates with other modules of the electronic device 20 over the bus 203. It should be understood that other hardware and/or software modules may be used in conjunction with electronic device 20, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
The processing unit 201 executes various functional applications and data processing by running a program stored in the system memory 202.
The electronic equipment provided by the invention can realize the following method: obtaining a sample image of the decorative plate, and generating a sample identifier of the sample image based on the type information of the sample image; the sample mark comprises a defect mark and a qualified mark; constructing a sample image set according to the sample images and the sample identifications corresponding to the sample images; and training to obtain a quality detection model meeting preset conditions through a sample image set and a target detection algorithm. The detection of the pressed artificial decorative plate is realized according to the quality detection model, the accuracy and the detection efficiency of the detection result are improved, and the human resources are saved.
EXAMPLE five
An embodiment of the present invention provides a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform a method for quality detection model training, the method comprising:
obtaining a sample image of the decorative plate, and generating a sample identifier of the sample image based on the type information of the sample image; the sample mark comprises a defect mark and a qualified mark; constructing a sample image set according to the sample images and the sample identifications corresponding to the sample images; and training to obtain a quality detection model meeting preset conditions through a sample image set and a target detection algorithm. The detection of the pressed artificial decorative plate is realized according to the quality detection model, the accuracy and the detection efficiency of the detection result are improved, and the human resources are saved.
Of course, the storage medium containing the computer-executable instructions provided by the embodiments of the present invention is not limited to the method operations described above, and may also perform related operations in the quality testing model training method provided by any embodiments of the present invention.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for embodiments of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. 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, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A quality detection model training method is characterized by comprising the following steps:
acquiring a sample image of a decorative plate, and generating a sample identifier of the sample image based on the type information of the sample image; wherein the sample mark comprises a defect mark and a qualified mark;
constructing a sample image set according to the sample image and the sample identification corresponding to the sample image;
and training to obtain a quality detection model meeting preset conditions based on the sample image set and the target detection algorithm.
2. The method of claim 1, wherein the obtaining a sample image of a trim panel comprises:
acquiring a defect sample image of a defective decorative plate with defects;
performing image processing on the defect sample image to obtain an extended sample image generated after the image processing;
and acquiring a qualified sample image of the qualified decorative plate corresponding to the defective decorative plate.
3. The method of claim 2, wherein the image processing the defect sample image comprises:
and at least one of cutting, turning, mirroring, rotating, adjusting brightness, adjusting chroma, adding noise, sharpening and converting the defect sample image into a gray scale image is carried out on the defect sample image.
4. The method of claim 2, wherein said obtaining a qualified sample image of a qualified trim panel corresponding to the defective trim panel comprises:
acquiring qualified sample images of qualified decorative plates corresponding to the defective decorative plates in a first preset number;
the sum of the number of the defect sample images and the number of the extension sample images is a second preset number, and the ratio of the first preset data to the second preset number is a preset fixed value.
5. The method of claim 2, wherein said obtaining a defect sample image of a defective trim panel having a defect comprises:
and acquiring a defect sample image of the defective decorative plate with at least one defect of edge cracking, wet flower, dry flower, scratch and crack.
6. The method of claim 1, wherein the sample image set comprises a training sample image set and a testing sample image set;
the training to obtain the quality detection model meeting the preset conditions based on the sample image set and the target detection algorithm comprises the following steps:
training to obtain a quality detection model to be detected based on the training sample image set and a target detection algorithm;
inputting the inspection sample image set into the quality detection model to be inspected to obtain a model output result corresponding to the inspection sample image set;
comparing the model output result with an actual quality result corresponding to the test sample image set, and counting the ratio of the number of the test sample images with the same model output result and actual quality result to the total number of the test sample images;
and when the ratio is larger than a preset threshold value, determining the quality detection model to be detected as the quality detection model meeting the preset condition.
7. The method of claim 1, wherein after the training obtains the quality detection model satisfying a preset condition, the method further comprises:
collecting an image to be detected of a decorative plate to be detected;
and inputting the image to be detected into the quality detection model, and determining whether the decorative plate to be detected is qualified or not based on an output result of the quality detection model.
8. A quality testing model training device, comprising:
the system comprises an acquisition sample image module, a display module and a display module, wherein the acquisition sample image module is used for acquiring a sample image of a decorative plate and generating a sample identifier of the sample image based on the type information of the sample image; wherein the sample mark comprises a defect mark and a qualified mark;
a sample image set constructing module, configured to construct a sample image set according to the sample image and the sample identifier corresponding to the sample image;
and the training quality detection model module is used for training to obtain a quality detection model meeting preset conditions based on the sample image set and the target detection algorithm.
9. An electronic device, comprising:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the quality detection model training method of any of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the quality detection model training method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111199659.0A CN113935415A (en) | 2021-10-14 | 2021-10-14 | Quality detection model training method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111199659.0A CN113935415A (en) | 2021-10-14 | 2021-10-14 | Quality detection model training method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113935415A true CN113935415A (en) | 2022-01-14 |
Family
ID=79279312
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111199659.0A Pending CN113935415A (en) | 2021-10-14 | 2021-10-14 | Quality detection model training method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113935415A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106323985A (en) * | 2016-08-29 | 2017-01-11 | 常熟品智自动化科技有限公司 | Solid wood panel quality detection method with combination of computer vision and self-learning behaviors |
| CN107392896A (en) * | 2017-07-14 | 2017-11-24 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of Wood Defects Testing method and system based on deep learning |
| CN109724984A (en) * | 2018-12-07 | 2019-05-07 | 上海交通大学 | A kind of defects detection identification device and method based on deep learning algorithm |
| CN210775265U (en) * | 2019-10-12 | 2020-06-16 | 南宁市威锐康商贸有限公司 | Artificial board surface defect detection system |
-
2021
- 2021-10-14 CN CN202111199659.0A patent/CN113935415A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106323985A (en) * | 2016-08-29 | 2017-01-11 | 常熟品智自动化科技有限公司 | Solid wood panel quality detection method with combination of computer vision and self-learning behaviors |
| CN107392896A (en) * | 2017-07-14 | 2017-11-24 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of Wood Defects Testing method and system based on deep learning |
| CN109724984A (en) * | 2018-12-07 | 2019-05-07 | 上海交通大学 | A kind of defects detection identification device and method based on deep learning algorithm |
| CN210775265U (en) * | 2019-10-12 | 2020-06-16 | 南宁市威锐康商贸有限公司 | Artificial board surface defect detection system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108229485B (en) | Method and apparatus for testing user interface | |
| CN112070135A (en) | Power equipment image detection method and device, power equipment and storage medium | |
| CN110490181B (en) | Form filling and auditing method, device and equipment based on OCR (optical character recognition) technology and computer storage medium | |
| CN110647523B (en) | Data quality analysis method and device, storage medium and electronic equipment | |
| CN107315140B (en) | AOI detection method, device, equipment and storage medium | |
| CN111428373A (en) | Product assembly quality detection method, device, equipment and storage medium | |
| CN111428374A (en) | Part defect detection method, device, equipment and storage medium | |
| CN107193747B (en) | Code testing method and device and computer equipment | |
| CN117392042A (en) | Defect detection method, defect detection apparatus, and storage medium | |
| CN113936232A (en) | Screen fragmentation identification method, device, equipment and storage medium | |
| TW202230281A (en) | Image reinspection method, computer device, and storage medium | |
| CN111723799B (en) | Coordinate positioning method, device, equipment and storage medium | |
| CN113935415A (en) | Quality detection model training method and device, electronic equipment and storage medium | |
| CN116824122A (en) | LED chip positioning method and LED chip positioning device based on deep learning | |
| CN112966671A (en) | Contract detection method and device, electronic equipment and storage medium | |
| CN111696154B (en) | Coordinate positioning method, device, equipment and storage medium | |
| CN114140612A (en) | Method, device, equipment and storage medium for detecting hidden danger of power equipment | |
| CN114418951A (en) | Pad detection method and device, computer equipment and storage medium | |
| CN110827261B (en) | Image quality detection method and device, storage medium and electronic equipment | |
| CN110457705B (en) | Method, device, equipment and storage medium for processing point of interest data | |
| CN113962933A (en) | PCB defect image detection method based on improved YOLOv3 | |
| CN108453050A (en) | Electric energy meter method for sorting, device and system | |
| CN112184637A (en) | 3D prints forming part defect and assesses device on line | |
| CN104361516A (en) | Internet alignment and transaction method and internet alignment and transaction platform for scientific research and development and test service | |
| TWI778735B (en) | Image processing method, computer device, and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |