CN114820459B - Computer-aided aluminum veneer polishing quality assessment method and system - Google Patents
Computer-aided aluminum veneer polishing quality assessment method and system Download PDFInfo
- Publication number
- CN114820459B CN114820459B CN202210336324.7A CN202210336324A CN114820459B CN 114820459 B CN114820459 B CN 114820459B CN 202210336324 A CN202210336324 A CN 202210336324A CN 114820459 B CN114820459 B CN 114820459B
- Authority
- CN
- China
- Prior art keywords
- characteristic
- region
- feature
- index
- sheet metal
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/54—Extraction of image or video features relating to texture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
- G06V10/763—Non-hierarchical techniques, e.g. based on statistics of modelling distributions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30136—Metal
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Probability & Statistics with Applications (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
本发明涉及基于计算机辅助的铝单板打磨质量评估方法及系统，属于电子数据数字处理技术领域。该方法利用了计算机进行辅助设计和处理，并且该方法能应用于新型软件和新型技术服务。该方法根据各纹理结构特征指标，得到各特征区域对应的第一特征指标；根据R通道强度差异指标、G通道强度差异指标以及B通道强度差异指标，得到各特征区域对应的第二特征指标；根据第一特征指标和第二特征指标，对生产铝单板时打磨工序对应的打磨质量进行评估。本发明相对于基于人工目检对铝单板的打磨质量进行评估的方式，能够更加可靠的对生产铝单板时打磨工序对应的打磨质量进行评估，并且对打磨工序对应的打磨质量进行评估的工作效率也较高。
The present invention relates to a computer-aided aluminum veneer polishing quality assessment method and system, and belongs to the technical field of electronic data digital processing. The method utilizes a computer for auxiliary design and processing, and the method can be applied to new software and new technical services. The method obtains a first characteristic index corresponding to each characteristic area according to each texture structure characteristic index; obtains a second characteristic index corresponding to each characteristic area according to an R channel intensity difference index, a G channel intensity difference index, and a B channel intensity difference index; and evaluates the polishing quality corresponding to the polishing process when producing aluminum veneers according to the first characteristic index and the second characteristic index. Compared with the method of evaluating the polishing quality of aluminum veneers based on manual visual inspection, the present invention can more reliably evaluate the polishing quality corresponding to the polishing process when producing aluminum veneers, and the work efficiency of evaluating the polishing quality corresponding to the polishing process is also high.
Description
Technical Field
The invention relates to the technical field of electronic data digital processing, in particular to an aluminum veneer polishing quality assessment method and system based on computer assistance.
Background
The aluminum veneer is a decoration material and also a novel material, and is applied to indoor aluminum veneer ceilings, building curtain walls, column beams, balconies, partition board cladding, indoor decoration and the like of various buildings such as markets, hotels, airports, railway stations, subways, office buildings, business buildings and the like, and an external wall aluminum veneer can be used for heat preservation of an external wall of a building. The sheet metal of preparation aluminium veneer generally only will be through shearing board, angle of attack, hem, welding, kind nail add muscle, process such as grinding, polishing, spraying and toasting can form aluminium veneer, but can probably make defects such as mar, polishing trace or crackle appear on the sheet metal surface at the in-process that the sheet metal was polished because of operation or machine reason, this not only can lead to the effect reduction to the aluminium veneer outward appearance of production, can lead to the effect of aluminium veneer when serious, influence life, consequently the detection evaluation to the sheet metal quality of polishing of aluminium veneer is a very important link.
The polishing quality of the aluminum veneer is generally evaluated based on the existing manual visual inspection mode, the subjectivity of the mode is high, the labor capacity is high, the working efficiency is low, and the phenomenon of missing detection or false detection can also occur in the detection and evaluation process, so that the reliability of the polishing quality evaluation of the aluminum veneer is low.
Disclosure of Invention
The invention provides an aluminum veneer polishing quality evaluation method and system based on computer assistance, which are used for solving the problem that the polishing quality of an aluminum veneer cannot be evaluated reliably in the prior art, and the adopted technical scheme is as follows:
In a first aspect, an embodiment of the present invention provides a method and a system for evaluating polishing quality of an aluminum veneer based on computer assistance, including the following steps:
Obtaining a metal plate target image after a polishing procedure in the production of an aluminum veneer, wherein the metal plate target image is an RGB image;
according to the pixel values of each pixel point in the sheet metal target image, obtaining each characteristic area corresponding to the sheet metal target image;
Obtaining each texture feature index corresponding to each feature region according to the neighborhood pixel points of each pixel point in each feature region in each feature direction;
Obtaining R channel intensity difference indexes, G channel intensity difference indexes and B channel intensity difference indexes corresponding to the characteristic areas according to the R, G, B channel values corresponding to the pixel points in the characteristic areas;
Obtaining a second characteristic index corresponding to each characteristic region according to the R channel intensity difference index, the G channel intensity difference index and the B channel intensity difference index;
and evaluating polishing quality corresponding to the polishing procedure when the aluminum veneer is produced according to the first characteristic index and the second characteristic index.
The invention also provides an aluminum veneer polishing quality evaluation system based on computer assistance, which comprises a memory and a processor, wherein the processor executes a computer program stored in the memory so as to realize the aluminum veneer polishing quality evaluation method based on computer assistance.
The method has the advantages that neighborhood pixel points of each pixel point in each characteristic area in each characteristic direction are used as the basis for obtaining each texture characteristic index corresponding to each characteristic area, each texture characteristic index is used as the basis for obtaining a first characteristic index corresponding to each characteristic area, the values of R, G, B channels corresponding to each pixel point in each characteristic area are used as the basis for obtaining R channel intensity difference indexes, G channel intensity difference indexes and B channel intensity difference indexes corresponding to each characteristic area, R channel intensity difference indexes, G channel intensity difference indexes and B channel intensity difference indexes are used as the basis for obtaining a second characteristic index corresponding to each characteristic area, and the first characteristic index and the second characteristic index are used as the basis for evaluating polishing quality corresponding to polishing procedures when an aluminum veneer is produced. The method utilizes a computer to carry out aided design and processing, and can be applied to novel software and novel technical service. Compared with a mode of evaluating the polishing quality of the aluminum veneer based on manual visual inspection, the method can evaluate the polishing quality corresponding to the polishing procedure in the aluminum veneer production more reliably, and the working efficiency of evaluating the polishing quality corresponding to the polishing procedure is higher.
Preferably, the method for obtaining each feature area corresponding to the sheet metal target image according to the pixel value of each pixel point in the sheet metal target image comprises the following steps:
carrying out graying treatment on the sheet metal target image to obtain a sheet metal gray image corresponding to the sheet metal target image;
clustering each pixel point on the sheet metal gray level image by using a DBSCAN clustering algorithm;
Acquiring the category with the largest number of pixel points, and marking the areas corresponding to the categories except the category with the largest number of pixel points as each characteristic area corresponding to the sheet metal gray level image;
and obtaining each characteristic region corresponding to the sheet metal target image according to each characteristic region corresponding to the sheet metal gray level image.
Preferably, the method for obtaining the feature index of each texture structure corresponding to each feature region according to the neighborhood pixel point of each pixel point in each feature region in each feature direction includes:
acquiring each characteristic direction corresponding to a sheet metal target image and angles corresponding to each characteristic direction;
Acquiring neighborhood pixel points of each pixel point in each characteristic region in each characteristic direction;
Calculating the average value of the gray values of the neighborhood pixel points of each pixel point in each characteristic region in each characteristic direction to obtain the gray average value of each pixel point in each characteristic region in each characteristic direction;
According to the gray values corresponding to the pixel points in the characteristic areas and the gray average value of the pixel points in the characteristic areas in the characteristic directions, constructing and obtaining characteristic descriptors corresponding to the pixel points in the characteristic areas in the characteristic directions;
Acquiring each feature descriptor corresponding to each feature region in each feature direction and the category number of the feature descriptors corresponding to each feature region in each feature direction;
Obtaining the probability of each feature descriptor of each feature region in each feature direction in each feature descriptor of each type in the corresponding feature region in the corresponding feature direction according to each feature descriptor of each feature region in each feature direction and the number of types of feature descriptors of each feature region in each feature direction;
And obtaining texture structure characteristic indexes corresponding to the characteristic areas according to the probability.
Preferably, the method for obtaining the first characteristic index corresponding to each characteristic region according to the characteristic index of each texture structure comprises the following steps:
Acquiring the center point positions corresponding to the characteristic areas;
making straight lines with the same angles as the corresponding angles of the characteristic directions through the center points corresponding to the characteristic areas, and marking the straight lines as first straight lines corresponding to the characteristic areas in the characteristic directions;
Acquiring each pixel point in a corresponding characteristic region of each characteristic region on a first straight line corresponding to each characteristic direction, and marking each pixel point in the corresponding characteristic region of each characteristic region on the first straight line corresponding to each characteristic direction as each first center point of each characteristic region corresponding to each characteristic direction;
making a straight line perpendicular to a first straight line corresponding to the corresponding characteristic region in each characteristic direction by passing through each first center point corresponding to each characteristic region in each characteristic direction, so as to obtain a perpendicular corresponding to each first center point corresponding to each characteristic region in each characteristic direction;
according to the pixel points on the vertical line, constructing and obtaining pixel point sequences corresponding to first center points corresponding to the characteristic areas in the characteristic directions;
According to the gray value in the pixel point sequence, constructing and obtaining a Gaussian mixture model corresponding to each first center point of each characteristic region in each characteristic direction;
calculating the K-L divergence between the Gaussian mixture models corresponding to any two first center points of each characteristic region in each characteristic direction to obtain each first divergence of each characteristic region in each characteristic direction;
Summing the first divergences corresponding to the characteristic regions in the characteristic directions, and then obtaining an average value to obtain first target divergences corresponding to the characteristic regions in the characteristic directions;
According to the first target divergence, calculating to obtain the reliability degree of each texture structure characteristic index corresponding to each characteristic region in each characteristic direction;
obtaining each target texture feature index corresponding to each feature region according to the reliability degree of each texture feature index and each texture feature index;
And obtaining a first characteristic index corresponding to each characteristic region according to the characteristic index of each target texture structure.
Preferably, the reliability degree of each texture feature index corresponding to each feature region in each feature direction is calculated according to the following formula:
Wherein, C i,m is the reliability of the texture feature index corresponding to the ith feature region in the mth feature direction, C1 i,m is the first target divergence corresponding to the ith feature region in the mth feature direction, w is the setting parameter, and w1 is the setting parameter.
Preferably, the method for obtaining the R channel intensity difference index, the G channel intensity difference index and the B channel intensity difference index corresponding to each feature region according to the R, G, B channel values corresponding to each pixel point in each feature region includes:
acquiring the values of R, G, B channels corresponding to each pixel point in each characteristic area and the central pixel point corresponding to each characteristic area;
obtaining R channel intensity, G channel intensity and B channel intensity corresponding to each characteristic region according to the average value of pixel values of each pixel point in each characteristic region corresponding to the R channel, the average value of pixel values of each pixel point in each characteristic region corresponding to the G channel and the average value of pixel values of each pixel point in each characteristic region corresponding to the B channel;
and obtaining R channel intensity difference indexes, G channel intensity difference indexes and B channel intensity difference indexes corresponding to the feature areas according to the differences among the R channel intensities, the G channel intensities and the B channel intensities corresponding to the two feature areas and the center pixel point in the two feature areas.
Preferably, the R channel intensity difference index corresponding to each feature region is calculated according to the following formula:
Wherein S i R is an R channel intensity difference index corresponding to an ith feature region in the sheet metal target image, I is the number of feature regions in the sheet metal target image, L i,j is the euclidean distance between a center pixel point corresponding to the ith feature region in the sheet metal target image and a center pixel point corresponding to the corresponding jth feature region, T is a set parameter, σ is a set parameter, H i R is an R channel intensity corresponding to the ith feature region in the sheet metal target image, and H j R is an R channel intensity corresponding to the jth feature region in the sheet metal target image.
Preferably, the method for obtaining the second characteristic index corresponding to each characteristic region according to the R channel intensity difference index, the G channel intensity difference index and the B channel intensity difference index includes:
Calculating the sum of the R channel intensity difference index, the G channel intensity difference index and the B channel intensity difference index corresponding to each characteristic region to obtain a comprehensive difference index corresponding to each characteristic region;
and obtaining a second characteristic index corresponding to each characteristic region according to the comprehensive difference index, the R channel intensity difference index, the G channel intensity difference index and the B channel intensity difference index corresponding to each characteristic region.
Preferably, the method for evaluating polishing quality corresponding to the polishing procedure when producing the aluminum veneer according to the first characteristic index and the second characteristic index comprises the following steps:
Multiplying the first characteristic index corresponding to each characteristic region with the corresponding second characteristic index to obtain a comprehensive characteristic index corresponding to each characteristic region;
acquiring the number of pixel points in each characteristic area;
Multiplying the comprehensive characteristic index corresponding to each characteristic region by the number of pixel points in the corresponding characteristic region to obtain the degree of abnormality corresponding to each characteristic region;
summing the abnormal degrees corresponding to the characteristic areas to obtain the abnormal degrees corresponding to the sheet metal target image;
And evaluating the polishing quality corresponding to the polishing procedure when the aluminum veneer is produced according to the abnormal degree corresponding to the metal plate target image.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of an aluminum veneer polishing quality evaluation method based on computer assistance.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, but not all embodiments, and all other embodiments obtained by those skilled in the art based on the embodiments of the present invention are within the scope of protection of the embodiments of the present invention.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The embodiment provides an aluminum veneer polishing quality evaluation method based on computer assistance, which is described in detail as follows:
as shown in fig. 1, the method for evaluating the polishing quality of the aluminum veneer based on the computer assistance comprises the following steps:
and S001, acquiring a metal plate target image after a polishing procedure in the production of the aluminum veneer, wherein the metal plate target image is an RGB image.
In this embodiment, the aluminum veneer processing process is generally divided into two steps, namely, sheet metal processing in the first step and spraying in the second step. The sheet metal processing process mainly includes the steps of cutting, flanging, bending, welding, polishing and the like on a sheet metal to process an aluminum veneer into a shape and a size required by construction, the polishing process in the sheet metal processing process possibly causes defects such as scratches, polishing marks or cracks on the surface of the sheet metal due to operation or machine reasons, the defects possibly affect the use effect of the produced aluminum veneer when serious, and the texture structure of a defect area is changed without periodicity the same as that of a normal area when the defects appear on the surface of the sheet metal after polishing, so that the polishing quality of the sheet metal after the polishing process in the processing process of the aluminum veneer is evaluated, and corresponding reference comments are provided for related staff.
In the embodiment, the camera is arranged right above the aluminum veneer manufacturing sheet metal, the camera collects the sheet metal surface image after the polishing procedure when the aluminum veneer is manufactured in a overlooking view angle, the influence of the camera view angle on image collection can be prevented, the precision is improved, the shooting range and the angle of the camera are required to be adjusted according to actual conditions, but the shooting range of the camera can cover the surface of the aluminum veneer manufacturing sheet metal so as to comprehensively detect the surface of the aluminum veneer manufacturing sheet metal.
The processing process environment for producing the aluminum veneer is complex, and more noise influence exists in the environment, so that the embodiment performs image preprocessing operation on the sheet metal surface image after the polishing process, namely, performs filtering processing on the sheet metal surface image after the polishing process through a Gaussian filtering algorithm to obtain a denoised filtered sheet metal surface image, the filtering processing can eliminate noise points in the sheet metal surface image, and because the aluminum veneer surface has the characteristic of illumination reflection, the embodiment performs illumination homogenization processing on the denoised filtered sheet metal surface image by adopting histogram equalization to avoid the influence of illumination non-uniformity on subsequent polishing quality evaluation, the filtered sheet metal surface image after the illumination homogenization processing is recorded as a sheet metal target image after the polishing process when the aluminum veneer is produced, and the sheet metal target image is an RGB image.
And step S002, obtaining each characteristic area corresponding to the sheet metal target image according to the pixel value of each pixel point in the sheet metal target image.
In the embodiment, when a defect area exists on a sheet metal target image, the texture structure of the defect area is changed relative to a normal area, so that pixel values of all pixel points on the sheet metal target image are required to be analyzed to obtain all characteristic areas corresponding to the sheet metal target image, and all the characteristic areas corresponding to the sheet metal target image are used as a basis for subsequently analyzing polishing quality corresponding to the sheet metal target image.
In the embodiment, a sheet metal target image is subjected to graying treatment to obtain a sheet metal gray image corresponding to the sheet metal target image, a DBSCAN clustering algorithm is utilized to cluster all pixel points on the sheet metal gray image to obtain a plurality of categories, the number of the categories is marked as U, the clustering radius is required to be set according to actual conditions, the characteristics of all the pixel points in the same category are mostly similar, namely the gray values of all the pixel points in the same category are similar, the defect area does not exist on the sheet metal gray image in a large amount, so that the category with the largest number of the pixel points is obtained, the category with the largest number of the pixel points is a normal area, the areas corresponding to the other categories except the category with the largest number of the pixel points are marked as all the characteristic areas corresponding to the sheet metal gray image, all the characteristic areas can be the areas with flaws or defects, and all the characteristic areas are further analyzed later, and all the characteristic areas corresponding to the sheet metal target image and the sheet metal gray image are obtained according to all the characteristic areas corresponding to the sheet metal gray image in a one-to one correspondence.
Step S003, obtaining each texture feature index corresponding to each feature region according to the neighborhood pixel point of each pixel point in each feature region in each feature direction, and obtaining a first feature index corresponding to each feature region according to each texture feature index.
In this embodiment, in order to analyze the influence of the polishing process on the surface of the metal plate in the processing process of the aluminum veneer, namely, the polishing quality in the processing process of the aluminum veneer, it is necessary to analyze the neighborhood pixel points of each pixel point in each characteristic region in each characteristic direction to obtain each texture characteristic index corresponding to each characteristic region, then obtain the first characteristic index corresponding to each characteristic region according to each texture characteristic index corresponding to each characteristic region, and use the obtained first characteristic index corresponding to each characteristic region as the basis for subsequently evaluating the polishing quality of the polishing process when producing the aluminum veneer.
(A) According to the neighborhood pixel points of each pixel point in each characteristic region in each characteristic direction, the specific process for obtaining each texture structure characteristic index corresponding to each characteristic region comprises the following steps:
In the embodiment, as the texture information analyzed by different directions has differences, the embodiment can analyze the characteristic areas from multiple directions more accurately by acquiring two neighborhood pixel points of each pixel point in the characteristic areas corresponding to the sheet metal gray level image in the characteristic directions, namely taking each pixel point in the characteristic areas corresponding to the sheet metal gray level image as a center, acquiring left and right neighborhood pixel points of each center point in the characteristic areas corresponding to the sheet metal gray level image in the characteristic directions, only acquiring one neighborhood pixel point of each edge pixel point in the characteristic directions when each pixel point in the characteristic areas corresponding to the sheet metal gray level image is an edge pixel point, interpolation processing is carried out on the non-existing neighborhood pixel point, so as to acquire two neighborhood pixel points of each pixel point in the characteristic areas corresponding to the sheet metal gray level image in the characteristic directions, calculating the left and right neighborhood pixel points of each center point in the characteristic areas corresponding to the sheet metal gray level image in the characteristic areas in the characteristic directions, and constructing the average value of each neighborhood pixel point in the characteristic areas corresponding to the characteristic areas in the characteristic directions according to the gray level value of each pixel point in the sheet metal gray level image in the characteristic areas in the characteristic directions, wherein when each pixel point in the sheet metal gray level image corresponds to the characteristic areas in the characteristic areas is an edge pixel point, the pixel point in the non-existing neighborhood pixel point is not existing, and the pixel point in the pixel point corresponding to the pixel point in the characteristic areas corresponding to the characteristic areas in the characteristic directions is obtained Wherein G is a characteristic descriptor corresponding to a certain pixel point in a certain characteristic area corresponding to the sheet metal gray level image in a certain characteristic direction, G 0 is a gray level value corresponding to the pixel point in the characteristic area,The gray average value of the pixel point in the characteristic region in the characteristic direction is obtained.
In the embodiment, the number of the set characteristic directions is four, namely, a first characteristic direction is 0 degree, a second characteristic direction is 45 degrees, a third characteristic direction is 90 degrees, and a fourth characteristic direction is 135 degrees, so that a first characteristic descriptor corresponding to each pixel point in each characteristic area corresponding to the sheet metal gray level image in the first characteristic direction, a second characteristic descriptor corresponding to each pixel point in each characteristic area in the second characteristic direction, a third characteristic descriptor corresponding to each pixel point in each characteristic area in the third characteristic direction, and a fourth characteristic descriptor corresponding to each pixel point in each characteristic area in the fourth characteristic direction can be obtained.
As other embodiments, other numbers of feature directions or other angles may be set for the feature directions according to the needs, for example, the number of feature directions may be two, and the angles of the feature directions may be 30 degrees and 90 degrees.
In the embodiment, the category number of the first feature descriptors in each feature area corresponding to the sheet metal gray image and the probability of each type of the first feature descriptors in the corresponding feature area in each feature area are obtained, the first texture feature index corresponding to each feature area in the first feature direction is obtained according to the probability of each type of the first feature descriptors in each feature area in the corresponding feature area, and the first texture feature index corresponding to each feature area corresponding to the sheet metal gray image in the first feature direction is calculated according to the following formula:
Wherein B is a first texture feature index corresponding to a certain feature area corresponding to the sheet metal gray level image in a first feature direction, B1 is the number of types of first feature descriptors in the feature area corresponding to the sheet metal gray level image, B1 b is the probability of a B-th type of first feature descriptors in the feature area corresponding to the sheet metal gray level image in the corresponding feature area, B is larger, which indicates that the texture corresponding to the feature area in the first feature direction is more disordered, and the logarithm in the embodiment is 2 as a base, and the unit is a bit.
The method comprises the steps of obtaining the probability of each second feature descriptor in each feature region in a corresponding feature region, obtaining second texture feature indexes corresponding to each feature region in a second feature direction according to the probability of each second feature descriptor in the corresponding feature region in each feature region, obtaining the probability of each third feature descriptor in each corresponding feature region in each feature region, obtaining third texture feature indexes corresponding to each feature region in a third feature direction according to the probability of each third feature descriptor in each feature region, obtaining the probability of each fourth feature descriptor in each feature region in the corresponding feature region, obtaining fourth texture feature indexes corresponding to each feature region in the fourth feature direction according to the probability of each fourth feature descriptor in each feature region, and obtaining the second texture feature indexes, the third texture feature indexes and the fourth texture feature indexes according to the probability of each fourth feature descriptor in each feature region in the corresponding feature region.
(B) According to the characteristic indexes of each texture structure corresponding to each characteristic area, the specific process for obtaining the first characteristic index corresponding to each characteristic area is as follows:
since the above feature directions are manually set, the reliability of the texture feature indexes extracted in different directions is different, so in this embodiment, the pixel points on both sides of the feature directions are analyzed to obtain the reliability of the texture feature indexes corresponding to each feature region. The method comprises the steps of obtaining the position of a central point corresponding to each characteristic area, then making a straight line with the same angle as the corresponding angle of the first characteristic direction through the central point corresponding to each characteristic area, recording the straight line as a first straight line corresponding to each first central point corresponding to each characteristic area in the first characteristic direction, obtaining pixel points in the corresponding characteristic area on the first straight line corresponding to each characteristic area in the first characteristic direction, recording the pixel points in the corresponding characteristic area on the first straight line corresponding to each characteristic area in the first characteristic direction as first central points corresponding to each characteristic area in the first characteristic direction, then making a straight line perpendicular to the first straight line corresponding to each characteristic area in the first characteristic direction through each first central point corresponding to each characteristic area in the first characteristic direction, obtaining N pixel points corresponding to each first central point corresponding to each characteristic area in the first characteristic direction and N pixel points corresponding to the left side of each first central point on the vertical line, constructing a sequence of the N pixel points corresponding to each first central point on the left side of each first central point and N pixel points corresponding to each first central point on the right side of the first central point on the first characteristic direction according to the first central point sequence of the N pixel points corresponding to the left side of each first central point corresponding to N pixel points corresponding to each first central point on the right side of each first central point on the vertical line, the method comprises the steps of constructing a Gaussian mixture model corresponding to each first center point of each characteristic region in a first characteristic direction, calculating K-L divergences between the Gaussian mixture models corresponding to any two first center points of each characteristic region in the first characteristic direction to obtain each first divergences corresponding to each characteristic region in the first characteristic direction, calculating the K-L divergences according to the following formula, wherein the calculation process of the K-L divergences is not described in detail in the prior art, summing the first divergences corresponding to each characteristic region in the first characteristic direction, then obtaining an average value to obtain a first target divergences corresponding to each characteristic region in the first characteristic direction, calculating the reliability degree of a first texture characteristic index corresponding to each characteristic region in the first characteristic direction according to the first target divergences corresponding to each characteristic region in the first characteristic direction, and calculating the reliability degree of the first texture characteristic index corresponding to each characteristic region in the first characteristic direction according to the following formula:
wherein C i is the reliability of the first texture feature index corresponding to the ith feature area in the first feature direction, C1 i is the first target divergence corresponding to the ith feature area in the first feature direction, w is a set parameter, w1 is a set parameter, C i is larger, the reliability of the first texture feature index corresponding to the ith feature area in the first feature direction is higher, and C1 i is larger, and C i is larger.
In this example, the values of the setting parameters w and w1 are both (0, 1), w is set to 0.6, and w1 is set to 0.5, and as another embodiment, the specific values of the setting parameters need to be set according to the actual situation.
In this embodiment, the reliability of the second texture feature index corresponding to each feature region in the second feature direction, the reliability of the third texture feature index corresponding to each feature region in the third feature direction, and the reliability of the fourth texture feature index corresponding to each feature region in the fourth feature direction can be obtained by analogy, and the reliability of the second texture feature index corresponding to each feature region in the second feature direction, the reliability of the third texture feature index corresponding to each feature region in the third feature direction, and the reliability of the fourth texture feature index corresponding to each feature region in the fourth feature direction are the same as the reliability of the first texture feature index corresponding to each feature region in the first feature direction.
In this embodiment, the result of multiplying the corresponding first texture feature indexes of each feature area in the first feature direction is recorded as the corresponding first target texture feature index of each feature area, and then the second target texture feature index corresponding to each feature area is obtained by analogy, the third target texture feature index corresponding to each feature area and the fourth target texture feature index corresponding to each feature area are obtained, the first target texture feature index, the second target texture feature index, the third target texture feature index and the fourth target texture feature index corresponding to each feature area are summed, the result of summation is recorded as the corresponding first feature index of each feature area, and the larger the value of the corresponding first feature index of each feature area indicates that the texture information in the corresponding feature area is more disordered and more disordered, the distribution is also more disordered, and the higher the abnormality degree in the corresponding feature area is, the more serious the flaws are.
Step S004, according to the R, G, B channel values corresponding to each pixel point in each characteristic area, obtaining an R channel intensity difference index, a G channel intensity difference index and a B channel intensity difference index corresponding to each characteristic area.
In this embodiment, the first characteristic index corresponding to each characteristic region reflects texture information, and when the texture distribution in the defect region is relatively uniform, the reliability of the quality of the sheet metal region corresponding to the sheet metal target image is relatively low by only the first characteristic index, that is, the reliability of the polishing quality in the processing process of the aluminum veneer is low, so that the degree of color difference between each characteristic region needs to be analyzed to further reflect the abnormal degree of each characteristic region, therefore, the embodiment analyzes the values of R, G, B channels corresponding to each pixel point in each characteristic region to obtain an R channel intensity difference index, a G channel intensity difference index and a B channel intensity difference index corresponding to each characteristic region, and uses the obtained R channel intensity difference index, G channel intensity difference index and B channel intensity difference index corresponding to each characteristic region as the basis for obtaining the second characteristic index corresponding to each characteristic region by subsequent analysis.
In the embodiment, the sheet metal target image is subjected to channel separation to obtain image data of R, G, B channels corresponding to each feature area, namely, R, G, B channel values corresponding to each pixel point in each feature area are obtained, the average value of pixel values of each pixel point in each feature area corresponding to an R channel is calculated, the average value of pixel values of each pixel point in each feature area corresponding to a G channel is calculated, the average value of pixel values of each pixel point in each feature area corresponding to a B channel is calculated, and the average value of pixel values of each pixel point in each feature area corresponding to the R channel, the average value of pixel values of each pixel point in each feature area corresponding to the G channel and the average value of pixel values of each pixel point in each feature area corresponding to the B channel are respectively recorded as R channel strength, G channel strength and B channel strength corresponding to each feature area.
According to the difference between R channel intensities, the difference between G channel intensities and the difference between B channel intensities corresponding to any two characteristic areas and the central pixel point in any two characteristic areas, R channel intensity difference indexes, G channel intensity difference indexes and B channel intensity difference indexes corresponding to the characteristic areas are obtained, and R channel intensity difference indexes corresponding to the characteristic areas are calculated according to the following formulas:
S i R is an R channel intensity difference index corresponding to an ith feature area in a sheet metal target image, I is the number of feature areas in the sheet metal target image, L i,j is the Euclidean distance between a central pixel point corresponding to the ith feature area in the sheet metal target image and a central pixel point corresponding to the corresponding jth feature area, T is a set parameter, sigma is a set parameter, H i R is the R channel intensity corresponding to the ith feature area in the sheet metal target image, H j R is the R channel intensity corresponding to the jth feature area in the sheet metal target image, when S i R is larger, the difference between the R channel value corresponding to each pixel point in the ith feature area and the R channel value corresponding to each pixel point in other feature areas is larger, namely the larger the color difference between the ith feature area and the R channel corresponding to the rest feature areas is indicated, and when the color difference is larger, the degree of abnormality of the ith feature area is higher.
In this example, the value of the setting parameter T is set to 2 and the value of the setting parameter σ is set to 5, and as another embodiment, another value may be set for the setting parameter according to the actual situation.
In this embodiment, the R channel intensity difference index corresponding to each feature region may be obtained through the above process, and so on, to obtain the G channel intensity difference index and the B channel intensity difference index corresponding to each feature region, where the calculation methods of the G channel intensity difference index and the B channel intensity difference index corresponding to each feature region are the same as those of the R channel intensity difference index corresponding to each feature region, so that detailed description is omitted.
And step S005, obtaining a second characteristic index corresponding to each characteristic region according to the R channel intensity difference index, the G channel intensity difference index and the B channel intensity difference index.
In the embodiment, the first characteristic index corresponding to the characteristic region reflects texture information, the R channel intensity difference index, the G channel intensity difference index and the B channel intensity difference index reflect color information, and when the R channel intensity difference index, the G channel intensity difference index and the B channel intensity difference index corresponding to each characteristic region are larger, the color difference degree between the corresponding characteristic region and other characteristic regions is higher, namely the abnormal degree of the corresponding characteristic region is higher, so that the embodiment obtains the second characteristic index corresponding to each characteristic region according to the R channel intensity difference index, the G channel intensity difference index and the B channel intensity difference index, and takes the second characteristic index corresponding to each characteristic region as the basis of polishing quality corresponding to a polishing procedure when the aluminum veneer is produced in a subsequent evaluation mode.
Calculating the sum of the R channel intensity difference index, the G channel intensity difference index and the B channel intensity difference index corresponding to each characteristic region to obtain a comprehensive difference index corresponding to each characteristic region, obtaining a second characteristic index corresponding to each characteristic region according to the comprehensive difference index, the R channel intensity difference index, the G channel intensity difference index and the B channel intensity difference index corresponding to each characteristic region, and calculating the second characteristic index corresponding to each characteristic region according to the following formula:
Wherein, The method comprises the steps that the method is characterized in that the method is used for obtaining a second characteristic index corresponding to an ith characteristic region in a sheet metal target image, S i R is used for obtaining an R channel intensity difference index corresponding to the ith characteristic region in the sheet metal target image, S i G is used for obtaining a G channel intensity difference index corresponding to the ith characteristic region in the sheet metal target image, S i B is used for obtaining a B channel intensity difference index corresponding to the ith characteristic region in the sheet metal target image, and S i is used for obtaining a comprehensive difference index corresponding to the ith characteristic region in the sheet metal target image; the larger the color difference degree between the ith characteristic area and other characteristic areas in the sheet metal target image is, the higher the degree of color difference between the ith characteristic area and other characteristic areas is, namely the higher the degree of abnormality of the ith characteristic area is.
And step S006, evaluating the polishing quality corresponding to the polishing procedure when the aluminum veneer is produced according to the first characteristic index and the second characteristic index.
In the embodiment, the first characteristic index and the second characteristic index corresponding to each characteristic region can reflect the abnormal degree of the corresponding characteristic region, and the abnormal degree of the characteristic region can reflect the polishing quality of the polishing process when the aluminum veneer is produced, so that the purpose of evaluating the polishing quality of the polishing process when the aluminum veneer is produced is achieved by analyzing the first characteristic index and the second characteristic index corresponding to each characteristic region.
In the embodiment, a first characteristic index and a second characteristic index corresponding to each characteristic area are subjected to normalization processing, the first characteristic index corresponding to each characteristic area after the normalization processing is multiplied by the corresponding second characteristic index to obtain a comprehensive characteristic index corresponding to each characteristic area, the number of pixels in each characteristic area is obtained, the comprehensive characteristic index corresponding to each characteristic area is multiplied by the number of pixels in the corresponding characteristic area to obtain an abnormality degree corresponding to each characteristic area, the abnormality degrees corresponding to each characteristic area are summed to obtain an abnormality degree corresponding to a sheet metal target image, the abnormality degree corresponding to the sheet metal target image is subjected to normalization processing, whether the abnormality degree corresponding to the sheet metal target image after the normalization processing is larger than a preset threshold value or not is judged, if yes, the polishing quality of a polishing procedure is not qualified when an aluminum veneer is produced is judged, the appearance and the service life of the produced aluminum veneer are affected, and the preset threshold value needs to be determined according to actual conditions.
The aluminum veneer polishing quality evaluation system based on the computer assistance of the embodiment comprises a memory and a processor, wherein the processor executes a computer program stored in the memory to realize the aluminum veneer polishing quality evaluation method based on the computer assistance.
The embodiment has the advantages that neighborhood pixel points of each pixel point in each characteristic area in each characteristic direction are used as the basis for obtaining each texture characteristic index corresponding to each characteristic area, each texture characteristic index is used as the basis for obtaining a first characteristic index corresponding to each characteristic area, the values of R, G, B channels corresponding to each pixel point in each characteristic area are used as the basis for obtaining R channel intensity difference index, G channel intensity difference index and B channel intensity difference index corresponding to each characteristic area, R channel intensity difference index, G channel intensity difference index and B channel intensity difference index are used as the basis for obtaining a second characteristic index corresponding to each characteristic area, and the first characteristic index and the second characteristic index are used as the basis for evaluating polishing quality of polishing procedures when aluminum veneers are produced. The method utilizes a computer to carry out aided design and processing, and can be applied to novel software and novel technical service. Compared with a mode of evaluating the polishing quality of the aluminum veneer based on manual visual inspection, the method and the device can evaluate the polishing quality corresponding to the polishing procedure in the aluminum veneer production process more reliably, and are higher in working efficiency of evaluating the polishing quality corresponding to the polishing procedure.
The foregoing embodiments are merely illustrative of the technical solutions of the present application, and not restrictive, and although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that modifications may still be made to the technical solutions described in the foregoing embodiments or equivalent substitutions of some technical features thereof, and that such modifications or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims (2)
1. The aluminum veneer polishing quality evaluation method based on the computer assistance is characterized by comprising the following steps of:
Obtaining a metal plate target image after a polishing procedure in the production of an aluminum veneer, wherein the metal plate target image is an RGB image;
according to the pixel values of each pixel point in the sheet metal target image, obtaining each characteristic area corresponding to the sheet metal target image;
Obtaining each texture feature index corresponding to each feature region according to the neighborhood pixel points of each pixel point in each feature region in each feature direction;
Obtaining R channel intensity difference indexes, G channel intensity difference indexes and B channel intensity difference indexes corresponding to the characteristic areas according to the R, G, B channel values corresponding to the pixel points in the characteristic areas;
Obtaining a second characteristic index corresponding to each characteristic region according to the R channel intensity difference index, the G channel intensity difference index and the B channel intensity difference index;
according to the first characteristic index and the second characteristic index, evaluating polishing quality corresponding to polishing procedures during aluminum veneer production;
the method for obtaining each characteristic region corresponding to the sheet metal target image according to the pixel value of each pixel point in the sheet metal target image comprises the following steps:
carrying out graying treatment on the sheet metal target image to obtain a sheet metal gray image corresponding to the sheet metal target image;
clustering each pixel point on the sheet metal gray level image by using a DBSCAN clustering algorithm;
Acquiring the category with the largest number of pixel points, and marking the areas corresponding to the categories except the category with the largest number of pixel points as each characteristic area corresponding to the sheet metal gray level image;
according to each characteristic region corresponding to the sheet metal gray level image, each characteristic region corresponding to the sheet metal target image is obtained;
the method for obtaining the characteristic index of each texture structure corresponding to each characteristic region according to the neighborhood pixel points of each pixel point in each characteristic region in each characteristic direction comprises the following steps:
acquiring each characteristic direction corresponding to a sheet metal target image and angles corresponding to each characteristic direction;
Acquiring neighborhood pixel points of each pixel point in each characteristic region in each characteristic direction;
Calculating the average value of the gray values of the neighborhood pixel points of each pixel point in each characteristic region in each characteristic direction to obtain the gray average value of each pixel point in each characteristic region in each characteristic direction;
According to the gray values corresponding to the pixel points in the characteristic areas and the gray average value of the pixel points in the characteristic areas in the characteristic directions, constructing and obtaining characteristic descriptors corresponding to the pixel points in the characteristic areas in the characteristic directions;
Acquiring each feature descriptor corresponding to each feature region in each feature direction and the category number of the feature descriptors corresponding to each feature region in each feature direction;
Obtaining the probability of each feature descriptor of each feature region in each feature direction in each feature descriptor of each type in the corresponding feature region in the corresponding feature direction according to each feature descriptor of each feature region in each feature direction and the number of types of feature descriptors of each feature region in each feature direction;
obtaining texture structure characteristic indexes corresponding to each characteristic region according to the probability;
the expression of the texture structure characteristic index corresponding to each characteristic region is as follows:
Wherein B i,m represents texture feature index of the ith feature region in the mth feature direction, B1 i,m,b represents probability of the B-th class feature descriptor of the ith feature region in the mth feature direction, B1 i,m represents class number of feature descriptors of the ith feature region in the mth feature direction, log () represents logarithmic function based on 2;
the method for obtaining the first characteristic index corresponding to each characteristic region according to the characteristic index of each texture structure comprises the following steps:
Acquiring the center point positions corresponding to the characteristic areas;
making straight lines with the same angles as the corresponding angles of the characteristic directions through the center points corresponding to the characteristic areas, and marking the straight lines as first straight lines corresponding to the characteristic areas in the characteristic directions;
Acquiring each pixel point in a corresponding characteristic region of each characteristic region on a first straight line corresponding to each characteristic direction, and marking each pixel point in the corresponding characteristic region of each characteristic region on the first straight line corresponding to each characteristic direction as each first center point of each characteristic region corresponding to each characteristic direction;
making a straight line perpendicular to a first straight line corresponding to the corresponding characteristic region in each characteristic direction by passing through each first center point corresponding to each characteristic region in each characteristic direction, so as to obtain a perpendicular corresponding to each first center point corresponding to each characteristic region in each characteristic direction;
according to the pixel points on the vertical line, constructing and obtaining pixel point sequences corresponding to first center points corresponding to the characteristic areas in the characteristic directions;
According to the gray value in the pixel point sequence, constructing and obtaining a Gaussian mixture model corresponding to each first center point of each characteristic region in each characteristic direction;
calculating the K-L divergence between the Gaussian mixture models corresponding to any two first center points of each characteristic region in each characteristic direction to obtain each first divergence of each characteristic region in each characteristic direction;
Summing the first divergences corresponding to the characteristic regions in the characteristic directions, and then obtaining an average value to obtain first target divergences corresponding to the characteristic regions in the characteristic directions;
According to the first target divergence, calculating to obtain the reliability degree of each texture structure characteristic index corresponding to each characteristic region in each characteristic direction;
obtaining each target texture feature index corresponding to each feature region according to the reliability degree of each texture feature index and each texture feature index;
obtaining a first characteristic index corresponding to each characteristic region according to the characteristic index of each target texture structure;
The expression of the first characteristic index corresponding to each characteristic region is as follows:
Wherein K i represents a first characteristic index of the ith characteristic region, C i,m represents the reliability of the texture characteristic index corresponding to the ith characteristic region in the mth characteristic direction, B i,m represents the texture characteristic index of the ith characteristic region in the mth characteristic direction, C1 i,m represents a first target divergence corresponding to the ith characteristic region in the mth characteristic direction, w is a set parameter, w1 is a set parameter, M represents the number of characteristic directions, and C i,m×Bi,m represents the target texture characteristic index of the ith characteristic region in the mth characteristic direction;
The method for obtaining the R channel intensity difference index, the G channel intensity difference index and the B channel intensity difference index corresponding to each characteristic region according to the R, G, B channel values corresponding to each pixel point in each characteristic region comprises the following steps:
acquiring the values of R, G, B channels corresponding to each pixel point in each characteristic area and the central pixel point corresponding to each characteristic area;
obtaining R channel intensity, G channel intensity and B channel intensity corresponding to each characteristic region according to the average value of pixel values of each pixel point in each characteristic region corresponding to the R channel, the average value of pixel values of each pixel point in each characteristic region corresponding to the G channel and the average value of pixel values of each pixel point in each characteristic region corresponding to the B channel;
Obtaining R channel intensity difference indexes, G channel intensity difference indexes and B channel intensity difference indexes corresponding to the feature areas according to the differences among the R channel intensities, the G channel intensities and the B channel intensities corresponding to the two feature areas and the center pixel point in the two feature areas;
and calculating R channel intensity difference indexes corresponding to each characteristic region according to the following formula:
Wherein S i R is an R channel intensity difference index corresponding to an ith feature region in the sheet metal target image, I is the number of feature regions in the sheet metal target image, L i,j is the euclidean distance between a center pixel point corresponding to the ith feature region in the sheet metal target image and a center pixel point corresponding to the corresponding jth feature region, T is a set parameter, σ is a set parameter, H i R is an R channel intensity corresponding to the ith feature region in the sheet metal target image, and H j R is an R channel intensity corresponding to the jth feature region in the sheet metal target image;
the method for obtaining the second characteristic index corresponding to each characteristic region according to the R channel intensity difference index, the G channel intensity difference index and the B channel intensity difference index comprises the following steps:
Calculating the sum of the R channel intensity difference index, the G channel intensity difference index and the B channel intensity difference index corresponding to each characteristic region to obtain a comprehensive difference index corresponding to each characteristic region;
Obtaining a second characteristic index corresponding to each characteristic region according to the comprehensive difference index, the R channel intensity difference index, the G channel intensity difference index and the B channel intensity difference index corresponding to each characteristic region;
The expression of the second characteristic index corresponding to each characteristic region is as follows:
Wherein, The method comprises the steps that the method is characterized in that the method is used for obtaining a second characteristic index corresponding to an ith characteristic region in a sheet metal target image, S i R is used for obtaining an R channel intensity difference index corresponding to the ith characteristic region in the sheet metal target image, S i G is used for obtaining a G channel intensity difference index corresponding to the ith characteristic region in the sheet metal target image, S i B is used for obtaining a B channel intensity difference index corresponding to the ith characteristic region in the sheet metal target image, and S i is used for obtaining a comprehensive difference index corresponding to the ith characteristic region in the sheet metal target image;
The method for evaluating polishing quality corresponding to polishing procedures during aluminum veneer production according to the first characteristic index and the second characteristic index comprises the following steps:
Multiplying the first characteristic index corresponding to each characteristic region with the corresponding second characteristic index to obtain a comprehensive characteristic index corresponding to each characteristic region;
acquiring the number of pixel points in each characteristic area;
Multiplying the comprehensive characteristic index corresponding to each characteristic region by the number of pixel points in the corresponding characteristic region to obtain the degree of abnormality corresponding to each characteristic region;
summing the abnormal degrees corresponding to the characteristic areas to obtain the abnormal degrees corresponding to the sheet metal target image;
And evaluating the polishing quality corresponding to the polishing procedure when the aluminum veneer is produced according to the abnormal degree corresponding to the metal plate target image.
2. A computer-aided aluminum veneer polishing quality assessment system comprising a memory and a processor, wherein the processor executes a computer program stored in the memory to implement the computer-aided aluminum veneer polishing quality assessment method of claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210336324.7A CN114820459B (en) | 2022-03-31 | 2022-03-31 | Computer-aided aluminum veneer polishing quality assessment method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210336324.7A CN114820459B (en) | 2022-03-31 | 2022-03-31 | Computer-aided aluminum veneer polishing quality assessment method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114820459A CN114820459A (en) | 2022-07-29 |
| CN114820459B true CN114820459B (en) | 2025-01-21 |
Family
ID=82532568
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210336324.7A Active CN114820459B (en) | 2022-03-31 | 2022-03-31 | Computer-aided aluminum veneer polishing quality assessment method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114820459B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115170446B (en) * | 2022-09-06 | 2022-11-18 | 聊城市洛溪信息科技有限公司 | Self-adaptive metal plate image enhancement method based on morphological processing |
| CN116630307B (en) * | 2023-07-20 | 2023-09-19 | 济宁市华祥石墨制品有限公司 | Graphite towbar polishing quality evaluation system, device and computer readable storage medium |
| CN118447025A (en) * | 2024-07-08 | 2024-08-06 | 江西鑫隆泰建材工业有限公司 | Method, device and equipment for evaluating processing quality of aluminum veneer |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111681181A (en) * | 2020-05-27 | 2020-09-18 | 浙江工贸职业技术学院 | Method for evaluating fabric surface pilling degree |
| CN113808138A (en) * | 2021-11-22 | 2021-12-17 | 山东鹰联光电科技股份有限公司 | Artificial intelligence-based wire and cable surface defect detection method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109670532B (en) * | 2018-11-23 | 2022-12-09 | 腾讯医疗健康(深圳)有限公司 | Method, device and system for identifying abnormality of biological organ tissue image |
| CN114170208A (en) * | 2021-12-14 | 2022-03-11 | 武汉福旺家包装有限公司 | Paper product defect detection method based on artificial intelligence |
-
2022
- 2022-03-31 CN CN202210336324.7A patent/CN114820459B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111681181A (en) * | 2020-05-27 | 2020-09-18 | 浙江工贸职业技术学院 | Method for evaluating fabric surface pilling degree |
| CN113808138A (en) * | 2021-11-22 | 2021-12-17 | 山东鹰联光电科技股份有限公司 | Artificial intelligence-based wire and cable surface defect detection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114820459A (en) | 2022-07-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114820459B (en) | Computer-aided aluminum veneer polishing quality assessment method and system | |
| Miao et al. | Cost-effective system for detection and quantification of concrete surface cracks by combination of convolutional neural network and image processing techniques | |
| CN115063409B (en) | Method and system for detecting surface material of mechanical cutter | |
| CN117315289B (en) | Aeroengine blade contour edge detection method based on image processing | |
| CN115082418A (en) | Precise identification method for automobile parts | |
| CN106778541B (en) | A kind of identification in the multilayer beam China and foreign countries beam hole of view-based access control model and localization method | |
| CN110689524B (en) | No-reference online image definition evaluation method and system | |
| CN115965623B (en) | Surface flaw detection method and system in transformer production | |
| CN117011292B (en) | Method for rapidly detecting surface quality of composite board | |
| CN115294144B (en) | Method for identifying surface defects of furniture composite board | |
| CN115205290A (en) | Online detection method and system for PCB production process | |
| CN115063423A (en) | Mechanical casting cold and hot crack self-adaptive identification method based on computer vision | |
| CN114565563B (en) | Color steel plate surface abnormity detection method based on artificial intelligence | |
| CN113155839A (en) | Steel plate outer surface defect online detection method based on machine vision | |
| Chaudhari et al. | Steel surface defect detection using glcm, gabor wavelet, hog, and random forest classifier | |
| CN117197138B (en) | Computer host shell scratch detection method based on image characteristics | |
| CN116630329A (en) | Online visual detection method for multi-axis multi-channel numerical control system | |
| CN111415339A (en) | Image defect detection method for complex texture industrial product | |
| CN113689426A (en) | Fire-fighting apparatus defect detection method based on image processing | |
| CN119274001B (en) | Quantitative recognition method of test paper color change based on improved MSRCR and random forest | |
| CN115131250A (en) | Intelligent machine tool component identification method for machine tool assembly | |
| CN117808809B (en) | Visual inspection method and system for wafer surface defects | |
| CN117314901B (en) | A scale-adaptive neural network system for chip detection | |
| CN116703922B (en) | Intelligent positioning method and system for sawn timber defect position | |
| CN116681703B (en) | Intelligent switch quality rapid detection method |
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 |